Building a Multi-Agent On-Call Copilot with Microsoft Agent Framework
Four AI agents, one incident payload, structured triage in under 60 seconds powered by Microsoft Agent Framework and Foundry Hosted Agents. Multi-Agent Microsoft Agent Framework Foundry Hosted Agents Python SRE / Incident Response When an incident fires at 3 AM, every second the on-call engineer spends piecing together alerts, logs, and metrics is a second not spent fixing the problem. What if an AI system could ingest the raw incident signals and hand you a structured triage, a Slack update, a stakeholder brief, and a draft post-incident report, all in under 10 seconds? That’s exactly what On-Call Copilot does. In this post, we’ll walk through how we built it using the Microsoft Agent Framework, deployed it as a Foundry Hosted Agent, and discuss the key design decisions that make multi-agent orchestration practical for production workloads. The full source code is open-source on GitHub. You can deploy your own instance with a single azd up . Why Multi-Agent? The Problem with Single-Prompt Triage Early AI incident assistants used a single large prompt: “Here is the incident. Give me root causes, actions, a Slack message, and a post-incident report.” This approach has two fundamental problems: Context overload. A real incident may have 800 lines of logs, 10 alert lines, and dense metrics. Asking one model to process everything and produce four distinct output formats in a single turn pushes token limits and degrades quality. Conflicting concerns. Triage reasoning and communication drafting are cognitively different tasks. A model optimised for structured JSON analysis often produces stilted Slack messages—and vice versa. The fix is specialisation: decompose the task into focused agents, give each agent a narrow instruction set, and run them in parallel. This is the core pattern that the Microsoft Agent Framework makes easy. Architecture: Four Agents Running Concurrently On-Call Copilot is deployed as a Foundry Hosted Agent—a containerised Python service running on Microsoft Foundry’s managed infrastructure. The core orchestrator uses ConcurrentBuilder from the Microsoft Agent Framework SDK to run four specialist agents in parallel via asyncio.gather() . All four panels populated simultaneously: Triage (red), Summary (blue), Comms (green), PIR (purple). Architecture: The orchestrator runs four specialist agents concurrently via asyncio.gather(), then merges their JSON fragments into a single response. All four agents The solution share a single Azure OpenAI Model Router deployment. Rather than hardcoding gpt-4o or gpt-4o-mini , Model Router analyses request complexity and routes automatically. A simple triage prompt costs less; a long post-incident synthesis uses a more capable model. One deployment name, zero model-selection code. Meet the Four Agents 🔍 Triage Agent Root cause analysis, immediate actions, missing data identification, and runbook alignment. suspected_root_causes · immediate_actions · missing_information · runbook_alignment 📋 Summary Agent Concise incident narrative: what happened and current status (ONGOING / MITIGATED / RESOLVED). summary.what_happened · summary.current_status 📢 Comms Agent Audience-appropriate communications: Slack channel update with emoji conventions, plus a non-technical stakeholder brief. comms.slack_update · comms.stakeholder_update 📝 PIR Agent Post-incident report: chronological timeline, quantified customer impact, and specific prevention actions. post_incident_report.timeline · .customer_impact · .prevention_actions The Code: Building the Orchestrator The entry point is remarkably concise. ConcurrentBuilder handles all the async wiring—you just declare the agents and let the framework handle parallelism, error propagation, and response merging. main.py — Orchestrator from agent_framework import ConcurrentBuilder from agent_framework.azure import AzureOpenAIChatClient from azure.ai.agentserver.agentframework import from_agent_framework from azure.identity import DefaultAzureCredential, get_bearer_token_provider from app.agents.triage import TRIAGE_INSTRUCTIONS from app.agents.comms import COMMS_INSTRUCTIONS from app.agents.pir import PIR_INSTRUCTIONS from app.agents.summary import SUMMARY_INSTRUCTIONS _credential = DefaultAzureCredential() _token_provider = get_bearer_token_provider( _credential, "https://cognitiveservices.azure.com/.default" ) def create_workflow_builder(): """Create 4 specialist agents and wire them into a ConcurrentBuilder.""" triage = AzureOpenAIChatClient(ad_token_provider=_token_provider).create_agent( instructions=TRIAGE_INSTRUCTIONS, name="triage-agent", ) summary = AzureOpenAIChatClient(ad_token_provider=_token_provider).create_agent( instructions=SUMMARY_INSTRUCTIONS, name="summary-agent", ) comms = AzureOpenAIChatClient(ad_token_provider=_token_provider).create_agent( instructions=COMMS_INSTRUCTIONS, name="comms-agent", ) pir = AzureOpenAIChatClient(ad_token_provider=_token_provider).create_agent( instructions=PIR_INSTRUCTIONS, name="pir-agent", ) return ConcurrentBuilder().participants([triage, summary, comms, pir]) def main(): builder = create_workflow_builder() from_agent_framework(builder.build).run() # starts on port 8088 if __name__ == "__main__": main() Key insight: DefaultAzureCredential means there are no API keys anywhere in the codebase. The container uses managed identity in production; local development uses your az login session. The same code runs in both environments without modification. Agent Instructions: Prompts as Configuration Each agent receives a tightly scoped system prompt that defines its output schema and guardrails. Here’s the Triage Agent—the most complex of the four: app/agents/triage.py TRIAGE_INSTRUCTIONS = """\ You are the **Triage Agent**, an expert Site Reliability Engineer specialising in root cause analysis and incident response. ## Task Analyse the incident data and return a single JSON object with ONLY these keys: { "suspected_root_causes": [ { "hypothesis": "string – concise root cause hypothesis", "evidence": ["string – supporting evidence from the input"], "confidence": 0.0 // 0-1, how confident you are } ], "immediate_actions": [ { "step": "string – concrete action with runnable command if applicable", "owner_role": "oncall-eng | dba | infra-eng | platform-eng", "priority": "P0 | P1 | P2 | P3" } ], "missing_information": [ { "question": "string – what data is missing", "why_it_matters": "string – why this data would help" } ], "runbook_alignment": { "matched_steps": ["string – runbook steps that match the situation"], "gaps": ["string – gaps or missing runbook coverage"] } } ## Guardrails 1. **No secrets** – redact any credential-like material as [REDACTED]. 2. **No hallucination** – if data is insufficient, set confidence to 0 and add entries to missing_information. 3. **Diagnostic suggestions** – when data is sparse, include diagnostic steps in immediate_actions. 4. **Structured output only** – return ONLY valid JSON, no prose. """ The Comms Agent follows the same pattern but targets a different audience: app/agents/comms.py COMMS_INSTRUCTIONS = """\ You are the **Comms Agent**, an expert incident communications writer. ## Task Return a single JSON object with ONLY this key: { "comms": { "slack_update": "Slack-formatted message with emoji, severity, status, impact, next steps, and ETA", "stakeholder_update": "Non-technical summary for executives. Focus on business impact and resolution." } } ## Guidelines - Slack: Use :rotating_light: for active SEV1/2, :warning: for degraded, :white_check_mark: for resolved. - Stakeholder: No jargon. Translate to business impact. - Tone: Calm, factual, action-oriented. Never blame individuals. - Structured output only – return ONLY valid JSON, no prose. """ Instructions as config, not code. Agent behaviour is defined entirely by instruction text strings. A non-developer can refine agent behaviour by editing the prompt and redeploying no Python changes needed. The Incident Envelope: What Goes In The agent accepts a single JSON envelope. It can come from a monitoring alert webhook, a PagerDuty payload, or a manual CLI invocation: Incident Input (JSON) { "incident_id": "INC-20260217-002", "title": "DB connection pool exhausted — checkout-api degraded", "severity": "SEV1", "timeframe": { "start": "2026-02-17T14:02:00Z", "end": null }, "alerts": [ { "name": "DatabaseConnectionPoolNearLimit", "description": "Connection pool at 99.7% on orders-db-primary", "timestamp": "2026-02-17T14:03:00Z" } ], "logs": [ { "source": "order-worker", "lines": [ "ERROR: connection timeout after 30s (attempt 3/3)", "WARN: pool exhausted, queueing request (queue_depth=847)" ] } ], "metrics": [ { "name": "db_connection_pool_utilization_pct", "window": "5m", "values_summary": "Jumped from 22% to 99.7% at 14:03Z" } ], "runbook_excerpt": "Step 1: Check DB connection dashboard...", "constraints": { "max_time_minutes": 15, "environment": "production", "region": "swedencentral" } } Declaring the Hosted Agent The agent is registered with Microsoft Foundry via a declarative agent.yaml file. This tells Foundry how to discover and route requests to the container: agent.yaml kind: hosted name: oncall-copilot description: | Multi-agent hosted agent that ingests incident signals and runs 4 specialist agents concurrently via Microsoft Agent Framework ConcurrentBuilder. metadata: tags: - Azure AI AgentServer - Microsoft Agent Framework - Multi-Agent - Model Router protocols: - protocol: responses environment_variables: - name: AZURE_OPENAI_ENDPOINT value: ${AZURE_OPENAI_ENDPOINT} - name: AZURE_OPENAI_CHAT_DEPLOYMENT_NAME value: model-router The protocols: [responses] declaration exposes the agent via the Foundry Responses API on port 8088. Clients can invoke it with a standard HTTP POST no custom API needed. Invoking the Agent Once deployed, you can invoke the agent with the project’s built-in scripts or directly via curl : CLI / curl # Using the included invoke script python scripts/invoke.py --demo 2 # multi-signal SEV1 demo python scripts/invoke.py --scenario 1 # Redis cluster outage # Or with curl directly TOKEN=$(az account get-access-token \ --resource https://ai.azure.com --query accessToken -o tsv) curl -X POST \ "$AZURE_AI_PROJECT_ENDPOINT/openai/responses?api-version=2025-05-15-preview" \ -H "Authorization: Bearer $TOKEN" \ -H "Content-Type: application/json" \ -d '{ "input": [ {"role": "user", "content": "<incident JSON here>"} ], "agent": { "type": "agent_reference", "name": "oncall-copilot" } }' The Browser UI The project includes a zero-dependency browser UI built with plain HTML, CSS, and vanilla JavaScript—no React, no bundler. A Python http.server backend proxies requests to the Foundry endpoint. The empty state. Quick-load buttons pre-populate the JSON editor with demo incidents or scenario files. Demo 1 loaded: API Gateway 5xx spike, SEV3. The JSON is fully editable before submitting. Agent Output Panels Triage: Root causes ranked by confidence. Evidence is collapsed under each hypothesis. Triage: Immediate actions with P0/P1/P2 priority badges and owner roles. Comms: Slack card with emoji substitution and a stakeholder executive summary. PIR: Chronological timeline with an ONGOING marker, customer impact in a red-bordered box. Performance: Parallel Execution Matters Incident Type Complexity Parallel Latency Sequential (est.) Single alert, minimal context (SEV4) Low 4–6 s ~16 s Multi-signal, logs + metrics (SEV2) Medium 7–10 s ~28 s Full SEV1 with long log lines High 10–15 s ~40 s Post-incident synthesis (resolved) High 10–14 s ~38 s asyncio.gather() running four independent agents cuts total latency by 3–4× compared to sequential execution. For a SEV1 at 3 AM, that’s the difference between a 10-second AI-powered head start and a 40-second wait. Five Key Design Decisions Parallel over sequential Each agent is independent and processes the full incident payload in isolation. ConcurrentBuilder with asyncio.gather() is the right primitive—no inter-agent dependencies, no shared state. JSON-only agent instructions Every agent returns only valid JSON with a defined schema. The orchestrator merges fragments with merged.update(agent_output) . No parsing, no extraction, no post-processing. No hardcoded model names AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=model-router is the only model reference. Model Router selects the best model at runtime based on prompt complexity. When new models ship, the agent gets better for free. DefaultAzureCredential everywhere No API keys. No token management code. Managed identity in production, az login in development. Same code, both environments. Instructions as configuration Each agent’s system prompt is a plain Python string. Behaviour changes are text edits, not code logic. A non-developer can refine prompts and redeploy. Guardrails: Built into the Prompts The agent instructions include explicit guardrails that don’t require external filtering: No hallucination: When data is insufficient, the agent sets confidence: 0 and populates missing_information rather than inventing facts. Secret redaction: Each agent is instructed to redact credential-like patterns as [REDACTED] in its output. Mark unknowns: Undeterminable fields use the literal string "UNKNOWN" rather than plausible-sounding guesses. Diagnostic suggestions: When signal is sparse, immediate_actions includes diagnostic steps that gather missing information before prescribing a fix. Model Router: Automatic Model Selection One of the most powerful aspects of this architecture is Model Router. Instead of choosing between gpt-4o , gpt-4o-mini , or o3-mini per agent, you deploy a single model-router endpoint. Model Router analyses each request’s complexity and routes it to the most cost-effective model that can handle it. Model Router insights: models selected per request with associated costs. Model Router telemetry from Microsoft Foundry: request distribution and cost analysis. This means you get optimal cost-performance without writing any model-selection logic. A simple Summary Agent prompt may route to gpt-4o-mini , while a complex Triage Agent prompt with 800 lines of logs routes to gpt-4o all automatically. Deployment: One Command The repo includes both azure.yaml and agent.yaml , so deployment is a single command: Deploy to Foundry # Deploy everything: infra + container + Model Router + Hosted Agent azd up This provisions the Foundry project resources, builds the Docker image, pushes to Azure Container Registry, deploys a Model Router instance, and creates the Hosted Agent. For more control, you can use the SDK deploy script: Manual Docker + SDK deploy # Build and push (must be linux/amd64) docker build --platform linux/amd64 -t oncall-copilot:v1 . docker tag oncall-copilot:v1 $ACR_IMAGE docker push $ACR_IMAGE # Create the hosted agent python scripts/deploy_sdk.py Getting Started Quickstart # Clone git clone https://github.com/microsoft-foundry/oncall-copilot cd oncall-copilot # Install python -m venv .venv source .venv/bin/activate # .venv\Scripts\activate on Windows pip install -r requirements.txt # Set environment variables export AZURE_OPENAI_ENDPOINT="https://<account>.openai.azure.com/" export AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="model-router" export AZURE_AI_PROJECT_ENDPOINT="https://<account>.services.ai.azure.com/api/projects/<project>" # Validate schemas locally (no Azure needed) MOCK_MODE=true python scripts/validate.py # Deploy to Foundry azd up # Invoke the deployed agent python scripts/invoke.py --demo 1 # Start the browser UI python ui/server.py # → http://localhost:7860 Extending: Add Your Own Agent Adding a fifth agent is straightforward. Follow this pattern: Create app/agents/<name>.py with a *_INSTRUCTIONS constant following the existing pattern. Add the agent’s output keys to app/schemas.py . Register it in main.py : main.py — Adding a 5th agent from app.agents.my_new_agent import NEW_INSTRUCTIONS new_agent = AzureOpenAIChatClient( ad_token_provider=_token_provider ).create_agent( instructions=NEW_INSTRUCTIONS, name="new-agent", ) workflow = ConcurrentBuilder().participants( [triage, summary, comms, pir, new_agent] ) Ideas for extensions: a ticket auto-creation agent that creates Jira or Azure DevOps items from the PIR output, a webhook adapter agent that normalises PagerDuty or Datadog payloads, or a human-in-the-loop agent that surfaces missing_information as an interactive form. Key Takeaways for AI Engineers The multi-agent pattern isn’t just for chatbots. Any task that can be decomposed into independent subtasks with distinct output schemas is a candidate. Incident response, document processing, code review, data pipeline validation—the pattern transfers. Microsoft Agent Framework gives you ConcurrentBuilder for parallel execution and AzureOpenAIChatClient for Azure-native auth—you write the prompts, the framework handles the plumbing. Foundry Hosted Agents let you deploy containerised agents with managed infrastructure, automatic scaling, and built-in telemetry. No Kubernetes, no custom API gateway. Model Router eliminates the model selection problem. One deployment name handles all scenarios with optimal cost-performance tradeoffs. Prompt-as-config means your agents are iterable by anyone who can edit text. The feedback loop from “this output could be better” to “deployed improvement” is minutes, not sprints. Resources Microsoft Agent Framework SDK powering the multi-agent orchestration Model Router Automatic model selection based on prompt complexity Foundry Hosted Agents Deploy containerised agents on managed infrastructure ConcurrentBuilder Samples Official agents-in-workflow sample this project follows DefaultAzureCredential Zero-config auth chain used throughout Hosted Agents Concepts Architecture overview of Foundry Hosted Agents The On-Call Copilot sample is open source under the MIT licence. Contributions, scenario files, and agent instruction improvements are welcome via pull request.Vectorless Reasoning-Based RAG: A New Approach to Retrieval-Augmented Generation
Introduction Retrieval-Augmented Generation (RAG) has become a widely adopted architecture for building AI applications that combine Large Language Models (LLMs) with external knowledge sources. Traditional RAG pipelines rely heavily on vector embeddings and similarity search to retrieve relevant documents. While this works well for many scenarios, it introduces challenges such as: Requires chunking documents into small segments Important context can be split across chunks Embedding generation and vector databases add infrastructure complexity A new paradigm called Vectorless Reasoning-Based RAG is emerging to address these challenges. One framework enabling this approach is PageIndex, an open-source document indexing system that organizes documents into a hierarchical tree structure and allows Large Language Models (LLMs) to perform reasoning-based retrieval over that structure. Vectorless Reasoning-Based RAG Instead of vectors, this approach uses structured document navigation. User Query ->Document Tree Structure ->LLM Reasoning ->Relevant Nodes Retrieved ->LLM Generates Answer This mimics how humans read documents: Look at the table of contents Identify relevant sections Read the relevant content Answer the question Core features No Vector Database: It relies on document structure and LLM reasoning for retrieval. It does not depend on vector similarity search. No Chunking: Documents are not split into artificial chunks. Instead, they are organized using their natural structure, such as pages and sections. Human-like Retrieval: The system mimics how human experts read documents. It navigates through sections and extracts information from relevant parts. Better Explainability and Traceability: Retrieval is based on reasoning. The results can be traced back to specific pages and sections. This makes the process easier to interpret. It avoids opaque and approximate vector search, often called “vibe retrieval.” When to Use Vectorless RAG Vectorless RAG works best when: Data is structured or semi-structured Documents have clear metadata Knowledge sources are well organized Queries require reasoning rather than semantic similarity Examples: enterprise knowledge bases internal documentation systems compliance and policy search healthcare documentation financial reporting Implementing Vectorless RAG with Azure AI Foundry Step 1 : Install Pageindex using pip command, from pageindex import PageIndexClient import pageindex.utils as utils # Get your PageIndex API key from https://dash.pageindex.ai/api-keys PAGEINDEX_API_KEY = "YOUR_PAGEINDEX_API_KEY" pi_client = PageIndexClient(api_key=PAGEINDEX_API_KEY) Step 2 : Set up your LLM Example using Azure OpenAI: from openai import AsyncAzureOpenAI client = AsyncAzureOpenAI( api_key=AZURE_OPENAI_API_KEY, azure_endpoint=AZURE_OPENAI_ENDPOINT, api_version=AZURE_OPENAI_API_VERSION ) async def call_llm(prompt, temperature=0): response = await client.chat.completions.create( model=AZURE_DEPLOYMENT_NAME, messages=[{"role": "user", "content": prompt}], temperature=temperature ) return response.choices[0].message.content.strip() Step 3: Page Tree Generation import os, requests pdf_url = "https://arxiv.org/pdf/2501.12948.pdf" //give the pdf url for tree generation, here given one for example pdf_path = os.path.join("../data", pdf_url.split('/')[-1]) os.makedirs(os.path.dirname(pdf_path), exist_ok=True) response = requests.get(pdf_url) with open(pdf_path, "wb") as f: f.write(response.content) print(f"Downloaded {pdf_url}") doc_id = pi_client.submit_document(pdf_path)["doc_id"] print('Document Submitted:', doc_id) Step 4 : Print the generated pageindex tree structure if pi_client.is_retrieval_ready(doc_id): tree = pi_client.get_tree(doc_id, node_summary=True)['result'] print('Simplified Tree Structure of the Document:') utils.print_tree(tree) else: print("Processing document, please try again later...") Step 5 : Use LLM for tree search and identify nodes that might contain relevant context import json query = "What are the conclusions in this document?" tree_without_text = utils.remove_fields(tree.copy(), fields=['text']) search_prompt = f""" You are given a question and a tree structure of a document. Each node contains a node id, node title, and a corresponding summary. Your task is to find all nodes that are likely to contain the answer to the question. Question: {query} Document tree structure: {json.dumps(tree_without_text, indent=2)} Please reply in the following JSON format: {{ "thinking": "<Your thinking process on which nodes are relevant to the question>", "node_list": ["node_id_1", "node_id_2", ..., "node_id_n"] }} Directly return the final JSON structure. Do not output anything else. """ tree_search_result = await call_llm(search_prompt) Step 6 : Print retrieved nodes and reasoning process node_map = utils.create_node_mapping(tree) tree_search_result_json = json.loads(tree_search_result) print('Reasoning Process:') utils.print_wrapped(tree_search_result_json['thinking']) print('\nRetrieved Nodes:') for node_id in tree_search_result_json["node_list"]: node = node_map[node_id] print(f"Node ID: {node['node_id']}\t Page: {node['page_index']}\t Title: {node['title']}") Step 7: Answer generation node_list = json.loads(tree_search_result)["node_list"] relevant_content = "\n\n".join(node_map[node_id]["text"] for node_id in node_list) print('Retrieved Context:\n') utils.print_wrapped(relevant_content[:1000] + '...') answer_prompt = f""" Answer the question based on the context: Question: {query} Context: {relevant_content} Provide a clear, concise answer based only on the context provided. """ print('Generated Answer:\n') answer = await call_llm(answer_prompt) utils.print_wrapped(answer) When to Use Each Approach Both vector-based RAG and vectorless RAG have their strengths. Choosing the right approach depends on the nature of the documents and the type of retrieval required. When to Use Vector Database–Based RAG Vector-based retrieval works best when dealing with large collections of unrelated or loosely structured documents. In such cases, semantic similarity is often sufficient to identify relevant information quickly. Use vector RAG when: Searching across many independent documents Semantic similarity is sufficient to locate relevant content Real-time retrieval is required over very large datasets Common use cases include: Customer support knowledge bases Conversational chatbots Product and content search systems When to Use Vectorless RAG Vectorless approaches such as PageIndex are better suited for long, structured documents where understanding the logical organization of the content is important. Use vectorless RAG when: Documents contain clear hierarchical structure Logical reasoning across sections is required High retrieval accuracy is critical Typical examples include: Financial filings and regulatory reports Legal documents and contracts Technical manuals and documentation Academic and research papers In these scenarios, navigating the document structure allows the system to identify the exact section that logically contains the answer, rather than relying only on semantic similarity. Conclusion Vector databases significantly advanced RAG architectures by enabling scalable semantic search across large datasets. However, they are not the optimal solution for every type of document. Vectorless approaches such as PageIndex introduce a different philosophy: instead of retrieving text that is merely semantically similar, they retrieve text that is logically relevant by reasoning over the structure of the document. As RAG architectures continue to evolve, the future will likely combine the strengths of both approaches. Hybrid systems that integrate vector search for broad retrieval and reasoning-based navigation for precision may offer the best balance of scalability and accuracy for enterprise AI applications.Azure Skilling at Microsoft Ignite 2025
The energy at Microsoft Ignite was unmistakable. Developers, architects, and technical decision-makers converged in San Francisco to explore the latest innovations in cloud technology, AI applications, and data platforms. Beyond the keynotes and product announcements was something even more valuable: an integrated skilling ecosystem designed to transform how you build with Azure. This year Azure Skilling at Microsoft Ignite 2025 brought together distinct learning experiences, over 150+ hands-on labs, and multiple pathways to industry-recognized credentials—all designed to help you master skills that matter most in today's AI-driven cloud landscape. Just Launched at Ignite Microsoft Ignite 2025 offered an exceptional array of learning opportunities, each designed to meet developers anywhere on the skilling journey. Whether you joined us in-person or on-demand in the virtual experience, multiple touchpoints are available to deepen your Azure expertise. Ignite 2025 is in the books, but you can still engage with the latest Microsoft skilling opportunities, including: The Azure Skills Challenge provides a gamified learning experience that lets you compete while completing task-based achievements across Azure's most critical technologies. These challenges aren't just about badges and bragging rights—they're carefully designed to help you advance technical skills and prepare for Microsoft role-based certifications. The competitive element adds urgency and motivation, turning learning into an engaging race against the clock and your peers. For those seeking structured guidance, Plans on Learn offer curated sets of content designed to help you achieve specific learning outcomes. These carefully assembled learning journeys include built-in milestones, progress tracking, and optional email reminders to keep you on track. Each plan represents 12-15 hours of focused learning, taking you from concept to capability in areas like AI application development, data platform modernization, or infrastructure optimization. The Microsoft Reactor Azure Skilling Series, running December 3-11, brings skilling to life through engaging video content, mixing regular programming with special Ignite-specific episodes. This series will deliver technical readiness and programming guidance in a livestream presentation that's more digestible than traditional documentation. Whether you're catching episodes live with interactive Q&A or watching on-demand later, you’ll get world-class instruction that makes complex topics approachable. Beyond Ignite: Your Continuous Learning Journey Here's the critical insight that separates Ignite attendees who transform their careers from those who simply collect swag: the real learning begins after the event ends. Microsoft Ignite is your launchpad, not your destination. Every module you start, every lab you complete, and every challenge you tackle connects to a comprehensive learning ecosystem on Microsoft Learn that's available 24/7, 365 days a year. Think of Ignite as your intensive immersion experience—the moment when you gain context, build momentum, and identify the skills that will have the biggest impact on your work. What you do in the weeks and months following determines whether that momentum compounds into career-defining expertise or dissipates into business as usual. For those targeting career advancement through formal credentials, Microsoft Certifications, Applied Skills and AI Skills Navigator, provide globally recognized validation of your expertise. Applied Skills focus on scenario-based competencies, demonstrating that you can build and deploy solutions, not simply answer theoretical questions. Certifications cover role-based scenarios for developers, data engineers, AI engineers, and solution architects. The assessment experiences include performance-based testing in dedicated Azure tenants where you complete real configuration and development tasks. And finally, the NEW AI Skills Navigator is an agentic learning space, bringing together AI-powered skilling experiences and credentials in a single, unified experience with Microsoft, LinkedIn Learning and GitHub – all in one spot Why This Matters: The Competitive Context The cloud skills race is intensifying. While our competitors offer robust training and content, Microsoft's differentiation comes not from having more content—though our 1.4 million module completions last fiscal year and 35,000+ certifications awarded speak to scale—but from integration of services to orchestrate workflows. Only Microsoft offers a truly unified ecosystem where GitHub Copilot accelerates your development, Azure AI services power your applications, and Azure platform services deploy and scale your solutions—all backed by integrated skilling content that teaches you to maximize this connected experience. When you continue your learning journey after Ignite, you're not just accumulating technical knowledge. You're developing fluency in an integrated development environment that no competitor can replicate. You're learning to leverage AI-powered development tools, cloud-native architectures, and enterprise-grade security in ways that compound each other's value. This unified expertise is what transforms individual developers into force-multipliers for their organizations. Start Now, Build Momentum, Never Stop Microsoft Ignite 2025 offered the chance to compress months of learning into days of intensive, hands-on experience, but you can still take part through the on-demand videos, the Global Ignite Skills Challenge, visiting the GitHub repos for the /Ignite25 labs, the Reactor Azure Skilling Series, and the curated Plans on Learn provide multiple entry points regardless of your current skill level or preferred learning style. But remember: the developers who extract the most value from Ignite are those who treat the event as the beginning, not the culmination, of their learning journey. They join hackathons, contribute to GitHub repositories, and engage with the Azure community on Discord and technical forums. The question isn't whether you'll learn something valuable from Microsoft Ignite 2025-that's guaranteed. The question is whether you'll convert that learning into sustained momentum that compounds over months and years into career-defining expertise. The ecosystem is here. The content is ready. Your skilling journey doesn't end when Ignite does—it accelerates.AI Toolkit Extension Pack for Visual Studio Code: Ignite 2025 Update
Unlock the Latest Agentic App Capabilities The Ignite 2025 update delivers a major leap forward for the AI Toolkit extension pack in VS Code, introducing a unified, end-to-end environment for building, visualizing, and deploying agentic applications to Microsoft Foundry, and the addition of Anthropic’s frontier Claude models in the Model Catalog! This release enables developers to build and debug locally in VS Code, then deploy to the cloud with a single click. Seamlessly switch between VS Code and the Foundry portal for visualization, orchestration, and evaluation, creating a smooth roundtrip workflow that accelerates innovation and delivers a truly unified AI development experience. Download the http://aka.ms/aitoolkit today and start building next-generation agentic apps in VS Code! What Can You Do with the AI Toolkit Extension Pack? Access Anthropic models in the Model Catalog Following the Microsoft, NVIDIA and Anthropic strategic partnerships announcement today, we are excited to share that Anthropic’s frontier Claude models including Claude Sonnet 4.5, Claude Opus 4.1, and Claude Haiku 4.5, are now integrated into the AI Toolkit, providing even more choices and flexibility when building intelligent applications and AI agents. Build AI Agents Using GitHub Copilot Scaffold agent applications using best-practice patterns, tool-calling examples, tracing hooks, and test scaffolds, all powered by Copilot and aligned with the Microsoft Agent Framework. Generate agent code in Python or .NET, giving you flexibility to target your preferred runtime. Build and Customize YAML Workflows Design YAML-based workflows in the Foundry portal, then continue editing and testing directly in VS Code. To customize your YAML-based workflows, instantly convert it to Agent Framework code using GitHub Copilot. Upgrade from declarative design to code-first customization without starting from scratch. Visualize Multi-Agent Workflows Envision your code-based agent workflows with an interactive graph visualizer that reveals each component and how they connect Watch in real-time how each node lights up as you run your agent. Use the visualizer to understand and debug complex agent graphs, making iteration fast and intuitive. Experiment, Debug, and Evaluate Locally Use the Hosted Agents Playground to quickly interact with your agents on your development machine. Leverage local tracing support to debug reasoning steps, tool calls, and latency hotspots—so you can quickly diagnose and fix issues. Define metrics, tasks, and datasets for agent evaluation, then implement metrics using the Foundry Evaluation SDK and orchestrate evaluations runs with the help of Copilot. Seamless Integration Across Environments Jump from Foundry Portal to VS Code Web for a development environment in your preferred code editor setting. Open YAML workflows, playgrounds, and agent templates directly in VS Code for editing and deployment. How to Get Started Install the AI Toolkit extension pack from the VS Code marketplace. Check out documentation. Get started with building workflows with Microsoft Foundry in VS Code 1. Work with Hosted (Pro-code) Agent workflows in VS Code 2. Work with Declarative (Low-code) Agent workflows in VS Code Feedback & Support Try out the extensions and let us know what you think! File issues or feedback on our GitHub repo for Foundry extension and AI Toolkit extension. Your input helps us make continuous improvements.Serverless MCP Agent with LangChain.js v1 — Burgers, Tools, and Traces 🍔
AI agents that can actually do stuff (not just chat) are the fun part nowadays, but wiring them cleanly into real APIs, keeping things observable, and shipping them to the cloud can get... messy. So we built a fresh end‑to‑end sample to show how to do it right with the brand new LangChain.js v1 and Model Context Protocol (MCP). In case you missed it, MCP is a recent open standard that makes it easy for LLM agents to consume tools and APIs, and LangChain.js, a great framework for building GenAI apps and agents, has first-class support for it. You can quickly get up speed with the MCP for Beginners course and AI Agents for Beginners course. This new sample gives you: A LangChain.js v1 agent that streams its result, along reasoning + tool steps An MCP server exposing real tools (burger menu + ordering) from a business API A web interface with authentication, sessions history, and a debug panel (for developers) A production-ready multi-service architecture Serverless deployment on Azure in one command ( azd up ) Yes, it’s a burger ordering system. Who doesn't like burgers? Grab your favorite beverage ☕, and let’s dive in for a quick tour! TL;DR key takeaways New sample: full-stack Node.js AI agent using LangChain.js v1 + MCP tools Architecture: web app → agent API → MCP server → burger API Runs locally with a single npm start , deploys with azd up Uses streaming (NDJSON) with intermediate tool + LLM steps surfaced to the UI Ready to fork, extend, and plug into your own domain / tools What will you learn here? What this sample is about and its high-level architecture What LangChain.js v1 brings to the table for agents How to deploy and run the sample How MCP tools can expose real-world APIs Reference links for everything we use GitHub repo LangChain.js docs Model Context Protocol Azure Developer CLI MCP Inspector Use case You want an AI assistant that can take a natural language request like “Order two spicy burgers and show me my pending orders” and: Understand intent (query menu, then place order) Call the right MCP tools in sequence, calling in turn the necessary APIs Stream progress (LLM tokens + tool steps) Return a clean final answer Swap “burgers” for “inventory”, “bookings”, “support tickets”, or “IoT devices” and you’ve got a reusable pattern! Sample overview Before we play a bit with the sample, let's have a look at the main services implemented here: Service Role Tech Agent Web App ( agent-webapp ) Chat UI + streaming + session history Azure Static Web Apps, Lit web components Agent API ( agent-api ) LangChain.js v1 agent orchestration + auth + history Azure Functions, Node.js Burger MCP Server ( burger-mcp ) Exposes burger API as tools over MCP (Streamable HTTP + SSE) Azure Functions, Express, MCP SDK Burger API ( burger-api ) Business logic: burgers, toppings, orders lifecycle Azure Functions, Cosmos DB Here's a simplified view of how they interact: There are also other supporting components like databases and storage not shown here for clarity. For this quickstart we'll only interact with the Agent Web App and the Burger MCP Server, as they are the main stars of the show here. LangChain.js v1 agent features The recent release of LangChain.js v1 is a huge milestone for the JavaScript AI community! It marks a significant shift from experimental tools to a production-ready framework. The new version doubles down on what’s needed to build robust AI applications, with a strong focus on agents. This includes first-class support for streaming not just the final output, but also intermediate steps like tool calls and agent reasoning. This makes building transparent and interactive agent experiences (like the one in this sample) much more straightforward. Quickstart Requirements GitHub account Azure account (free signup, or if you're a student, get free credits here) Azure Developer CLI Deploy and run the sample We'll use GitHub Codespaces for a quick zero-install setup here, but if you prefer to run it locally, check the README. Click on the following link or open it in a new tab to launch a Codespace: Create Codespace This will open a VS Code environment in your browser with the repo already cloned and all the tools installed and ready to go. Provision and deploy to Azure Open a terminal and run these commands: # Install dependencies npm install # Login to Azure azd auth login # Provision and deploy all resources azd up Follow the prompts to select your Azure subscription and region. If you're unsure of which one to pick, choose East US 2 . The deployment will take about 15 minutes the first time, to create all the necessary resources (Functions, Static Web Apps, Cosmos DB, AI Models). If you're curious about what happens under the hood, you can take a look at the main.bicep file in the infra folder, which defines the infrastructure as code for this sample. Test the MCP server While the deployment is running, you can run the MCP server and API locally (even in Codespaces) to see how it works. Open another terminal and run: npm start This will start all services locally, including the Burger API and the MCP server, which will be available at http://localhost:3000/mcp . This may take a few seconds, wait until you see this message in the terminal: 🚀 All services ready 🚀 When these services are running without Azure resources provisioned, they will use in-memory data instead of Cosmos DB so you can experiment freely with the API and MCP server, though the agent won't be functional as it requires a LLM resource. MCP tools The MCP server exposes the following tools, which the agent can use to interact with the burger ordering system: Tool Name Description get_burgers Get a list of all burgers in the menu get_burger_by_id Get a specific burger by its ID get_toppings Get a list of all toppings in the menu get_topping_by_id Get a specific topping by its ID get_topping_categories Get a list of all topping categories get_orders Get a list of all orders in the system get_order_by_id Get a specific order by its ID place_order Place a new order with burgers (requires userId , optional nickname ) delete_order_by_id Cancel an order if it has not yet been started (status must be pending , requires userId ) You can test these tools using the MCP Inspector. Open another terminal and run: npx -y @modelcontextprotocol/inspector Then open the URL printed in the terminal in your browser and connect using these settings: Transport: Streamable HTTP URL: http://localhost:3000/mcp Connection Type: Via Proxy (should be default) Click on Connect, then try listing the tools first, and run get_burgers tool to get the menu info. Test the Agent Web App After the deployment is completed, you can run the command npm run env to print the URLs of the deployed services. Open the Agent Web App URL in your browser (it should look like https://<your-web-app>.azurestaticapps.net ). You'll first be greeted by an authentication page, you can sign in either with your GitHub or Microsoft account and then you should be able to access the chat interface. From there, you can start asking any question or use one of the suggested prompts, for example try asking: Recommend me an extra spicy burger . As the agent processes your request, you'll see the response streaming in real-time, along with the intermediate steps and tool calls. Once the response is complete, you can also unfold the debug panel to see the full reasoning chain and the tools that were invoked: Tip: Our agent service also sends detailed tracing data using OpenTelemetry. You can explore these either in Azure Monitor for the deployed service, or locally using an OpenTelemetry collector. We'll cover this in more detail in a future post. Wrap it up Congratulations, you just finished spinning up a full-stack serverless AI agent using LangChain.js v1, MCP tools, and Azure’s serverless platform. Now it's your turn to dive in the code and extend it for your use cases! 😎 And don't forget to azd down once you're done to avoid any unwanted costs. Going further This was just a quick introduction to this sample, and you can expect more in-depth posts and tutorials soon. Since we're in the era of AI agents, we've also made sure that this sample can be explored and extended easily with code agents like GitHub Copilot. We even built a custom chat mode to help you discover and understand the codebase faster! Check out the Copilot setup guide in the repo to get started. You can quickly get up speed with the MCP for Beginners course and AI Agents for Beginners course. If you like this sample, don't forget to star the repo ⭐️! You can also join us in the Azure AI community Discord to chat and ask any questions. Happy coding and burger ordering! 🍔Introducing the Microsoft Agent Framework
Introducing the Microsoft Agent Framework: A Unified Foundation for AI Agents and Workflows The landscape of AI development is evolving rapidly, and Microsoft is at the forefront with the release of the Microsoft Agent Framework an open-source SDK designed to empower developers to build intelligent, multi-agent systems with ease and precision. Whether you're working in .NET or Python, this framework offers a unified, extensible foundation that merges the best of Semantic Kernel and AutoGen, while introducing powerful new capabilities for agent orchestration and workflow design. Introducing Microsoft Agent Framework: The Open-Source Engine for Agentic AI Apps | Azure AI Foundry Blog Introducing Microsoft Agent Framework | Microsoft Azure Blog Why Another Agent Framework? Both Semantic Kernel and AutoGen have pioneered agentic development, Semantic Kernel with its enterprise-grade features and AutoGen with its research-driven abstractions. The Microsoft Agent Framework is the next generation of both, built by the same teams to unify their strengths: AutoGen’s simplicity in multi-agent orchestration. Semantic Kernel’s robustness in thread-based state management, telemetry, and type safety. New capabilities like graph-based workflows, checkpointing, and human-in-the-loop support This convergence means developers no longer have to choose between experimentation and production. The Agent Framework is designed to scale from single-agent prototypes to complex, enterprise-ready systems Core Capabilities AI Agents AI agents are autonomous entities powered by LLMs that can process user inputs, make decisions, call tools and MCP servers, and generate responses. They support providers like Azure OpenAI, OpenAI, and Azure AI, and can be enhanced with: Agent threads for state management. Context providers for memory. Middleware for action interception. MCP clients for tool integration Use cases include customer support, education, code generation, research assistance, and more—especially where tasks are dynamic and underspecified. Workflows Workflows are graph-based orchestrations that connect multiple agents and functions to perform complex, multi-step tasks. They support: Type-based routing Conditional logic Checkpointing Human-in-the-loop interactions Multi-agent orchestration patterns (sequential, concurrent, hand-off, Magentic) Workflows are ideal for structured, long-running processes that require reliability and modularity. Developer Experience The Agent Framework is designed to be intuitive and powerful: Installation: Python: pip install agent-framework .NET: dotnet add package Microsoft.Agents.AI Integration: Works with Foundry SDK, MCP SDK, A2A SDK, and M365 Copilot Agents Samples and Manifests: Explore declarative agent manifests and code samples Learning Resources: Microsoft Learn modules AI Agents for Beginners AI Show demos Azure AI Foundry Discord community Migration and Compatibility If you're currently using Semantic Kernel or AutoGen, migration guides are available to help you transition smoothly. The framework is designed to be backward-compatible where possible, and future updates will continue to support community contributions via the GitHub repository. Important Considerations The Agent Framework is in public preview. Feedback and issues are welcome on the GitHub repository. When integrating with third-party servers or agents, review data sharing practices and compliance boundaries carefully. The Microsoft Agent Framework marks a pivotal moment in AI development, bringing together research innovation and enterprise readiness into a single, open-source foundation. Whether you're building your first agent or orchestrating a fleet of them, this framework gives you the tools to do it safely, scalably, and intelligently. Ready to get started? Download the SDK, explore the documentation, and join the community shaping the future of AI agents.Transform Your AI Applications with Local LLM Deployment
Introduction Are you tired of watching your AI application costs spiral out of control every time your user base grows? As AI Engineers and Developers, we've all felt the pain of cloud-dependent LLM deployments. Every API call adds up, latency becomes a bottleneck in real-time applications, and sensitive data must leave your infrastructure to get processed. Meanwhile, your users demand faster responses, better privacy, and more reliable service. What if there was a way to run powerful language models directly on your users' devices or your local infrastructure? Enter the world of Edge AI deployment with Microsoft's Foundry Local a game-changing approach that brings enterprise-grade LLM capabilities to local hardware while maintaining full OpenAI API compatibility. The Edge AI for Beginners https://aka.ms/edgeai-for-beginners curriculum provides AI Engineers and Developers with comprehensive, hands-on training to master local LLM deployment. This isn't just another theoretical course, it's a practical guide that will transform how you think about AI infrastructure, combining cutting-edge local deployment techniques with production-ready implementation patterns. In this post, we'll explore why Edge AI deployment represents the future of AI applications, dive deep into Foundry Local's capabilities across multiple frameworks, and show you exactly how to implement local LLM solutions that deliver both technical excellence and significant business value. Why Edge AI Deployment Changes Everything for Developers The shift from cloud-dependent to edge-deployed AI represents more than just a technical evolution, it's a fundamental reimagining of how we build intelligent applications. As AI Engineers, we're witnessing a transformation that addresses the most pressing challenges in modern AI deployment while opening up entirely new possibilities for innovation. Consider the current state of cloud-based LLM deployment. Every user interaction requires a round-trip to external servers, introducing latency that can kill user experience in real-time applications. Costs scale linearly (or worse) with usage, making successful applications expensive to operate. Sensitive data must traverse networks and live temporarily in external systems, creating compliance nightmares for enterprise applications. Edge AI deployment fundamentally changes this equation. By running models locally, we achieve several critical advantages: Data Sovereignty and Privacy Protection: Your sensitive data never leaves your infrastructure. For healthcare applications processing patient records, financial services handling transactions, or enterprise tools managing proprietary information, this represents a quantum leap in security posture. You maintain complete control over data flow, meeting even the strictest compliance requirements without architectural compromises. Real-Time Performance at Scale: Local inference eliminates network latency entirely. Instead of 200-500ms round-trips to cloud APIs, you get sub-10ms response times. This enables entirely new categories of applications—real-time code completion, interactive AI tutoring systems, voice assistants that respond instantly, and IoT devices that make intelligent decisions without connectivity. Predictable Cost Structure: Transform variable API costs into fixed infrastructure investments. Instead of paying per-token for potentially unlimited usage, you invest in local hardware that serves unlimited requests. This makes ROI calculations straightforward and removes the fear of viral success destroying your margins. Offline Capabilities and Resilience: Local deployment means your AI features work even when connectivity fails. Mobile applications can provide intelligent features in areas with poor network coverage. Critical systems maintain AI capabilities during network outages. Edge devices in remote locations operate autonomously. The technical implications extend beyond these obvious benefits. Local deployment enables new architectural patterns: AI-powered applications that work entirely client-side, edge computing nodes that make intelligent routing decisions, and distributed systems where intelligence lives close to data sources. Foundry Local: Multi-Framework Edge AI Deployment Made Simple Microsoft's Foundry Local https://www.foundrylocal.ai represents a breakthrough in local AI deployment, designed specifically for developers who need production-ready edge AI solutions. Unlike single-framework tools, Foundry Local provides a unified platform that works seamlessly across multiple programming languages and deployment scenarios while maintaining full compatibility with existing OpenAI-based workflows. The platform's approach to multi-framework support means you're not locked into a single technology stack. Whether you're building TypeScript applications, Python ML pipelines, Rust systems programming projects, or .NET enterprise applications, Foundry Local provides native SDKs and consistent APIs that integrate naturally with your existing codebase. Enterprise-Grade Model Catalog: Foundry Local comes with a curated selection of production-ready models optimized for edge deployment. The `phi-3.5-mini` model delivers impressive performance in a compact footprint, perfect for resource-constrained environments. For applications requiring more sophisticated reasoning, `qwen2.5-0.5b` provides enhanced capabilities while maintaining efficiency. When you need maximum capability and have sufficient hardware resources, `gpt-oss-20b` offers state-of-the-art performance with full local control. Intelligent Hardware Optimization: One of Foundry Local's most powerful features is its automatic hardware detection and optimization. The platform automatically identifies your available compute resources, NVIDIA CUDA GPUs, AMD GPUs, Intel NPUs, Qualcomm Snapdragon NPUs, or CPU-only environments and downloads the most appropriate model variant. This means the same application code delivers optimal performance across diverse hardware configurations without manual intervention. ONNX Runtime Acceleration: Under the hood, Foundry Local leverages Microsoft's ONNX Runtime for maximum performance. This provides significant advantages over generic inference engines, delivering optimized execution paths for different hardware architectures while maintaining model accuracy and compatibility. OpenAI SDK Compatibility: Perhaps most importantly for developers, Foundry Local maintains complete API compatibility with the OpenAI SDK. This means existing applications can migrate to local inference by changing only the endpoint configuration—no rewriting of application logic, no learning new APIs, no disruption to existing workflows. The platform handles the complex aspects of local AI deployment automatically: model downloading, hardware-specific optimization, memory management, and inference scheduling. This allows developers to focus on building intelligent applications rather than managing AI infrastructure. Framework-Agnostic Benefits: Foundry Local's multi-framework approach delivers consistent benefits regardless of your technology choices. Whether you're working in a Node.js microservices architecture, a Python data science environment, a Rust embedded system, or a C# enterprise application, you get the same advantages: reduced latency, eliminated API costs, enhanced privacy, and offline capabilities. This universal compatibility means teams can adopt edge AI deployment incrementally, starting with pilot projects in their preferred language and expanding across their technology stack as they see results. The learning curve is minimal because the API patterns remain familiar while the underlying infrastructure transforms to local deployment. Implementing Edge AI: From Code to Production Moving from cloud APIs to local AI deployment requires understanding the implementation patterns that make edge AI both powerful and practical. Let's explore how Foundry Local's SDKs enable seamless integration across different development environments, with real-world code examples that you can adapt for your production systems. Python Implementation for Data Science and ML Pipelines Python developers will find Foundry Local's integration particularly natural, especially in data science and machine learning contexts where local processing is often preferred for security and performance reasons. import openai from foundry_local import FoundryLocalManager # Initialize with automatic hardware optimization alias = "phi-3.5-mini" manager = FoundryLocalManager(alias) This simple initialization handles a remarkable amount of complexity automatically. The `FoundryLocalManager` detects your hardware configuration, downloads the most appropriate model variant for your system, and starts the local inference service. Behind the scenes, it's making intelligent decisions about memory allocation, selecting optimal execution providers, and preparing the model for efficient inference. # Configure OpenAI client for local deployment client = openai.OpenAI( base_url=manager.endpoint, api_key=manager.api_key # Not required for local, but maintains API compatibility ) # Production-ready inference with streaming def analyze_document(content: str): stream = client.chat.completions.create( model=manager.get_model_info(alias).id, messages=[{ "role": "system", "content": "You are an expert document analyzer. Provide structured analysis." }, { "role": "user", "content": f"Analyze this document: {content}" }], stream=True, temperature=0.7 ) result = "" for chunk in stream: if chunk.choices[0].delta.content: content_piece = chunk.choices[0].delta.content result += content_piece yield content_piece # Enable real-time UI updates return result Key implementation benefits here: • Automatic model management: The `FoundryLocalManager` handles model lifecycle, memory optimization, and hardware-specific acceleration without manual configuration. • Streaming interface compatibility: Maintains the familiar OpenAI streaming API while processing locally, enabling real-time user interfaces with zero latency overhead. • Production error handling: The manager includes built-in retry logic, graceful degradation, and resource management for reliable production deployment. JavaScript/TypeScript Implementation for Web Applications JavaScript and TypeScript developers can integrate local AI capabilities directly into web applications, enabling entirely new categories of client-side intelligent features. import { OpenAI } from "openai"; import { FoundryLocalManager } from "foundry-local-sdk"; class LocalAIService { constructor() { this.foundryManager = null; this.openaiClient = null; this.isInitialized = false; } async initialize(modelAlias = "phi-3.5-mini") { this.foundryManager = new FoundryLocalManager(); const modelInfo = await this.foundryManager.init(modelAlias); this.openaiClient = new OpenAI({ baseURL: this.foundryManager.endpoint, apiKey: this.foundryManager.apiKey, }); this.isInitialized = true; return modelInfo; } The initialization pattern establishes local AI capabilities with full error handling and resource management. This enables web applications to provide AI features without external API dependencies. async generateCodeCompletion(codeContext, userPrompt) { if (!this.isInitialized) { throw new Error("LocalAI service not initialized"); } try { const completion = await this.openaiClient.chat.completions.create({ model: this.foundryManager.getModelInfo().id, messages: [ { role: "system", content: "You are a code completion assistant. Provide accurate, efficient code suggestions." }, { role: "user", content: `Context: ${codeContext}\n\nComplete: ${userPrompt}` } ], max_tokens: 150, temperature: 0.2 }); return completion.choices[0].message.content; } catch (error) { console.error("Local AI completion failed:", error); throw new Error("Code completion unavailable"); } } } Implementation advantages for web applications • Zero-dependency AI features: Applications work entirely offline once models are downloaded, enabling AI capabilities in disconnected environments. • Instant response times: Eliminate network latency for real-time features like code completion, content generation, or intelligent search. • Client-side privacy: Sensitive code or content never leaves the user's device, meeting strict security requirements for enterprise development tools. Cross-Platform Production Deployment Patterns Both Python and JavaScript implementations share common production deployment patterns that make Foundry Local particularly suitable for enterprise applications: Automatic Hardware Optimization: The platform automatically detects and utilizes available acceleration hardware. On systems with NVIDIA GPUs, it leverages CUDA acceleration. On newer Intel systems, it uses NPU acceleration. On ARM-based systems like Apple Silicon or Qualcomm Snapdragon, it optimizes for those architectures. This means the same application code delivers optimal performance across diverse deployment environments. Graceful Resource Management: Foundry Local includes sophisticated memory management and resource allocation. Models are loaded efficiently, memory is recycled properly, and concurrent requests are handled intelligently to maintain system stability under load. Production Monitoring Integration: The platform provides comprehensive metrics and logging that integrate naturally with existing monitoring systems, enabling production observability for AI workloads running at the edge. These implementation patterns demonstrate how Foundry Local transforms edge AI from an experimental concept into a practical, production-ready deployment strategy that works consistently across different technology stacks and hardware environments. Measuring Success: Technical Performance and Business Impact The transition to edge AI deployment delivers measurable improvements across both technical and business metrics. Understanding these impacts helps justify the architectural shift and demonstrates the concrete value of local LLM deployment in production environments. Technical Performance Gains Latency Elimination: The most immediately visible benefit is the dramatic reduction in response times. Cloud API calls typically require 200-800ms round-trips, depending on geographic location and network conditions. Local inference with Foundry Local reduces this to sub-10ms response times—a 95-99% improvement that fundamentally changes user experience possibilities. Consider a code completion feature: cloud-based completion feels sluggish and interrupts developer flow, while local completion provides instant suggestions that enhance productivity. The same applies to real-time chat applications, interactive AI tutoring systems, and any application where response latency directly impacts usability. Automatic Hardware Utilization: Foundry Local's intelligent hardware detection and optimization delivers significant performance improvements without manual configuration. On systems with NVIDIA RTX 4000 series GPUs, inference speeds can be 10-50x faster than CPU-only processing. On newer Intel systems with NPUs, the platform automatically leverages neural processing units for efficient AI workloads. Apple Silicon systems benefit from Metal Performance Shaders optimization, delivering excellent performance per watt. ONNX Runtime Optimization: Microsoft's ONNX Runtime provides substantial performance advantages over generic inference engines. In benchmark testing, ONNX Runtime consistently delivers 2-5x performance improvements compared to standard PyTorch or TensorFlow inference, while maintaining full model accuracy and compatibility. Scalability Characteristics: Local deployment transforms scaling economics entirely. Instead of linear cost scaling with usage, you get horizontal scaling through hardware deployment. A single modern GPU can handle hundreds of concurrent inference requests, making per-request costs approach zero for high-volume applications. Business Impact Analysis Cost Structure Transformation: The financial implications of local deployment are profound. Consider an application processing 1 million tokens daily through OpenAI's API—this represents $20-60 in daily costs depending on the model. Over a year, this becomes $7,300-21,900 in recurring expenses. A comparable local deployment might require a $2,000-5,000 hardware investment with no ongoing API costs. For high-volume applications, the savings become dramatic. Applications processing 100 million tokens monthly face $60,000-180,000 annual API costs. Local deployment with appropriate hardware infrastructure could reduce this to electricity and maintenance costs—typically under $10,000 annually for equivalent processing capacity. Enhanced Privacy and Compliance: Local deployment eliminates data sovereignty concerns entirely. Healthcare applications processing patient records, financial services handling transaction data, and enterprise tools managing proprietary information can deploy AI capabilities without data leaving their infrastructure. This simplifies compliance with GDPR, HIPAA, SOX, and other regulatory frameworks while reducing legal and security risks. Operational Resilience: Local deployment provides significant business continuity advantages. Applications continue functioning during network outages, API service disruptions, or third-party provider issues. For mission-critical systems, this resilience can prevent costly downtime and maintain user productivity during external service failures. Development Velocity: Local deployment accelerates development cycles by eliminating API rate limits, usage quotas, and external dependencies during development and testing. Developers can iterate freely, run comprehensive test suites, and experiment with AI features without cost concerns or rate limiting delays. Enterprise Adoption Metrics Real-world enterprise deployments demonstrate measurable business value: Local Usage: Foundry Local for internal AI-powered tools, reporting 60-80% reduction in AI-related operational costs while improving developer productivity through instant AI responses in development environments. Manufacturing Applications: Industrial IoT deployments using edge AI for predictive maintenance show 40-60% reduction in unplanned downtime while eliminating cloud connectivity requirements in remote facilities. Financial Services: Trading firms deploying local LLMs for market analysis report sub-millisecond decision latencies while maintaining complete data isolation for competitive advantage and regulatory compliance. ROI Calculation Framework For AI Engineers evaluating edge deployment, consider these quantifiable factors: Direct Cost Savings: Compare monthly API costs against hardware amortization over 24-36 months. Most applications with >$1,000 monthly API costs achieve positive ROI within 12-18 months. Performance Value: Quantify the business impact of reduced latency. For customer-facing applications, each 100ms of latency reduction typically correlates with 1-3% conversion improvement. Risk Mitigation: Calculate the cost of downtime or compliance violations prevented by local deployment. For many enterprise applications, avoiding a single significant outage justifies the infrastructure investment. Development Efficiency: Measure developer productivity improvements from unlimited local AI access during development. Teams report 20-40% faster iteration cycles when AI features can be tested without external dependencies. These metrics demonstrate that edge AI deployment with Foundry Local delivers both immediate technical improvements and substantial long-term business value, making it a strategic investment in AI infrastructure that pays dividends across multiple dimensions. Your Edge AI Journey Starts Here The shift to edge AI represents more than just a technical evolution, it's an opportunity to fundamentally improve your applications while building valuable expertise in an emerging field. Whether you're looking to reduce costs, improve performance, or enhance privacy, the path forward involves both learning new concepts and connecting with a community of practitioners solving similar challenges. Master Edge AI with Comprehensive Training The Edge AI for Beginners https://aka.ms/edgeai-for-beginners curriculum provides the complete foundation you need to become proficient in local AI deployment. This isn't a superficial overview, it's a comprehensive, hands-on program designed specifically for developers who want to build production-ready edge AI applications. The curriculum takes you through hours of structured learning, progressing from fundamental concepts to advanced deployment scenarios. You'll start by understanding the principles of edge AI and local inference, then dive deep into practical implementation with Foundry Local across multiple programming languages. The program includes working examples and comprehensive sample applications that demonstrate real-world use cases. What sets this curriculum apart is its practical focus. Instead of theoretical discussions, you'll build actual applications: document analysis systems that work offline, real-time code completion tools, intelligent chatbots that protect user privacy, and IoT applications that make decisions locally. Each project teaches both the technical implementation and the architectural thinking needed for successful edge AI deployment. The curriculum covers multi-framework deployment patterns extensively, ensuring you can apply edge AI principles regardless of your preferred development stack. Whether you're working in Python data science environments, JavaScript web applications, C# enterprise systems, or Rust embedded projects, you'll learn the patterns and practices that make edge AI successful. Join a Community of AI Engineers Learning edge AI doesn't happen in isolation, it requires connection with other developers who are solving similar challenges and discovering new possibilities. The Foundry Local Discord community https://aka.ms/foundry-local-discord provides exactly this environment, connecting AI Engineers and Developers from around the world who are implementing local AI solutions. This community serves multiple crucial functions for your development as an edge AI practitioner. You'll find experienced developers sharing implementation patterns they've discovered, debugging complex deployment issues collaboratively, and discussing the architectural decisions that make edge AI successful in production environments. The Discord community includes dedicated channels for different programming languages, specific deployment scenarios, and technical discussions about optimization and performance. Whether you're implementing your first local AI feature or optimizing a complex multi-model deployment, you'll find peers and experts ready to help problem-solve and share insights. Beyond technical support, the community provides valuable career and business insights. Members share their experiences with edge AI adoption in different industries, discuss the business cases that have proven most successful, and collaborate on open-source projects that advance the entire ecosystem. Share Your Experience and Build Expertise One of the most effective ways to solidify your edge AI expertise is by sharing your implementation experiences with the community. As you build applications with Foundry Local and deploy edge AI solutions, documenting your process and sharing your learnings provides value both to others and to your own professional development. Consider sharing your deployment stories, whether they're successes or challenges you've overcome. The community benefits from real-world case studies that show how edge AI performs in different environments and use cases. Your experience implementing local AI in a healthcare application, financial services system, or manufacturing environment provides valuable insights that others can build upon. Technical contributions are equally valuable, whether it's sharing configuration patterns you've discovered, performance optimizations you've implemented, or integration approaches you've developed for specific frameworks or libraries. The edge AI field is evolving rapidly, and practical contributions from working developers drive much of the innovation. Sharing your work also builds your professional reputation as an edge AI expert. As organizations increasingly adopt local AI deployment strategies, developers with proven experience in this area become valuable resources for their teams and the broader industry. The combination of structured learning through the Edge AI curriculum, active participation in the community, and sharing your practical experiences creates a comprehensive path to edge AI expertise that serves both your immediate project needs and your long-term career development as AI deployment patterns continue evolving. Key Takeaways Local LLM deployment transforms application economics: Replace variable API costs with fixed infrastructure investments that scale to unlimited usage, typically achieving ROI within 12-18 months for applications with significant AI workloads. Foundry Local enables multi-framework edge AI: Consistent deployment patterns across Python, JavaScript, C#, and Rust environments with automatic hardware optimization and OpenAI API compatibility. Performance improvements are dramatic and measurable: Sub-10ms response times replace 200-800ms cloud API latency, while automatic hardware acceleration delivers 2-50x performance improvements depending on available compute resources. Privacy and compliance become architectural advantages: Local deployment eliminates data sovereignty concerns, simplifies regulatory compliance, and provides complete control over sensitive information processing. Edge AI expertise is a strategic career investment: As organizations increasingly adopt local AI deployment, developers with hands-on edge AI experience become valuable technical resources with unique skills in an emerging field. Conclusion Edge AI deployment represents the next evolution in intelligent application development, transforming both the technical possibilities and economic models of AI-powered systems. With Foundry Local and the comprehensive Edge AI for Beginners curriculum, you have access to production-ready tools and expert guidance to make this transition successfully. The path forward is clear: start with the Edge AI for Beginners curriculum to build solid foundations, connect with the Foundry Local Discord community to learn from practicing developers, and begin implementing local AI solutions in your projects. Each step builds valuable expertise while delivering immediate improvements to your applications. As cloud costs continue rising and privacy requirements become more stringent, organizations will increasingly rely on developers who can implement local AI solutions effectively. Your early adoption of edge AI deployment patterns positions you at the forefront of this technological shift, with skills that will become increasingly valuable as the industry evolves. The future of AI deployment is local, private, and performance-optimized. Start building that future today. Resources Edge AI for Beginners Curriculum: Comprehensive training with 36-45 hours of hands-on content examples, and production-ready deployment patterns https://aka.ms/edgeai-for-beginners Foundry Local GitHub Repository: Official documentation, samples, and community contributions for local AI deployment https://github.com/microsoft/foundry_local Foundry Local Discord Community: Connect with AI Engineers and Developers implementing edge AI solutions worldwide https://aka.ms/foundry/discord Foundry Local Documentation: Complete technical documentation and API references Foundry Local documentation | Microsoft Learn Foundry Local Model Catalog: Browse available models and deployment options for different hardware configurations Foundry Local Models - Browse AI ModelsGPT-5: Will it RAG?
OpenAI released the GPT-5 model family last week, with an emphasis on accurate tool calling and reduced hallucinations. For those of us working on RAG (Retrieval-Augmented Generation), it's particularly exciting to see a model specifically trained to reduce hallucination. There are five variants in the family: gpt-5 gpt-5-mini gpt-5-nano gpt-5-chat: Not a reasoning model, optimized for chat applications gpt-5-pro: Only available in ChatGPT, not via the API As soon as GPT-5 models were available in Azure AI Foundry, I deployed them and evaluated them inside our most popular open source RAG template. I was immediately impressed - not by the model's ability to answer a question, but by it's ability to admit it could not answer a question! You see, we have one test question for our sample data (HR documents for a fictional company's) that sounds like it should be an easy question: "What does a Product Manager do?" But, if you actually look at the company documents, there's no job description for "Product Manager", only related jobs like "Senior Manager of Product Management". Every other model, including the reasoning models, has still pretended that it could answer that question. For example, here's a response from o4-mini: However, the gpt-5 model realizes that it doesn't have the information necessary, and responds that it cannot answer the question: As I always say: I would much rather have an LLM admit that it doesn't have enough information instead of making up an answer. Bulk evaluation But that's just a single question! What we really need to know is whether the GPT-5 models will generally do a better job across the board, on a wide range of questions. So I ran bulk evaluations using the azure-ai-evaluations SDK, checking my favorite metrics: groundedness (LLM-judged), relevance (LLM-judged), and citations_matched (regex based off ground truth citations). I didn't bother evaluating gpt-5-nano, as I did some quick manual tests and wasn't impressed enough - plus, we've never used a nano sized model for our RAG scenarios. Here are the results for 50 Q/A pairs: metric stat gpt-4.1-mini gpt-4o-mini gpt-5-chat gpt-5 gpt-5-mini o3-mini groundedness pass % 94% 86% 96% 100% 🏆 94% 96% ↑ mean score 4.76 4.50 4.86 5.00 🏆 4.82 4.80 relevance pass % 94% 🏆 84% 90% 90% 74% 90% ↑ mean score 4.42 🏆 4.22 4.06 4.20 4.02 4.00 answer_length mean 829 919 549 844 940 499 latency mean 2.9 4.5 2.9 9.6 7.5 19.4 citations_matched % 52% 49% 52% 47% 49% 51% For the LLM-judged metrics of groundedness and relevance , the LLM awards a score of 1-5, and both 4 and 5 are considered passing scores. That's why you see both a "pass %" (percentage with 4 or 5 score) and an average score in the table above. For the groundedness metric, which measures whether an answer is grounded in the retrieved search results, the gpt-5 model does the best (100%), while the other gpt-5 models do quite well as well, on par with our current default model of gpt-4.1-mini. For the relevance metric, which measures whether an answer fully answers a question, the gpt-5 models don't score as highly as gpt-4.1-mini. I looked into the discrepancies there, and I think that's actually due to gpt-5 being less willing to give an answer when it's not fully confident in it - it would rather give a partial answer instead. That's a good thing for RAG apps, so I am comfortable with that metric being less than 100%. The latency metric is generally higher for the gpt-5 reasoning models, as would be expected, but is also variable based on on deployment region, region capacity, etc, assuming you're not using a "provisioned thoroughput" deployment. Also note that the latency here records the total time taken, from first token to last token, whereas the most important metric for a user-facing streaming chat is the time to first token. For the gpt-5 reasoning models in this evaluation, I set the reasoning_effort to "minimal", which means the model chooses whether to use reasoning tokens. I have never seen it actually use any reasoning tokens when I set the effort to minimal, so maybe that means that a higher reasoning effort is really only needed for longer or more complex tasks, and RAG answering is a non-reasoning task. A higher reasoning effort would definitely affect the latency and likely also affect the answer quality. I did not test that out, since the "minimal" effort setting already results in high quality answers. Answer differences Now that we've seen the overall metrics, let's dig into some actual answers, and see some of the key ways that GPT-5 model answers differ. Quicker to say "I don't know" 🤷🏻 Let's start with the first thing I noticed: gpt-5 was happy to admit when it couldn't fully answer a question. In the 50 questions evaluated, the gpt-5 model started off their answer with "I don't know" for 3 of the answers, while gpt-5-mini started that way for 10 of the answers. In table form: gpt-4.1-mini gpt-5 gpt-5-mini gpt-5-chat 1 (1.6%) 3 (6%) 10 (20%) 1 (1.6%) Here's an example of a gpt-4.1-mini answer versus a gpt-5 answer: Q: Explain the eligibility criteria for the Northwind Standard plan offered to Contoso employees? gpt-4.1-mini gpt-5 The eligibility criteria for the Northwind Standard plan for Contoso employees are not explicitly detailed in the provided sources. However, it is mentioned that prior-authorization may be required for certain services or treatments, which involves approval from Northwind Health based on medical necessity and coverage under the plan. Employees must have their physician submit a request for prior-authorization, and in some cases, meet specific criteria such as medical tests, treatments, or lifestyle changes to be approved. Preventive care, emergency services, mental health, and substance abuse coverage do not require prior-authorization. Out-of-network services do require prior-authorization and may incur additional costs [Northwind_Standard_Benefits_Details.pdf#page=63][Northwind_Standard_Benefits_Details.pdf#page=102]. If you need information on basic eligibility (such as employment status or tenure), that is not provided in these sources. I don’t know. The provided sources describe compliance (ERISA, COBRA, HIPAA, ACA) and note that Northwind Standard is a group plan covering “all eligible employees of Contoso and their spouses or dependents,” but they do not define the specific eligibility criteria (e.g., hours worked, waiting period, employment class). [Northwind_Standard_Benefits_Details.pdf#page=88][Northwind_Standard_Benefits_Details.pdf#page=85][Northwind_Standard_Benefits_Details.pdf#page=86] Both of the answers admit some degree of not-knowing, but gpt-5 comes right out with it at the start of the answer. Notably, our system prompt includes this instruction: Answer ONLY with the facts listed in the list of sources below. If there isn't enough information below, say you don't know. So what we may be seeing is a combination of two factors: 1) the gpt-5 reasoning models are generally better at following instructions, 2) the gpt-5 reasoning models went through a specific alignment process to reduce hallucination. Notably, however, the gpt-5-chat model rarely responded with "I don't know", so it is not as affected by whatever factors are increasing the likelihood of the reasoning models to answer that way. You may be wondering why I have questions in the evaluation set that aren't fully answerable - it's hard to generate a good set of ground truth for evaluation, and my ground truth data is not the optimal set of questions. Ideally, I would do a separate evaluation for all the fully knowable questions versus all the unknowable questions - and I even have a specific custom metric for "don't-know-ness" that I run on those - but a few partially knowable questions snuck into this ground truth data set. Requests for clarification 🙋🏻♀️ Our system prompt also encourages the model to ask clarifying questions when necessary: If asking a clarifying question to the user would help, ask the question. But I had never actually seen a clarifying question from a model until gpt-5-chat, which replied with a question to 2 of the 50 questions. Example: Q: What should I do if I need healthcare services outside Washington with Northwind Health? gpt-4.1-mini gpt-5-chat If you have Northwind Standard and need healthcare services outside Washington, you must meet these criteria for coverage: be outside Washington for no more than 12 consecutive months, be more than 100 miles away from your primary care provider, and have had your plan in effect for at least 6 months before receiving out-of-area care. You must contact Northwind Health in advance and obtain prior authorization for the care; otherwise, you may be responsible for the full cost. Emergency services outside Washington are covered, but non-emergency services are not unless these conditions are met [Northwind_Standard_Benefits_Details.pdf#page=59][Northwind_Standard_Benefits_Details.pdf#page=60]. If you have Northwind Health Plus, first ensure the provider is in the nationwide network by checking the online directory or calling customer service. Keep receipts and documentation for any out-of-state services, as you may need to submit claims for reimbursement. Contact Northwind Health Plus before receiving services to confirm coverage, as not all services outside Washington are covered [Northwind_Health_Plus_Benefits_Details.pdf#page=62]. Which plan do you have — Northwind Standard or Northwind Health Plus? Like in the example above, other models typically avoid asking a clarifying question by instead addressing every possible scenario (covering all their bases!), resulting in a fairly long answer. Arguably, it's a better user experience to ask the clarifying question, so that the user can get an answer tailored to their specific situation and not get confused by other possibilities. The primary drawback is the additional back-and-forth for the final answer. I did not personally see clarifying questions from the GPT-5 reasoning models, but my colleagues noticed an increase in such questions when using gpt-5 with GitHub Copilot Agent mode, so it's possible that every model in the family has an increased likelihood to ask for clarification when faced with ambiguity. Reasoning models ❤️ lists I saw a definite tendency of the GPT-5 reasoning models to output the answer as a list, even though there's nothing in the RAG system prompt that tells it to use lists. Out of the 50 questions evaluated, here are the number with answers formatted as a top-level bulleted list: gpt-4.1-mini gpt-5 gpt-5-mini gpt-5-chat 0 36 (72%) 26 (52%) 0 Here's an example of a gpt-4.1-mini answer (paragraph) versus a gpt-5 answer (list): Q: What are the coverage limitations of the Northwind Standard plan regarding clinical trials? gpt-4.1-mini gpt-5 The Northwind Standard plan covers certain clinical trial services such as diagnostic testing, treatment of the condition being studied, medications, lab services, and imaging services. However, it does not cover travel expenses associated with attending clinical trials. Additionally, any experimental treatments or services not part of the clinical trial are not covered. Coverage for other clinical trial services not explicitly listed may be considered on a case-by-case basis. Members should contact Northwind Health customer service for more details [Northwind_Standard_Benefits_Details.pdf#page=23][Northwind_Standard_Benefits_Details.pdf#page=24]. Travel expenses for attending clinical trials are not covered [Northwind_Standard_Benefits_Details.pdf#page=23][Northwind_Standard_Benefits_Details.pdf#page=24]. Experimental treatments or services that are not part of the clinical trial are not covered [Northwind_Standard_Benefits_Details.pdf#page=24]. Services or treatments deemed experimental or investigational are not covered by the plan [Northwind_Standard_Benefits_Details.pdf#page=53]. Now, is it a bad thing that the gpt-5 reasoning models use lists? Not necessarily! But if that's not the style you're looking for, then you either want to consider the gpt-5-chat model or add specific messaging in the system prompt to veer the model away from top level lists. Longer answers As we saw in overall metrics above, there was an impact of the answer length (measured in the number of characters, not tokens). Let's isolate those stats: gpt-4.1-mini gpt-5 gpt-5-mini gpt-5-chat 829 844 990 549 The gpt-5 reasoning models are generating answers of similar length to the current baseline of gpt-4.1-mini, though the gpt-5-mini model seems to be a bit more verbose. The API now has a new parameter to control verbosity for those models, which defaults to "medium". I did not try an evaluation with that set to "low" or "high", which would be an interesting evaluation to run. The gpt-5-chat model outputs relatively short answers, which are actually closer in length to the answer length that I used to see from gpt-3.5-turbo. What answer length is best? A longer answer will take longer to finish rendering to the user (even when streaming), and will cost the developer more tokens. However, sometimes answers are longer due to better formatting that is easier to skim, so longer does not always mean less readable. For the user-facing RAG chat scenario, I generally think that shorter answers are better. If I was putting these gpt-5 reasoning models in production, I'd probably try out the "low" verbosity value, or put instructions in the system prompt, so that users get their answers more quickly. They can always ask follow-up questions as needed. Fancy punctuation This is a weird difference that I discovered while researching the other differences: the GPT-5 models are more likely to use “smart” quotes instead of standard ASCII quotes. Specifically: Left single: ‘ (U+2018) Right single / apostrophe: ’ (U+2019) Left double: “ (U+201C) Right double: ” (U+201D) For example, the gpt-5 model actually responded with " I don’t know ", not with " I don't know ". It's a subtle difference, but if you are doing any sort of post-processing or analysis, it's good to know. I've also seen the models using the smart quotes incorrectly in coding contexts (like GitHub Copilot Agent mode), so that's another potential issue to look out for. I assumed that the models were trained on data that tended to use smart quotes more often, perhaps synthetic data or book text. I know that as a normal human, I rarely use them, given the extra effort required to type them. Query rewriting to the extreme Our RAG flow makes two LLM calls: the second answers the question, as you’d expect, but the first rewrites the user’s query into a strong search query. This step can fix spelling mistakes, but it’s even more important for filling in missing context in multi-turn conversations—like when the user simply asks, “what else?” A well-crafted rewritten query leads to better search results, and ultimately, a more complete and accurate answer. During my manual tests, I noticed that the rewritten queries from the GPT-5 models are much longer, filled to the brim with synonyms. For example: Q: What does a Product Manager do? gpt-4.1-mini gpt-5-mini product manager responsibilities Product Manager role responsibilities duties skills day-to-day tasks product management overview Are these new rewritten queries better or worse than the previous short ones? It's hard to tell, since they're just one factor in the overall answer output, and I haven't set up a retrieval-specific metric. The closest metric is citations_matched , since the new answer from the app can only match the citations in the ground truth if the app managed to retrieve all the same citations. That metric was generally high for these models, and when I looked into the cases where the citations didn't match, I typically thought the gpt-5 family of responses were still good answers. I suspect that the rewritten query does not have a huge effect either way, since our retrieval step uses hybrid search from Azure AI Search, and the combined power of both hybrid and vector search generally compensates for differences in search query wording. It's worth evaluating this further however, and considering using a different model for the query rewriting step. Developers often choose to use a smaller, faster model for that stage, since query rewriting is an easier task than answering a question. So, are the answers accurate? Even with a 100% groundedness score from an LLM judge, it's possible that a RAG app can be producing inaccurate answers, like if the LLM judge is biased or the retrieved context is incomplete. The only way to really know if RAG answers are accurate is to send them to a human expert. For the sample data in this blog, there is no human expert available, since they're based off synthetically generated documents. Despite two years of staring at those documents and running dozens of evaluations, I still am not an expert in the HR benefits of the fictional Contoso company. That's why I also ran the same evaluations on the same RAG codebase, but with data that I know intimately: my own personal blog. I looked through 200 answers from gpt-5, and did not notice any inaccuracies in the answers. Yes, there are times when it says "I don't know" or asks a clarifying question, but I consider those to be accurate answers, since they do not spread misinformation. I imagine that I could find some way to trick up the gpt-5 model, but on the whole, it looks like a model with a high likelihood of generating accurate answers when given relevant context. Evaluate for yourself! I share my evaluations on our sample RAG app as a way to share general learnings on model differences, but I encourage every developer to evaluate these models for your specific domain, alongside domain experts that can reason about the correctness of the answers. How can you evaluate? If you are using the same open source RAG project for Azure, deploy the GPT-5 models and follow the steps in the evaluation guide. If you have your own solution, you can use an open-source SDK for evaluating, like azure-ai-evaluation (the one that I use), DeepEval, promptfoo, etc. If you are using an observability platform like Langfuse, Arize, or Langsmith, they have evaluation strategies baked in. Or if you're using an agents framework like Pydantic AI, those also often have built-in eval mechanisms. If you can share what you learn from evaluations, please do! We are all learning about the strange new world of LLMs together.LangChain v1 is now generally available!
Today LangChain v1 officially launches and marks a new era for the popular AI agent library. The new version ushers in a more streamlined, and extensible foundation for building agentic LLM applications. In this post we'll breakdown what’s new, what changed, and what “general availability” means in practice. Join Microsoft Developer Advocates, Marlene Mhangami and Yohan Lasorsa, to see live demos of the new API and find out more about what JavaScript and Python developers need to know about v1. Register for this event here. Why v1? The Motivation Behind the Redesign The number of abstractions in LangChain had grown over the years to include chains, agents, tools, wrappers, prompt helpers and more, which, while powerful, introduced complexity and fragmentation. As model APIs evolve (multimodal inputs, richer structured output, tool-calling semantics), LangChain needed a cleaner, more consistent core to ensure production ready stability. In v1: All existing chains and agent abstractions in the old LangChain are deprecated; they are replaced by a single high-level agent abstraction built on LangGraph internals. LangGraph becomes the foundational runtime for durable, stateful, orchestrated execution. LangChain now emphasizes being the “fast path to agents” that doesn’t hide but builds upon LangGraph. The internal message format has been upgraded to support standard content blocks (e.g. text, reasoning, citations, tool calls) across model providers, decoupling “content” from raw strings. Namespace cleanup: the langchain package now focuses tightly on core abstractions (agents, models, messages, tools), while legacy patterns are moved into langchain-classic (or equivalents). What’s New & Noteworthy for Developers Here are key changes developers should pay attention to: 1. create_agent becomes the default API The create_agent function is now the idiomatic way to spin up agents in v1. It replaces older constructs (e.g. create_react_agent) with a clearer, more modular API. You can also now compose middleware around model calls, tool calls, before/after hooks, error handling, etc. 2. Standard content blocks & normalized message model One of LangChain's greatest stregnth's is it's model agnosticism. Content blocks move to standardize all outputs, so developers know exactly what to expect regardless of the model they are using. Responses from models are no longer opaque strings. Instead, they carry structured `content_blocks` which classify parts of the output (e.g. “text”, “reasoning”, “citation”, “tool_call”). 3. Multimodal and richer model inputs / outputs LangChain continues to support more than just text-based interactions, but in a more comprehensive way in v1. Models can accept and return files, images, video, etc., and the message format reflects this flexibility. This upgrade prepares us well for the next generation of models with mixed modalities (vision, audio, etc.). 4. Middleware hooks Because create_agent is designed as a pluggable pipeline, developers can now inject logic before/after model calls, before tool calls and more. New middleware such as 'human in the loop' and 'summarization' middleware have been added. This is a feature of the new package that I am most excited about it! Even with the simplified agents API, this option provides more room to customize workflows! Developers can try pre-built middleware or make their own. 5. Simplified, leaner namespace Many formerly top-level modules or helper classes have been removed or relocated to langchain-classic (or similarly stamped “legacy”) to declutter the main API surface. A migration guide is available to help projects transition from v0 to v1. While v1 is now the main line, older v0 is still documented and maintained for compatibility. What “General Availability” Means (and Doesn’t) v1 is production-ready, after testing the alpha version. The stable v0 release line remains supported for those unwilling or unable to migrate immediately. Breaking changes in public APIs will be accompanied by version bumps (i.e. minor version increments) and deprecation notices. The roadmap anticipates minor versions every 2–3 months (with patch releases more frequently). Because the field of LLM applications is evolving rapidly, the team expects continued iterations in v1—even in GA mode—with users encouraged to surface feedback, file issues, and adopt the migration path. (This is in line with the philosophy stated in docs.) Developer Callouts & Suggested Steps Some things we recommend for developers to do to get started with v1: Try the new API Now! LangChain Azure AI and Azure OpenAI have migrated to LangChain v1 and are ready to test! Learn more about using LangChain and Azure AI: Python: https://docs.langchain.com/oss/python/integrations/providers/azure_ai JavaScript: https://docs.langchain.com/oss/javascript/integrations/providers/microsoft Join us for a Live Stream on Wednesday 22 October 2025 Join Microsoft Developer Advocates Marlene Mhangami and Yohan Lasorsa for a livestream this Wednesday to see live demos and find out more about what JavaScript and Python developers need to know about v1. Register for this event here.Giving Your AI Agents Reliable Skills with the Agent Skills SDK
AI agents are becoming increasingly capable, but they often do not have the context they need to do real work reliably. Your agent can reason well, but it does not actually know how to do the specific things your team needs it to do. For example, it cannot follow your company's incident response playbook, it does not know your escalation policy, and it has no idea how to page the on-call engineer at 3 AM. There are many ways to close this gap, from RAG to custom tool implementations. Agent Skills is one approach that stands out because it is designed around portability and progressive disclosure, keeping context window usage minimal while giving agents access to deep expertise on demand. What is Agent Skills? Agent Skills is an open format for giving agents new capabilities and expertise. The format was originally developed by Anthropic and released as an open standard. It is now supported by a growing list of agent products including Claude Code, VS Code, GitHub, OpenAI Codex, Cursor, Gemini CLI, and many others. As defined in the spec, a skill is a folder on disk containing a SKILL.md file with metadata and instructions, plus optional scripts, references, and assets: incident-response/ SKILL.md # Required: instructions + metadata references/ # Optional: additional documentation severity-levels.md escalation-policy.md scripts/ # Optional: executable code page-oncall.sh assets/ # Optional: templates, diagrams, data files The SKILL.md file has YAML frontmatter with a name and description (so agents know when the skill is relevant), followed by markdown instructions that tell the agent how to perform the task. The format is intentionally simple: self-documenting, extensible, and portable. What makes this design practical is progressive disclosure. The spec is built around the idea that agents should not load everything at once. It works in three stages: Discovery: At startup, agents load only the name and description of each available skill, just enough to know when it might be relevant. Activation: When a task matches a skill's description, the agent reads the full SKILL.md instructions into context. Execution: The agent follows the instructions, optionally loading referenced files or executing bundled scripts as needed. This keeps agents fast while giving them access to deep context on demand. The format is well-designed and widely adopted, but if you want to use skills from your own agents, there is a gap between the spec and a working implementation. The Agent Skills SDK Conceptually, a skill is more than a folder. It is a unit of expertise: a name, a description, a body of instructions, and a set of supporting resources. The file layout is one way to represent that, but there is nothing about the concept that requires a filesystem. The Agent Skills SDK is an open-source Python library built around that idea, treating skills as abstract units of expertise that can be stored anywhere and consumed by any agent framework. It does this by addressing two challenges that come up when you try to use the format from your own agents. The first is where skills live. The spec defines skills as folders on disk, and the tools that support the format today all assume skills are local files. Files are inherently portable, and that is one of the format's strengths. But in the real world, not every team can or wants to serve skills from the filesystem. Maybe your team keeps them in an S3 bucket. Maybe they are in Azure Blob Storage behind your CDN. Maybe they live in a database alongside the rest of your application data. At the moment, if your skills are not on the local filesystem, you are on your own. The SDK changes where skills are served from, not how they are authored. The content and format stay the same regardless of the storage backend, so skills remain portable across providers. The second is how agents consume them. The spec defines the progressive disclosure pattern but actually implementing it in your agent requires real work. You need to figure out how to validate skills against the spec, generate a catalog for the system prompt, expose the right tools for on-demand content retrieval, and handle the back-and-forth of the agent requesting metadata, then the body, then individual references or scripts. That is a lot of plumbing regardless of where the skills are stored, and the work multiplies if you want to support more than one agent framework. The SDK solves both by separating where skills come from (providers) from how agents use them (integrations), so you can mix and match freely. Load skills from the filesystem today, move them to an HTTP server tomorrow, swap in a custom database provider next month, and your agent code does not change at all. How the SDK works The SDK is a set of Python packages organized around two ideas: storage-agnostic providers and progressive disclosure. The provider abstraction means your skills can live anywhere. The SDK ships with providers for the local filesystem and static HTTP servers, but the SkillProvider interface is simple enough that you can write your own in a few methods. A Cosmos DB provider, a Git provider, a SharePoint provider, whatever makes sense for your team. The rest of the SDK does not care where the data comes from. On top of that, the SDK implements the progressive disclosure pattern from the spec as a set of tools that any LLM agent can use. At startup, the SDK generates a skills catalog containing each skill's name and description. Your agent injects this catalog into its system prompt so it knows what is available. Then, during a conversation, the agent calls tools to retrieve content on demand, following the same discovery-activation-execution flow the spec describes. Here is the flow in practice: You register skills from any source (local files, an HTTP server, your own database). The SDK generates a catalog and tool usage instructions, which you inject into the system prompt. The agent calls tools to retrieve content on demand. This matters because context windows are finite. An incident response skill might have a main body, three reference documents, two scripts, and a flowchart. The agent should not load all of that upfront. It should read the body first, then pull the escalation policy only when the conversation actually gets to escalation. A quick example Here is what it looks like in practice. Start by loading a skill from the filesystem: from pathlib import Path from agentskills_core import SkillRegistry from agentskills_fs import LocalFileSystemSkillProvider provider = LocalFileSystemSkillProvider(Path("my-skills")) registry = SkillRegistry() await registry.register("incident-response", provider) Now wire it into a LangChain agent: from langchain.agents import create_agent from agentskills_langchain import get_tools, get_tools_usage_instructions tools = get_tools(registry) skills_catalog = await registry.get_skills_catalog(format="xml") tool_usage_instructions = get_tools_usage_instructions() system_prompt = ( "You are an SRE assistant. Use the available skill tools to look up " "incident response procedures, severity definitions, and escalation " "policies. Always cite which reference document you used.\n\n" f"{skills_catalog}\n\n" f"{tool_usage_instructions}" ) agent = create_agent( llm, tools, system_prompt=system_prompt, ) That is it. The agent now knows what skills are available and has tools to fetch their content. When a user asks "How do I handle a SEV1 incident?", the agent will call get_skill_body to read the instructions, then get_skill_reference to pull the severity levels document, all without you writing any of that retrieval logic. The same pattern works with Microsoft Agent Framework: from agentskills_agentframework import get_tools, get_tools_usage_instructions tools = get_tools(registry) skills_catalog = await registry.get_skills_catalog(format="xml") tool_usage_instructions = get_tools_usage_instructions() system_prompt = ( "You are an SRE assistant. Use the available skill tools to look up " "incident response procedures, severity definitions, and escalation " "policies. Always cite which reference document you used.\n\n" f"{skills_catalog}\n\n" f"{tool_usage_instructions}" ) agent = Agent( client=client, instructions=system_prompt, tools=tools, ) What is in the SDK The SDK is split into small, composable packages so you only install what you need: agentskills-core handles registration, validation, the skills catalog, and the progressive disclosure API. It also defines the SkillProvider interface that all providers implement. agentskills-fs and agentskills-http are the two built-in providers. The filesystem provider loads skills from local directories. The HTTP provider loads them from any static file host: S3, Azure Blob Storage, GitHub Pages, a CDN, or anything that serves files over HTTP. agentskills-langchain and agentskills-agentframework generate framework-native tools and tool usage instructions from a skill registry. agentskills-mcp-server spins up an MCP server that exposes skill tool access and usage as tools and resources, so any MCP-compatible client can use them. Because providers and integrations are separate packages, you can combine them however you want. Use the filesystem provider during development, switch to the HTTP provider in production, or write a custom provider that reads skills from your own database. The integration layer does not need to know or care. Where to go from here The full source, working examples, and detailed API docs are on GitHub: github.com/pratikxpanda/agentskills-sdk The repo includes end-to-end examples for both LangChain and Microsoft Agent Framework, covering filesystem providers, HTTP providers, and MCP. There is also a sample incident-response skill you can use to try things out. A proposal to contribute this SDK to the official agentskills repository has been submitted. If you find it useful, feel free to show your support on the GitHub issue. To learn more about the Agent Skills format itself: What are skills? covers the format and why it matters. Specification is the complete format reference for SKILL.md files. Integrate skills explains how to add skills support to your agent. Example skills on GitHub are a good starting point for writing your own. The SDK is MIT licensed and contributions are welcome. If you have questions or ideas, post a question here or open an issue on the repo.
