Building an End-to-End Azure RAG Strategy Agent with MS Foundry
High-Level Architecture This architecture represents an end-to-end Retrieval-Augmented Generation (RAG) pipeline where raw documents are ingested from Azure Blob Storage, processed using Document Intelligence, transformed into embeddings via Azure OpenAI, and indexed in Azure AI Search for hybrid retrieval. A Foundry/MAF-based agent orchestrates query processing by combining user input with relevant search results and generates contextual responses, which are exposed through a FastAPI or CLI interface. This solution is composed of two main layers: 1. Data Ingestion Layer (RAG Pipeline) This layer transforms raw enterprise documents into searchable knowledge. Flow: Raw documents stored in Azure Blob Storage Supported formats: PDF, DOCX, PPTX, images, etc. Document Intelligence extraction Extracts: Text Tables Key-value pairs Structure Writes output as structured JSON back to Blob (processed/) Chunking + Embedding Documents are split into chunks Each chunk is embedded using Azure OpenAI (text-embedding-*) Indexing into Azure AI Search Creates a hybrid index: Keyword search Semantic ranking Vector search Enables flexible retrieval strategies 2. Query Layer (Strategy Agents) This layer enables intelligent query answering. Flow: User sends a query via: FastAPI endpoint CLI interface Query is handled by: Microsoft Agent Framework (MAF) agent Running on Azure AI Foundry Agent: Queries Azure AI Search Retrieves top relevant chunks Injects them into LLM prompt LLM generates grounded response This follows the standard RAG pattern: Retrieval → Augmentation → Generation End-to-End Flow Key Azure Services Used Service Purpose Azure Blob Storage Raw + processed document storage Azure AI Document Intelligence Extract structured content Azure OpenAI Embeddings + LLM generation Azure AI Search Hybrid retrieval engine Azure AI Foundry Agent orchestration Microsoft Agent Framework Agent execution layer Why this Architecture Matters This solution goes beyond basic RAG and provides: Hybrid Retrieval Combines keyword + semantic + vector search Improves recall and accuracy Structured Document Parsing Handles complex enterprise documents Extracts tables and metadata Agent-Based Orchestration Enables reasoning over retrieval results Extensible for multi-agent workflows Scalable Data Pipeline Supports continuous ingestion Works with large document collections Enterprise Considerations Use Managed Identity for secure service access Apply RBAC on Cosmos DB / Search / Storage Enable Private Endpoints for network isolation Use Guardrails + Evaluations in Foundry Summary This repository demonstrates a production-ready Azure RAG architecture: Ingest → Extract → Chunk → Embed → Index Retrieve → Reason → Generate Powered by Azure AI Foundry + Agent Framework By combining data engineering + AI orchestration, it enables enterprise AI systems that are: Accurate Grounded Extensible Repo: https://github.com/snd94/azure-rag-strategy-agent Please refer to the Microsoft Learn Documentation for further information: Azure AI Search documentation - Azure AI Search | Microsoft Learn Document Intelligence documentation - Quickstarts, Tutorials, API Reference - Foundry Tools | Microsoft Learn How to generate embeddings with Azure OpenAI in Microsoft Foundry Models - Microsoft Foundry | Microsoft Learn How to generate embeddings with Azure OpenAI in Microsoft Foundry Models - Microsoft Foundry | Microsoft Learn Microsoft Agent Framework Overview | Microsoft Learn What is Microsoft Foundry? - Microsoft Foundry | Microsoft Learn
Confidence-Aware RAG: Teaching Your AI Pipeline to Acknowledge Uncertainty
Introduction Retrieval-Augmented Generation (RAG) has become the standard architecture for grounding Large Language Models (LLMs) with enterprise data. By retrieving relevant documents before generating a response, RAG helps reduce hallucinations compared to relying on model knowledge alone. However, an important limitation remains in most implementations: RAG systems can produce confident-sounding answers even when the underlying data is incomplete, irrelevant, or missing. This happens when: • Retrieved documents are loosely related to the query • The answer exists partially but lacks key details • Retrieved sources contradict each other • The query falls entirely outside the knowledge base In enterprise environments, this behavior carries real risk. A reliable AI system must not only answer well - it must also know when not to answer. This article presents a practical confidence-aware RAG architecture using three layered strategies: retrieval confidence scoring, citation validation, and LLM-based abstention - all implemented with Azure AI Search and Azure OpenAI. The Problem: Confident Hallucination Consider a real-world enterprise scenario. An employee asks: "What is our company's parental leave policy for contractors?""What is our company's parental leave policy for contractors?" The knowledge base contains parental leave policies for full-time employees - but nothing specific to contractors. A standard RAG pipeline retrieves the closest matching document and confidently presents full-time employee policy as the answer. This outcome is worse than returning no answer. The user trusts the system, acts on incorrect information, and the error may not surface until real consequences follow. This pattern is sometimes called hallucination laundering - the RAG architecture creates the appearance of factual grounding while the response is not actually supported by the retrieved evidence. Fixing this requires deliberate confidence checkpoints at each stage of the pipeline. Architecture Overview A standard RAG pipeline follows a simple path: User Query → Retrieve Documents → Generate Answer A confidence-aware pipeline adds two explicit decision checkpoints: Each layer catches failures the previous one may miss. Together, they form a defense-in-depth approach to output reliability. Strategy 1: Retrieval Confidence Scoring The first checkpoint evaluates whether retrieved documents are genuinely relevant before passing them to the LLM. Azure AI Search returns a @search.rerankerScore when semantic ranking is enabled - a value on the 0-4 scale that reflects how well each document matches the query intent, not just keyword overlap. from azure.search.documents import SearchClient from azure.identity import DefaultAzureCredential search_client = SearchClient( endpoint=AZURE_SEARCH_ENDPOINT, index_name="enterprise-knowledge-base", credential=DefaultAzureCredential() ) def retrieve_with_confidence(query: str, threshold: float = 1.5, top_k: int = 5): results = search_client.search( search_text=query, query_type="semantic", semantic_configuration_name="default", top=top_k, select=["content", "title", "source"] ) confident_results = [] for result in results: reranker_score = result.get("@search.rerankerScore", 0) if reranker_score >= threshold: confident_results.append({ "content": result["content"], "title": result["title"], "source": result["source"], "score": reranker_score }) return confident_results If no documents clear the threshold, the pipeline abstains rather than forcing a low-quality answer: results = retrieve_with_confidence(user_query, threshold=1.5) if not results: return { "answer": ( "I don't have enough information in the knowledge base to answer " "this question. Please contact the relevant team for assistance." ), "status": "abstained_retrieval" } Threshold tuning: Start at 1.5 on the 0-4 scale. Evaluate against a labeled test set and adjust based on your precision/recall requirements. Higher thresholds reduce false positives but may increase abstention on edge cases. Strategy 2: Citation Validation Even when retrieval scores are high, the LLM may synthesize information that does not exist in the retrieved context. Citation validation addresses this by requiring the model to ground every factual claim in a specific named source - and then programmatically verifying those citations exist in the retrieved set. from openai import AzureOpenAI client = AzureOpenAI( api_key=AZURE_OPENAI_API_KEY, azure_endpoint=AZURE_OPENAI_ENDPOINT, api_version="2025-12-01-preview" ) ANSWER_WITH_CITATIONS_PROMPT = """ You are an enterprise assistant. Answer the question using ONLY the provided context. RULES: 1. Every factual claim MUST include a citation in the format [Source: <title>]. 2. If the context does not contain enough information, respond with: "I don't have sufficient information to answer this question." 3. Do NOT infer, assume, or use knowledge outside the provided context. 4. If context partially answers the question, state what you know and explicitly note what information is missing. Context: {context} Question: {question} Answer: """ def generate_answer(question: str, context: str, sources: list) -> dict: prompt = ANSWER_WITH_CITATIONS_PROMPT.format( context=context, question=question ) response = client.chat.completions.create( model=AZURE_DEPLOYMENT_NAME, messages=[{"role": "user", "content": prompt}], temperature=0 ) answer = response.choices[0].message.content.strip() validation = validate_citations(answer, sources) return {"answer": answer, "citation_check": validation} The validation function checks that every citation in the answer maps to a document that was actually retrieved: import re def validate_citations(answer: str, sources: list) -> dict: cited = re.findall(r'\[Source:\s*(.+?)\]', answer) source_titles = {s["title"].lower().strip() for s in sources} valid, invalid = [], [] for citation in cited: if citation.lower().strip() in source_titles: valid.append(citation) else: invalid.append(citation) return { "total_citations": len(cited), "valid": valid, "invalid": invalid, "is_trustworthy": len(invalid) == 0 and len(cited) > 0 } If is_trustworthy is False, the pipeline flags the response for review or suppresses it: if not generation["citation_check"]["is_trustworthy"]: return { "answer": "I found related information but cannot provide a reliable answer based on the available sources.", "status": "abstained_citation" } Strategy 3: LLM-Based Abstention Scoring The third layer adds a second LLM call that acts as a quality judge - explicitly evaluating whether the generated answer is well-supported by the retrieved context, independent of citation formatting. ABSTENTION_JUDGE_PROMPT = """ You are an answer quality judge. Given a question, retrieved context, and a generated answer, evaluate whether the answer is fully supported by the context. Respond ONLY in JSON format: {{ "verdict": "supported" | "partial" | "unsupported", "confidence": <float between 0.0 and 1.0>, "reasoning": "<brief explanation>" }} Question: {question} Context: {context} Answer: {answer} """ def judge_answer(question: str, context: str, answer: str) -> dict: import json prompt = ABSTENTION_JUDGE_PROMPT.format( question=question, context=context, answer=answer ) response = client.chat.completions.create( model=AZURE_DEPLOYMENT_NAME, messages=[{"role": "user", "content": prompt}], temperature=0 ) return json.loads(response.choices[0].message.content.strip()) Integrate the judge with a confidence threshold of 0.6: judgement = judge_answer(user_query, context, generation["answer"]) if judgement["verdict"] == "unsupported" or judgement["confidence"] < 0.6: return { "answer": "I don't have sufficient information to answer this question confidently.", "status": "abstained_judge" } if judgement["verdict"] == "partial": generation["answer"] += ( "\n\nNote: This answer may be incomplete. " "Some aspects of your question were not covered in the available documents." ) End-to-End Pipeline Combining all three strategies gives a complete confidence-aware pipeline: def confidence_aware_rag(user_query: str) -> dict: # Layer 1: Retrieve with confidence gating results = retrieve_with_confidence(user_query, threshold=1.5) if not results: return { "answer": "I don't have enough information in the knowledge base to answer this.", "status": "abstained_retrieval" } context = "\n\n".join(r["content"] for r in results) # Layer 2: Generate with citation requirements generation = generate_answer(user_query, context, results) if not generation["citation_check"]["is_trustworthy"]: return { "answer": "I found related information but cannot provide a reliable answer.", "status": "abstained_citation" } # Layer 3: Judge the answer judgement = judge_answer(user_query, context, generation["answer"]) if judgement["verdict"] == "unsupported" or judgement["confidence"] < 0.6: return { "answer": "I don't have sufficient information to answer this question confidently.", "status": "abstained_judge" } if judgement["verdict"] == "partial": generation["answer"] += ( "\n\nNote: This answer may be incomplete. " "Some aspects of your question were not covered in available documents." ) return { "answer": generation["answer"], "status": "answered", "confidence": judgement["confidence"], "sources": [r["source"] for r in results[:3]] }def confidence_aware_rag(user_query: str) -> dict: # Layer 1: Retrieve with confidence gating results = retrieve_with_confidence(user_query, threshold=1.5) if not results: return { "answer": "I don't have enough information in the knowledge base to answer this.", "status": "abstained_retrieval" } context = "\n\n".join(r["content"] for r in results) # Layer 2: Generate with citation requirements generation = generate_answer(user_query, context, results) if not generation["citation_check"]["is_trustworthy"]: return { "answer": "I found related information but cannot provide a reliable answer.", "status": "abstained_citation" } # Layer 3: Judge the answer judgement = judge_answer(user_query, context, generation["answer"]) if judgement["verdict"] == "unsupported" or judgement["confidence"] < 0.6: return { "answer": "I don't have sufficient information to answer this question confidently.", "status": "abstained_judge" } if judgement["verdict"] == "partial": generation["answer"] += ( "\n\nNote: This answer may be incomplete. " "Some aspects of your question were not covered in available documents." ) return { "answer": generation["answer"], "status": "answered", "confidence": judgement["confidence"], "sources": [r["source"] for r in results[:3]] } Choosing the Right Strategies for Your Use Case Each strategy adds a layer of safety at a different cost. The right combination depends on the stakes involved in your deployment. Strategy Added Cost Latency Best For Retrieval Confidence Scoring None (uses existing search scores) None All RAG applications - this should be universal Citation Validation Minimal (regex post-processing) Negligible Regulated industries, compliance, audit trails LLM Abstention Judge One additional LLM call +1-3 seconds High-stakes decisions - financial, legal, medical For most enterprise applications, combining retrieval scoring and citation validation provides a strong baseline with minimal overhead. The judge layer is most valuable when incorrect answers carry significant business or compliance risk. Threshold calibration There is a meaningful tradeoff in threshold selection. Setting thresholds too high reduces hallucination but increases abstention - the system may refuse to answer even when reliable information is available. The recommended approach is to build a labeled evaluation set of query/answer pairs, run the pipeline at multiple threshold values, and select the point that meets your precision/recall requirements for the specific domain. When to Apply This Pattern Confidence-aware RAG is most valuable in deployments where: Data coverage is uneven - the knowledge base may have detailed coverage in some areas and gaps in others, making it difficult to predict when retrieval will be reliable Errors carry downstream consequences - healthcare documentation, legal and compliance search, financial reporting, and regulated industries where a wrong answer is worse than no answer Users have varying expertise - non-expert users may not recognize a plausible-sounding but incorrect response, making transparent uncertainty signals especially important Audit or traceability requirements apply - the ability to trace each answer back to a specific source with a confidence signal supports governance and review workflows Conclusion Building a RAG system that retrieves documents and generates responses is relatively straightforward. Building one that understands the limits of its own knowledge requires deliberate design. The three strategies covered here - retrieval confidence scoring, citation validation, and LLM-based abstention - form a layered defense against the most common failure mode in production RAG systems: the confident, well-formatted, completely unreliable answer. The most dangerous AI system is not one that fails openly. It is one that fails silently, with confidence. Teaching your pipeline to say "I don't know" is not a limitation. It is a feature that builds user trust and makes enterprise AI adoption sustainable over time.
Introducing PII Shield: A Privacy Proxy for Every LLM Call
Why do we need a utility like PII Shield? Let’s start with an uncomfortable truth: modern AI systems are swimming in sensitive data - often without us fully realizing the risks we’re taking. The data is sensitive. Names, emails, phone numbers, credit cards, IBANs, SSNs, Aadhaar, PAN, Driving Licenses, UPI IDs, addresses - all of them frequently appear in user prompts, RAG documents, and tool inputs. Prompts leaving trust boundary: Even when the model lives in your own subscription - Azure OpenAI, a Foundry deployment, a self-hosted OSS model - the prompt still travels through SDKs, gateways, observability stacks etc. Before it gets to LLM, the inference layer often logs, evaluates, or fine-tunes against what it sees. Any of those hops could be a potential exposure of raw PII if not handled well. Changing regulatory asks: EU AI Act, India's DPDP Act, CCPA, HIPAA, PCI-DSS and a dozen sectoral rules now explicitly cover AI-driven processing. “Not knowing that your data may get stored elsewhere” is not an option anymore. The ad-hoc fixes don't scale. Most teams start with a regex or two. Then they add another team, another use case, another language, another ID format — and the regex file becomes a tar pit nobody wants to touch. The damage from getting this wrong is asymmetric. When controls hold and decisions are sound, nothing remarkable happens. The AI feature launches, threats are contained, and the system does what it was designed to do. But when security assumptions fail, the consequences compound fast. A single misstep can trigger public disclosures, regulatory scrutiny, financial penalties and more. That imbalance is why security can’t be treated as a finishing step. We need a single, well-tested, observable layer that sits between every AI application in the organisation and every model it talks to - and makes sure raw PII never crosses that boundary. Introducing PII Shield "PII Shield" is an intelligent anonymization layer that sits between your AI application and the LLM. It detects PII, applies a configurable privacy action per entity type, and - when you want it to - reverses the anonymization after the LLM has done its work. At a glance: REST API: /anonymize, /deanonymize and /apps - built with FastAPI. PII detection via Microsoft Presidio, with a pluggable NLP backend (spaCy, ONNX, Stanza, HuggingFace Transformers). Custom recognisers for India specific identifiers: Aadhaar, PAN, Driving Licence (all 36 states), PIN code, UPI ID, Indian phone numbers — plus 100+ Presidio defaults. Per-entity strategies: replace, hash (SHA-256), encrypt (PQC ML-KEM-768 + AES-256-GCM) or fake Multi-tenant: register applications via POST /apps, configure strategies per app, route via the X-App-Id header. Reversible by design: the "Anonymise → LLM → De-anonymise" sandwich pattern means the LLM only sees anonymized values (e.g. {{PERSON_1}} and {{EMAIL_ADDRESS_2}} etc.), never the real values. Library mode: pip install pii_shield and use the engine directly for batch jobs, no FastAPI required. Observability built in - Open Telemetry traces/metrics/logs, dual-backend (OTLP for local Grafana LGTM, Azure Monitor for production), pre-built Grafana dashboards Before we go deep into how this works, let's understand a few key concepts that this utility is centered around. Entities and recognisers An entity is a single, contiguous piece of PII that PII Shield treats as one unit of redaction - for example PERSON, EMAIL_ADDRESS, PHONE_NUMBER, CREDIT_CARD, IBAN_CODE, LOCATION, IN_AADHAAR, IN_PAN, IN_DRIVING_LICENSE, IN_UPI_ID. Each entity has: a type (the label above) that determines which placeholder format and which anonymisation strategy applies. a span in the original text - start and end character offsets - so the anonymiser can replace exactly the right slice without disturbing the surrounding text. a confidence score (0.0–1.0) reported by whichever recogniser found it, which the downstream code uses to drop low-quality hits or break ties between overlapping matches. a stable identity within the request - two occurrences of "Rahul Sharma" are the same entity instance, so they collapse to a single {{PERSON_1}} placeholder rather than {{PERSON_1}} and {{PERSON_2}}. That property is what makes coreference survive the round-trip through the LLM. A recogniser is the component that actually finds entities of a given type in text. PII Shield uses three recognizers, and they typically run together: NLP recognisers rely on the language model loaded by the Presidio Analyzer (spaCy / ONNX / Stanza / Transformers). They're the right tool for entities that have no fixed shape such as PERSON, LOCATION, ORGANIZATION, NRP where context and grammar matter more than format. E.g. "Rahul met Priya in Bengaluru" can't be detected with regex; the model must understand that those tokens are people and a place. Pattern recognisers (extension of the PatternRecognizer Class) are small Python classes that combine three things: one or more regex patterns (e.g. the 12-digit Aadhaar layout, the AAAAA9999A PAN structure, a state-prefixed Driving Licence number); a list of context keywords that boost confidence when they appear nearby (aadhaar, uidai, licence, dl, pan, card, dob); and a base confidence score plus an optional validator function for IDs with a checksum (Aadhaar's Verhoeff digit, PAN's structural rules, IBAN's mod-97). The regex says "this could be an Aadhaar"; the context boost says "and the word 'aadhaar' is three tokens to the left, so I'm now very sure" and the validator says "the checksum agrees, accept it." That layering is what keeps false positives in check on noisy CRM notes and chat transcripts. Hybrid / deny-list recognisers sit on top, for things like an internal project codename list or a customer-id format that's specific to your business. When the Analyzer runs, every recogniser scores the same span independently; overlapping hits are reconciled (highest-confidence wins, longer spans absorb shorter ones), and a final list of (entity type, start, end, score) tuples is what the anonymiser sees. Adding a new recognizer is easy with the YAML configuration approach. Refer to the below document for details how-to-add-a-recognizer The Sandwich Pattern We call it a sandwich pattern because two thin layers of PII Shield wrap around the LLM call: a) the top slice (anonymise) replaces every detected entity with a stable, opaque placeholder before the prompt ever leaves your trust boundary, b) the bottom slice (de-anonymise) puts the original values back when the response returns. The LLM in the middle is just the filling - it reasons over {{PERSON_1}} and {{EMAIL_ADDRESS_2}} instead of "Rahul Sharma" and "rahul@example.com", and it has no idea that anything was ever swapped. This is what makes the pattern so easy to retrofit: your application keeps its existing prompts, the LLM keeps its existing API, and the only "PII Shield" component that knows the real values is the very short-lived mapping. Coreference still works end-to-end because {{PERSON_1}} is the same person everywhere in the prompt - and, almost always, everywhere in the response too. Encrypted entities use ML-KEM-768 + AES-256-GCM by default — a NIST-standardised post-quantum KEM. High level design The diagram below depicts key components of “PII Shield”. User / Client App: The end user (or a downstream service) who initiates the request that eventually reaches an AI workload. They are unaware of the redaction layer; from their perspective the AI app responds with full, restored PII. AI Application (Agent / RAG / Chat): The customer's GenAI workload (chatbot, agentic flow, RAG pipeline). It owns the business logic but does not call the LLM directly with raw user data. Instead, it routes every prompt through PII Shield first and only forwards the anonymized result. This keeps the AI app free of redaction logic and lets the same shield be reused across multiple workloads. PII Shield (FastAPI): The central, stateless service. Every request flows through this single boundary, which makes it the natural place to enforce policy, rate-limit, audit, and instrument. Internally it is composed of several cooperating layers: REST API - the public surface: POST /anonymize_unique (detect + redact in one call, returning a session ID), POST /deanonymize (restore using that session ID), plus /apps and /apps/{id}/config for tenant onboarding and per-app strategy configuration. Health, metrics, and OpenAPI docs are exposed alongside. Presidio Engine: the detection-and-redaction core, built on Microsoft Presidio and split into two stages - Analyze: runs the configured NLP backend (spaCy for fastest CPU inference, ONNX for quantized speed, Stanza for higher recall, or Hugging Face Transformers for state-of-the-art models like IndicNER) and PII Shield's own custom recognizers (Aadhaar, PAN, IFSC, UPI, IN_BANK_ACCOUNT, IN_PHONE, IN_PIN_CODE, CKYC, PRAN, APAAR, GeoCoordinate, NaturalDate, etc.). Each detected span carries a confidence score and is disambiguated using context-keyword boosting. Anonymizer (Operators): applies the per-entity strategy chosen by the app config: replace (placeholder tokens like {{IN_AADHAAR_1}} for the LLM-sandwich pattern), hash (irreversible SHA-256, for analytics on hashed values), encrypt (reversible AES-GCM or post-quantum Kyber for compliance-sensitive flows), or fake (format-preserving synthetic values from Faker for safe demo / synthetic-test datasets). State Stores: there are two logical stores, both backed by Redis but with different lifetimes and access patterns: Session Mapping Store: short-lived UUID→entity-map records that power the sandwich pattern (anonymize → call LLM → de-anonymize the response back to original values). The default TTL is intentionally short (seconds-to-minutes) so plaintext mappings don't linger. App Registry: long-lived per-app configuration: entity-type strategies, allow-lists, entity-type-allow-lists, encryption-key references, and a curated allow-list of fictional brand names. This is what makes the platform multi-tenant with per-tenant policy. Telemetry: Uses OpenTelemetry SDK, and auto-instruments every stage of the pipeline: span per request, metrics for entity-type counts/anonymization latency/cache hit rate, and structured logs with trace correlation. The same OTLP stream can be split between Azure Monitor and a self-hosted Grafana stack. LLM (Azure OpenAI / OSS): The downstream model. PII Shield's contract guarantees it only ever receives anonymized text; raw PII never crosses the trust boundary into the model provider's tenancy. This satisfies most data-residency, DPDP, and GDPR concerns by construction rather than by audit after the fact. Azure Monitor / OTLP → Grafana: This is where OpenTelemetry data lands. Operators get pre-built Grafana dashboards (request volume by entity type, p95/p99 latency per stage, per-app usage, error breakdowns) so production issues — a misbehaving recognizer, a slow NLP backend, a noisy app — are diagnosed from a single pane. Playground & Admin UI: Two Streamlit front-ends come bundled with the platform. The Playground lets developers paste arbitrary text, switch NLP backends, and instantly see what gets detected and how it is redacted — invaluable for tuning recognizers and demos. The Admin UI lets operators register applications, set per-entity strategies, manage allow-lists, and view live entity stats. Both call the same REST API, so anything the UI does is reproducible from a script or CI pipeline. Request flow at a glance - A user types a message into the AI application — say, a chatbot that helps customers with banking queries. Before the application sends anything to the language model, it hands the raw text over to PII Shield through the /anonymize_unique endpoint. PII Shield runs the text through its detection pipeline, swaps every piece of personal information for a stable placeholder token, and returns two things to the AI app: the redacted text and a short-lived session ID. The application then calls the LLM with this safe, placeholder-laden prompt — the model never sees a real Aadhaar number, account number, or phone number. Once the LLM responds, the AI app posts that response back to PII Shield's /deanonymize endpoint along with the same session ID it received earlier. PII Shield looks up the session, restores every placeholder in the LLM's reply with the original value, and hands the fully restored text back to the application, which delivers it to the user. From the user's perspective the conversation feels completely natural — they see their own details, in their own words, exactly as they'd expect. Behind the scenes, the session mapping that made the round-trip possible is automatically dropped from Redis the moment its TTL expires, so plaintext PII never lingers in the system longer than it has to. In parallel, every stage of this flow emits OpenTelemetry traces, metrics, and logs to the observability stack, giving operators a clear, real-time view of what was detected, how long each step took, and how the system is behaving in production. The entire set-up could be deployed on premises as well as on any of the clouds by replacing components with corresponding cloud offerings. Below is an example in Azure - Container apps is used to host the REST services, Azure Cache for Redis is for the state store, Application Insights, Log Ananlutics and Azure Managed Grafana are used for telemetry. Please refer to the codebase here for the implementation and deployment scripts (local & Azure). code repository pii-shield How does it work? The sandwich pattern explained earlier has three phrases: Anonymize LLM Processing De-anonymize Anonymize When the app sends POST /anonymize with "Call Rahul Sharma at rahul@example.com about Aadhaar 2345 6789 0123.", PII Shield does five things in order: Resolve config. If an X-App-Id header is present, the app's per-entity strategy map is loaded from Redis (with a short in-process cache to keep the hot path fast). If absent, global defaults apply. Detect. The Presidio Analyzer runs the configured NLP backend (spaCy / ONNX / Transformers) plus all built-in and custom pattern recognisers. The output is a list of spans — (entity_type, start, end, score, text) tuples — possibly overlapping, possibly with low-confidence noise. Post-analyse. Adjacent locations and PIN codes get merged into a single ADDRESS, overlapping detections are deduped (longest wins, ties broken by score), context keywords boost confidence, and entries below threshold are dropped. This is the difference between "raw Presidio output" and "something safe to anonymise". Assign unique placeholders. For each distinct PII value, a numbered placeholder is minted: {{PERSON_1}}, {{PERSON_2}}, … The numbering is per entity type, per request, and ordering is stable — the same person mentioned three times in the input gets the same {{PERSON_1}} everywhere. This is what lets the LLM reason about coreference correctly. Apply operators. For each entity, the per-app strategy decides what to write into the output: replace → the placeholder above (reversible; mapping kept). hash → {ENTITY}_<sha256-prefix>> (one-way; not added to entity_mapping — there's nothing to restore). encrypt → {{{ENTITY}_ENC_<base64-ciphertext>}} using ML-KEM-768 + AES-256-GCM (reversible without keeping a mapping; the ciphertext is self-contained). fake → a synthetic value from the locale-aware faker (irreversible; useful for demos and synthetic test data). The reversible mapping {placeholder → original} is then saved to the session store (in-memory dict keyed by a fresh UUID by default; swappable for Redis or a database). The response carries the id, the anonymized_text, and entity_mapping for inspection: { "id": "a1b2c3d4-...", "anonymized_text": "Call {{PERSON_1}} at {{EMAIL_ADDRESS_1}} about Aadhaar {{IN_AADHAAR_1}}.", "entity_mapping": { "{{PERSON_1}}": "Rahul Sharma", "{{EMAIL_ADDRESS_1}}": "rahul@example.com", "{{IN_AADHAAR_1}}": "2345 6789 0123" } } LLM Processing The app sends the anonymised text to the LLM exactly as it would have sent the original. The model treats {{PERSON_1}}, {{IN_AADHAAR_1}}, etc. as opaque proper nouns and reasons over them naturally. Because each distinct value got a stable, unique placeholder, the model doesn't lose coreference: "Tell {{PERSON_1}} that their Aadhaar {{IN_AADHAAR_1}} has been verified" still makes perfect sense. The response usually preserves the placeholders verbatim — sometimes the LLM rewrites half the sentence, but as long as the placeholders are still in there somewhere, de-anonymisation will work. De-anonymize The app calls POST /deanonymize with the session id and the LLM's response. PII Shield does three things: Fetch the mapping for that id from the session store (single dict lookup; sub-microsecond). Replace placeholders in the text — longest placeholder first. This matters: a naïve replacement could let {{PERSON_1}} clobber the inner part of {{PERSON_10}}. Sorting by length descending is a small detail with big consequences. Decrypt encrypted entities in-place. Encrypted entities don't appear in the session mapping (the ciphertext is the placeholder), so they're handled separately: any {{ENTITY_ENC_…}} token in the text is base64-decoded and decrypted with the configured backend (PQC by default; Fernet auto-detected for backwards compatibility). Importantly, the input text to /deanonymize does not have to match what /anonymize produced. The LLM may have rewritten everything around the placeholders - added text, translated, summarised - and PII Shield will still cleanly restore the PII wherever the placeholders appear. Only the placeholders trigger replacement; everything else passes through untouched. The library mode The application can also be used as a library if you do not want to deploy it as a service for batch use cases. Here is an example: from pii_shield import PiiShieldEngine engine = PiiShieldEngine() # load NLP model once, reuse result = engine.anonymize("Rahul's Aadhaar is 2345 6789 0123") # "<PERSON_1>'s Aadhaar is <IN_AADHAAR_1>" restored = engine.deanonymize(result.anonymized_text, result.entity_mapping) The BatchProcessor currently handles CSVs and DataFrames with thread/process parallelism - useful for ad-hoc file processing and batch offline pipelines. What's next PII Shield is the foundation. Where it really starts to pay off is when you wire it into the rest of your AI stack so that no developer can accidentally bypass it. There are two more blogs in the series: PII Shield as middleware in Microsoft Agent Framework Agents are versatile. They invoke tools, fan out to sub-agents, cache intermediate context, and call LLMs from places you didn't expect. The next post will show how to plug PII Shield in as a middleware in Microsoft Agent Framework — automatically anonymising every prompt going out to a model and de-anonymising every response coming back, transparently to the agent author. No more "did we remember to scrub this one?". PII Shield + Azure API Management (APIM) For organisations standardising on APIM as their LLM gateway, the natural place for PII Shield is inside the policy pipeline. The follow-up post will cover integrating PII Shield with APIM so that every request to an LLM backend — regardless of which app or team made it — is intercepted, anonymised, forwarded, and de-anonymised on the way back. One policy, organisation-wide privacy.From Terminal to Autonomous Coding: Mastering GitHub Copilot CLI ACP Server
Introduction The rise of AI-powered development is no longer just about autocomplete—it’s about autonomous agents that can think, act, and collaborate. At the center of this transformation is the Agent Client Protocol (ACP) and its integration with GitHub Copilot CLI. If you’ve ever wanted to: Integrate Copilot into your own tools Build custom AI-driven developer workflows Orchestrate coding agents in CI/CD Then understanding the GitHub Copilot CLI ACP Server is a game-changer. This article will take you from zero to advanced, covering concepts, architecture, setup, and real-world use cases. What Is Agent Client Protocol (ACP)? The Agent Client Protocol (ACP) is an open standard designed to connect clients (like IDEs or tools) with AI agents in a consistent and interoperable way. Why ACP Exists Before ACP: Every IDE needed custom integration for each AI agent Every agent needed custom APIs per editor ACP solves this by introducing a universal communication layer. Key Idea “Any editor can talk to any agent.” Core Capabilities ACP enables: Standardized messaging between client and agent Streaming responses Tool execution with permissions Session lifecycle management Multi-agent coordination This makes ACP a foundation layer for the agentic developer ecosystem. What Is GitHub Copilot CLI ACP Server? GitHub Copilot CLI can run as an ACP-compatible server, exposing its AI capabilities programmatically. 👉 In simple terms: It turns Copilot into a backend AI agent service that any tool can connect to. According to GitHub Docs: Copilot CLI can run in ACP mode using a flag It supports standardized communication via ACP It enables integration with IDEs, pipelines, and custom tools Architecture: How ACP + Copilot CLI Works Components Component Role Client Sends prompts, receives responses ACP Protocol Standard communication layer Copilot CLI AI agent executing tasks System Files, repos, tools Getting Started (Beginner Level) Install GitHub Copilot CLI Ensure: Copilot subscription is active CLI installed and authenticated Start ACP Server Default (stdio mode – recommended) TCP Mode (for remote systems) stdio: Best for IDE integration TCP: Best for distributed systems Connect Using ACP Client (Example) Using TypeScript SDK: You: Start Copilot as a process Create streams Initialize connection Send prompt Receive streaming response ACP uses: NDJSON streams over stdin/stdout Event-driven communication ACP Workflow Explained A typical flow looks like this: Step-by-step lifecycle Initialize connection Create session Send prompt Agent processes task Streaming updates returned Optional tool execution (with permissions) Session ends ACP supports: Text + multimodal inputs Incremental responses Cancellation and control Real-World Use Cases IDE Integration (Custom Editors) Build your own AI-powered editor: Connect via ACP Send code context Receive suggestions CI/CD Automation Imagine: Use ACP to: Auto-fix bugs Generate tests Refactor code Multi-Agent Systems ACP enables: Copilot + other agents working together Task delegation Workflow orchestration Custom Developer Tools Examples: AI code review dashboards Internal dev assistants ChatOps integrations Advanced Concepts Session Management ACP allows: Isolated sessions Custom working directories Context persistence Streaming Responses Instead of waiting: Receive responses in chunks Build real-time UIs Permission Handling ACP includes: Tool execution approvals Security boundaries Controlled automation Extensibility ACP supports: Multiple SDKs (TypeScript, Python, Rust, Kotlin) Custom clients Future protocol evolution ACP vs Traditional Integration Feature Traditional APIs ACP Integration Custom per tool Standardized Streaming Limited Native Multi-agent Hard Built-in Extensibility Low High Interoperability Poor Excellent Why ACP + Copilot CLI Is a Big Deal This combination unlocks: ✅ Platform-level AI integration No more vendor lock-in per editor ✅ True agentic workflows Agents don’t just suggest—they act ✅ Ecosystem growth Any tool can plug into Copilot Challenges & Considerations ACP is still in public preview Requires understanding of: Streams Async communication Debugging agent workflows can be complex Future of Developer Experience ACP represents a shift toward: “AI-native development platforms” Future possibilities: Fully autonomous CI/CD pipelines Cross-agent collaboration Self-healing codebases Final Thoughts The GitHub Copilot CLI ACP Server is not just a feature—it’s a foundation for the next generation of software development. If you are: A developer → build smarter tools A tech lead → design AI-driven workflows A CTO aspirant → understand this deeply Then ACP is something you must master early. Quick Summary ACP = Standard protocol for AI agents Copilot CLI = Can run as ACP server Enables = IDEs, CI/CD, multi-agent systems Key power = interoperability + automation
The Future of Agentic AI: Inside Microsoft Agent Framework 1.0
Agentic AI is rapidly moving beyond demos and chatbots toward long‑running, autonomous systems that reason, call tools, collaborate with other agents, and operate reliably in production. On April 3, 2026, Microsoft marked a major milestone with the General Availability (GA) release of Microsoft Agent Framework 1.0, a production‑ready, open‑source framework for building agents and multi‑agent workflows in.NET and Python. [techcommun...rosoft.com] In this post, we’ll deep‑dive into: What Microsoft Agent Framework actually is Its core architecture and design principles What’s new in version 1.0 How it differs from other agent frameworks When and how to use it—with real code examples What Is Microsoft Agent Framework? According to the official announcement, Microsoft Agent Framework is an open‑source SDK and runtime for building AI agents and multi‑agent workflows with strong enterprise foundations. Agent Framework provides two primary capability categories: 1. Agents Agents are long‑lived runtime components that: Use LLMs to interpret inputs Call tools and MCP servers Maintain session state Generate responses They are not just prompt wrappers, but stateful execution units. 2. Workflows Workflows are graph‑based orchestration engines that: Connect agents and functions Enforce execution order Support checkpointing and human‑in‑the‑loop scenarios This leads to a clean separation of responsibilities: Concern Handled By Reasoning & interpretation Agent Execution policy & control flow Workflow This separation is a foundational design decision. High‑Level Architecture From the official overview, Agent Framework is composed of several core building blocks: Model clients (chat completions & responses) Agent sessions (state & conversation management) Context providers (memory and retrieval) Middleware pipeline (interception, filtering, telemetry) MCP clients (tool discovery and invocation) Workflow engine (graph‑based orchestration) Conceptual Flow 🌟 What’s New in Version 1.0 Version 1.0 marks the transition from "Release Candidate" to "General Availability" (GA). Production-Ready Stability: Unlike the earlier experimental packages, 1.0 offers stable APIs, versioned releases, and a commitment to long-term support (LTS). A2A Protocol (Agent-to-Agent): A new structured messaging protocol that allows agents to communicate across different runtimes. For example, an agent built in Python can seamlessly coordinate with an agent running in a .NET environment. MCP (Model Context Protocol) Support: Full integration with the Model Context Protocol, enabling agents to dynamically discover and invoke external tools and data sources without manual integration code. Multi-Agent Orchestration Patterns: Stable implementations of complex patterns, including: Sequential: Linear handoffs between specialized agents. Group Chat: Collaborative reasoning where agents discuss and solve problems. Magentic-One: A sophisticated pattern for task-oriented reasoning and planning. Middleware Pipeline: The new middleware architecture lets you inject logic into the agent's execution loop without modifying the core prompts. This is essential for Responsible AI (RAI), allowing you to add content safety filters, logging, and compliance checks globally. DevUI Debugger: A browser-based local debugger that provides a real-time visual representation of agent message flows, tool calls, and state changes. Code Examples Creating a Simple Agent (C#) From Microsoft Learn : using Azure.AI.Projects; using Azure.Identity; using Microsoft.Agents.AI; AIAgent agent = new AIProjectClient( new Uri("https://your-foundry-service.services.ai.azure.com/api/projects/your-project"), new AzureCliCredential()) .AsAIAgent( model: "gpt-5.4-mini", instructions: "You are a friendly assistant. Keep your answers brief."); Console.WriteLine(await agent.RunAsync("What is the largest city in France?")); This shows: Provider‑agnostic model access Session‑aware agent execution Minimal setup for production agents Creating a Simple Agent (Python) from agent_framework.foundry import FoundryChatClient from azure.identity import AzureCliCredential client = FoundryChatClient( project_endpoint="https://your-foundry-service.services.ai.azure.com/api/projects/your-project", model="gpt-5.4-mini", credential=AzureCliCredential(), ) agent = client.as_agent( name="HelloAgent", instructions="You are a friendly assistant. Keep your answers brief.", ) result = await agent.run("What is the largest city in France?") print(result) The same agent abstraction applies across languages. When to Use Agents vs Workflows Microsoft provides clear guidance: Use an Agent when… Use a Workflow when… Task is open‑ended Steps are well‑defined Autonomous tool use is needed Execution order matters Single decision point Multiple agents/functions collaborate Key principle: If you can solve the task with deterministic code, do that instead of using an AI agent. 🔄 How It Differs from Other Frameworks Microsoft Agent Framework 1.0 distinguishes itself by focusing on "Enterprise Readiness" and "Interoperability." Feature Microsoft Agent Framework 1.0 Semantic Kernel / AutoGen LangChain / CrewAI Philosophy Unified, production-ready SDK. Research-focused or tool-specific. High-level, developer-friendly abstractions. Integration Deeply integrated with Microsoft Foundry and Azure. Varied; often requires more glue code. Generally cloud-agnostic. Interoperability Native A2A and MCP for cross-framework tasks. Limited to internal ecosystem. Uses proprietary connectors. Runtime Identical API parity for .NET and Python. Primarily Python-first (SK has C#). Primarily Python. Control Graph-based deterministic workflows. More non-deterministic/experimental. Mixture of role-based and agentic. 🛠️ Key Technical Components Agent Harness: The execution layer that provides agents with controlled access to the shell, file system, and messaging loops. Agent Skills: A portable, file-based or code-defined format for packaging domain expertise. Implementation Tip: If you are coming from Semantic Kernel, Microsoft provides migration assistants that analyze your existing code and generate step-by-step plans to upgrade to the new Agent Framework 1.0 standards. Microsoft Agent Framework Version 1.0 | Microsoft Agent Framework Agent Framework documentation 🎯 Summary Microsoft Agent Framework 1.0 is the "grown-up" version of AI orchestration. By standardizing the way agents talk to each other (A2A), discover tools (MCP), and process information (Middleware), Microsoft has provided a clear path for taking AI experiments into production. For more detailed guides, check out the official Microsoft Agent Framework DocumentationMicrosoft Agent Framework - .NET AI Community StandupIf You're Building AI on Azure, ECS 2026 is Where You Need to Be
Let me be direct: there's a lot of noise in the conference calendar. Generic cloud events. Vendor showcases dressed up as technical content. Sessions that look great on paper but leave you with nothing you can actually ship on Monday. ECS 2026 isn't that. As someone who will be on stage at Cologne this May, I can tell you the European Collaboration Summit combined with the European AI & Cloud Summit and European Biz Apps Summit is one of the few events I've seen where engineers leave with real, production-applicable knowledge. Three days. Three summits. 3,000+ attendees. One of the largest Microsoft-focused events in Europe, and it keeps getting better. If you're building AI systems on Azure, designing cloud-native architectures, or trying to figure out how to take your AI experiments to production — this is where the conversation is happening. What ECS 2026 Actually Is ECS 2026 runs May 5–7 at Confex in Cologne, Germany. It brings together three co-located summits under one roof: European Collaboration Summit — Microsoft 365, Teams, Copilot, and governance European AI & Cloud Summit — Azure architecture, AI agents, cloud security, responsible AI European BizApps Summit — Power Platform, Microsoft Fabric, Dynamics For Azure engineers and AI developers, the European AI & Cloud Summit is your primary destination. But don't ignore the overlap, some of the most interesting AI conversations happen at the intersection of collaboration tooling and cloud infrastructure. The scale matters here: 3,000+ attendees, 100+ sessions, multiple deep-dive tracks, and a speaker lineup that includes Microsoft executives, Regional Directors, and MVPs who have built, broken, and rebuilt production systems. The Azure + AI Track - What's Actually On the Agenda The AI & Cloud Summit agenda is built around real technical depth. Not "intro to AI" content, actual architecture decisions, patterns that work, and lessons from things that didn't. Here's what you can expect: AI Agents and Agentic Systems This is where the energy is right now, and ECS is leaning in. Expect sessions covering how to design agent workflows, chain reasoning steps, handle memory and state, and integrate with Azure AI services. Marco Casalaina, VP of Products for Azure AI at Microsoft, is speaking if you want to understand the direction of the Azure AI platform from the people building it, this is a direct line. Azure Architecture at Scale Cloud-native patterns, microservices, containers, and the architectural decisions that determine whether your system holds up under real load. These sessions go beyond theory you'll hear from engineers who've shipped these designs at enterprise scale. Observability, DevOps, and Production AI Getting AI to production is harder than the demos suggest. Sessions here cover monitoring AI systems, integrating LLMs into CI/CD pipelines, and building the operational practices that keep AI in production reliable and governable. Cloud Security and Compliance Security isn't optional when you're putting AI in front of users or connecting it to enterprise data. Tracks cover identity, access patterns, responsible AI governance, and how to design systems that satisfy compliance requirements without becoming unmaintainable. Pre-Conference Deep Dives One underrated part of ECS: the pre-conference workshops. These are extended, hands-on sessions typically 3–6 hours that let you go deep on a single topic with an expert. Think of them as intensive short courses where you can actually work through the material, not just watch slides. If you're newer to a particular area of Azure AI, or you want to build fluency in a specific pattern before the main conference sessions, these are worth the early travel. The Speaker Quality Is Different Here The ECS speaker roster includes Microsoft executives, Microsoft MVPs, and Regional Directors, people who have real accountability for the products and patterns they're presenting. You'll hear from over 20 Microsoft speakers: Marco Casalaina — VP of Products, Azure AI at Microsoft Adam Harmetz — VP of Product at Microsoft, Enterprise Agent And dozens of MVPs and Regional Directors who are in the field every day, solving the same problems you are. These aren't keynote-only speakers — they're in the session rooms, at the hallway track, available for real conversations. The Hallway Track Is Not a Cliché I know "networking" sounds like a corporate afterthought. At ECS it genuinely isn't. When you put 3,000 practitioners, engineers, architects, DevOps leads, security specialists in one venue for three days, the conversations between sessions are often more valuable than the sessions themselves. You get candid answers to "how are you actually handling X in production?" that you won't find in documentation. The European Microsoft community is tight-knit and collaborative. ECS is where that community concentrates. Why This Matters Right Now We're in a period where AI development is moving fast but the engineering discipline around it is still maturing. Most teams are figuring out: How to move from AI prototype to production system How to instrument and observe AI behaviour reliably How to design agent systems that don't become unmaintainable How to satisfy security and compliance requirements in AI-integrated architectures ECS 2026 is one of the few places where you can get direct answers to these questions from people who've solved them — not theoretically, but in production, on Azure, in the last 12 months. If you go, you'll come back with practical patterns you can apply immediately. That's the bar I hold events to. ECS consistently clears it. Register and Explore the Agenda Register for ECS 2026: ecs.events Explore the AI & Cloud Summit agenda: cloudsummit.eu/en/agenda Dates: May 5–7, 2026 | Location: Confex, Cologne, Germany Early registration is worth it the pre-conference workshops fill up. And if you're coming, find me, I'll be the one talking too much about AI agents and Azure deployments. See you in Cologne.
Building an Enterprise HR Chatbot with Multi-Strategy RAG and Live Agent Handoff on Azure
HR teams deal with thousands of employee questions every day — policy lookups, leave balances, case escalations, and sensitive topics like harassment or misconduct. AI chatbots can handle the routine stuff and free up HR advisors for the hard cases. But most chatbot projects get stuck at basic Q&A. They can't handle multi-country policies, employee slang, or smooth handoffs to a real person. This post covers how we built Eva, a production HR chatbot using Microsoft Bot Framework and Semantic Kernel on Azure. I'll focus on three problems and how we solved them: Getting accurate answers when employees and policy documents use different words Handing off to a live human advisor in real time Catching answer quality regressions automatically Why basic RAG isn't enough for HR Retrieval-Augmented Generation (RAG) — fetching relevant documents and feeding them to an LLM — is the standard approach. But plain RAG breaks down in HR for a few reasons: Vocabulary mismatch. An employee asks "How does misconduct affect my ACB?" but the policy document says "Annual Cash Bonus eligibility criteria." The search doesn't connect the two. Multi-country ambiguity. The same question can have different answers depending on the employee's country, grade, or role. Sensitive topics. Questions about harassment, disability, or whistleblowing should go to a human, not get an AI-generated answer. Ranking noise. Search results often include globally relevant but locally irrelevant documents. Eva handles these with a layered pipeline: query augmentation → multi-index search → LLM reranking → answer generation → citation handling. Architecture at a glance Layer Technology Bot framework Microsoft Agents SDK (aiohttp) LLM orchestration Semantic Kernel Primary LLM Azure OpenAI Service (GPT-4.1 / GPT-4o) Knowledge search Azure AI Search (hybrid + vector) Live agent chat Salesforce MIAW via server-sent events Evaluation Azure AI Evaluation SDK + custom LLM judge Config Pydantic-settings + Azure App Configuration + Key Vault Four retrieval strategies, controlled by feature flags Instead of one search approach, Eva supports four — toggled by feature flags so we can A/B test per country without code changes. They run in a priority cascade: HyDE (Hypothetical Document Embeddings) Instead of searching with the employee's question, the LLM first generates a hypothetical policy document thatwouldanswer it. We embed that synthetic document and use it as the search query. Since a hypothetical answer is closer in embedding space to the real answer than the original question is, this bridges vocabulary gaps effectively. Step-back prompting The LLM broadens the question. "How does misconduct affect my ACB?" becomes "What is the Annual Cash Bonus policy and what factors affect eligibility?" This works well when answers live in broader policy sections. Query rewrite The LLM expands abbreviations and adds HR domain context, then runs a hybrid (text + vector) search. Standard search (fallback) Basic intent classification with hybrid search. No augmentation. All four strategies return the same Pydantic model, so the rest of the pipeline doesn't care which one ran. The team can enable HyDE globally, roll out step-back to specific countries, or revert instantly if something underperforms. LLM reranking After pulling results from both a country-specific index and a global index, Eva optionally reranks them using a RankGPT-style approach — the LLM scores document relevance with a bias toward local content. If reranking fails for any reason, it falls back to the original ordering so the pipeline keeps moving. Answer generation with local vs. global context The answer stage separates retrieved documents into local context (country-specific) and global context (company-wide), injected as distinct prompt sections. The LLM returns a structured response with reasoning, the actual answer, citations, and a coverage classification (full, partial, or denial). Prompts are stored as version-controlled .txt files with per-model variants (e.g., gpt-4o.txt, gpt-4.1.txt), resolved at runtime. This makes prompts reviewable in PRs and deployable without code changes. Live agent handoff with Salesforce When Eva determines a question needs a human — sensitive topic, complex case, or the employee simply asks — it hands off to a Salesforce advisor in real time. SSE streaming. Eva keeps a persistent HTTP connection to Salesforce for real-time messages, typing indicators, and session end signals. Session resilience. Session state persists across three layers — in-memory cache, Azure Cosmos DB, and Bot Framework turn state — to survive restarts and failovers. Message delivery workers. Each session has a dedicated async worker with exponential backoff retry. Overflow messages go to a failed messages list rather than being silently dropped. Queue position updates. While employees wait, Eva queries Salesforce for queue position and sends rate-limited updates. Context handoff. On session start, Eva sends the full conversation transcript so advisors don't ask employees to repeat themselves. Automated evaluation Eva includes an evaluation framework that runs as a separate process, testing against ground-truth Q&A pairs from CSV files. Factual questions are scored using Azure AI's SimilarityEvaluator on a 1–5 scale, with optional relevance and groundedness checks. Sensitive questions (harassment, disability, whistleblowing) use a custom LLM judge that checks whether the response acknowledges sensitivity and directs the employee to create a case or speak with an advisor. A deviation detector flags score drops between runs. SQLite stores results for trending, and Application Insights powers dashboards. Long evaluation runs support resume — the framework skips already-completed test cases on restart. Key takeaways Make retrieval strategies swappable. Feature flags let you A/B test without redeploying. Separate local and global knowledge explicitly. Don't rely on the LLM to figure out which country's policy applies. Invest in evaluation early. Ground-truth datasets with factual and behavioral scoring catch regressions that manual testing misses. Build resilience into live agent handoff. Multi-tier session recovery and retry logic prevent dropped conversations. Treat prompts as code. File-based, model-variant-aware prompts are easier to maintain than inline strings. Use Pydantic for structured LLM outputs. Typed models catch bad output at the validation boundary instead of letting it propagate. Get started Semantic Kernel documentation — LLM orchestration with plugins and structured outputs Azure OpenAI Service quickstart — Deploy GPT-4o or GPT-4.1 Azure AI Search vector search tutorial — Hybrid and vector search indices Microsoft Bot Framework SDK — Build bots for Teams and web Azure AI Evaluation SDK — Score for similarity, relevance, and groundedness⚡Foundry Toolkit for VS Code: A Deep Dive on GA
As we shared in the announcement, Microsoft Foundry Toolkit for Visual Studio Code is now generally available. In this deep dive, we walk through everything that’s in the GA release — from the rebrand and extension consolidation, to model experimentation, agent development, evaluations, and on-device AI for scientists and engineers pushing the boundaries of edge hardware. Whether you’re exploring your first model, shipping a production agent, or squeezing performance from edge hardware, Foundry Toolkit meets you where you are. 🧪The Fastest Way to Start Experimenting with AI Models You’ve heard about a new model and want to try it right now — not after spinning up infrastructure or writing boilerplate API code. That’s exactly what Microsoft Foundry Toolkit is built to deliver. With a Model Catalog spanning 100+ models — cloud-hosted from GitHub, Microsoft Foundry, OpenAI, Anthropic, and Google, plus local models via ONNX, Foundry Local, or Ollama — you go from curiosity to testing in minutes. The Model Playground is where experimentation lives: compare two models side by side, attach files for multimodal testing, enable web search, adjust system prompts, and watch streaming responses come in. When something works, View Code generates ready-to-use snippets in Python, JavaScript, C#, or Java — the exact API call you just tested, translated into your language of choice and ready to paste. 🤖Building AI Agents: From Prototype to Production Foundry Toolkit supports the full agent development journey with two distinct paths and a clean bridge between them. Path A: The Prototyper: No Code Required Agent Builder is a low-code interface that lets you take an idea, define instructions, attach tools, and start a conversation — all without writing a line of code. It’s the fastest way to validate whether an agent concept actually works. You can: Write and refine instructions with the built-in Prompt Optimizer, which analyzes your instructions and suggests improvements Connect tools from the Tool Catalog — browse tools from the Foundry public catalog or local MCP servers, configure them with a few clicks, and wire them into your agent Configure MCP tool approval — decide whether tool calls need your sign-off or can run automatically Switch between agents instantly with the quick switcher, and manage multiple agent drafts without losing work (auto-save has you covered) Save to Foundry with a single click and manage your agents from there. The result is a working, testable agent in minutes — perfect for validating use cases or prototyping features before investing in a full codebase. Path B: The Professional Team: Code-First, Production-Ready For teams building complex systems — multi-agent workflows, domain-specific orchestration, production deployments — code gives you control. Foundry Toolkit scaffolds production-ready code structures for Microsoft Agent Framework, LangGraph, and other popular orchestration frameworks. You’re not starting from scratch; you’re starting from a solid foundation. Once your agent is running, Agent Inspector turns debugging from guesswork into real engineering: Hit F5to launch your agent with full VS Code debugger support — breakpoints, variable inspection, step-through execution Watch real-time streaming responses, tool calls, and workflow graphs visualize as your agent runs Double-click any node in the workflow visualization to jump straight to the source code behind it Local tracing captures the full execution span tree across tool calls and delegation chains — no external infrastructure needed When you’re ready to ship, one-click deployment packages your agent and deploys it to a production-grade runtime on Microsoft Foundry Agent Service as a hosted-agent. The Hosted Agent Playground lets you test it directly from the VS Code sidebar, keeping the feedback loop tight. The Bridge: From Prototype to Code, Seamlessly These paths aren’t silos — they’re stages. When your Agent Builder prototype is ready to grow, export it directly to code with a single click. The generated project includes the agent’s instructions, tool configurations, and scaffolding — giving your engineering team a real starting point rather than a rewrite. GitHub Copilot with the Microsoft Foundry Skill keeps momentum going once you’re in code. The skill knows the Agent Framework patterns, evaluation APIs, and Foundry deployment model. Ask it to generate an agent, write an evaluation, or scaffold a multi-agent workflow, and it produces code that works with the rest of the toolkit. 🎯Evaluations: Quality Built Into the Workflow At every stage — prototype or production — integrated evaluations let you measure agent quality without switching tools. Define evaluations using familiar pytest syntax, run them from VS Code Test Explorer alongside your unit tests, and analyze results in a tabular view with Data Wrangler integration. When you need scale, submit the same definitions to run in Microsoft Foundry. Evaluations become versioned, repeatable, and CI-friendly — not one-off scripts you hope to remember. 💻Unlock AI's Full Capabilities on Edge Device AI running on your device — at your pace, without data leaving your machine. Cloud-hosted AI is convenient — but it's not always the right fit. Local models offer: Privacy and Compliance: Your data stays on your machine. No round-trips to a server. Cost control: Run as many inferences as you want — no per-token billing. Offline capability: Works anywhere, even without internet access. Hardware leverage: Modern Windows devices are built for localAI. That's why we're bringing a complete end-to-end workflow for discovering, running, converting, profiling, and fine-tuning AI models directly on Windows. Whether you're a developer exploring what models can do, an engineer optimizing models for production, or a researcher training domain-specific model adapters, Foundry Toolkit gives you the tools to work with local AI without compromise. Model Playground: Try Any Local Model, Instantly As we mentioned at the beginning of this article, the Model Playground is your starting point — not only for cloud models but also for local models. It includes Microsoft's full catalog of models, including the Phi open model family and Phi Silica — Microsoft's local language model optimized for Windows. As you go deeper, the Playground also supports any LLM model you've converted locally through the Conversion workflow — add it to My Resources and try it immediately in the same chat experience. Model Conversion: From Hugging Face to Hardware-Ready on Windows Getting a model from a research checkpoint to something that runs efficiently on your specific hardware is non-trivial. Foundry Toolkit's conversion pipeline handles the full transformation for a growing selection of popular HuggingFace models: Hugging Face → Conversion → Quantization → Evaluation → ONNX The result: a model optimized for Windows ML — Microsoft's unified runtime for local AI on Windows. All supported hardware targets are aligned with Windows ML's execution provider ecosystem: MIGraphX (AMD) NvTensorRtRtx (NVIDIA) OpenVINO (Intel) QNN (Qualcomm) VitisAI (AMD) Why Windows ML matters for you: Windows ML lets your app automatically acquire and use hardware-specific EPs at runtime — no device-specific code required. Your converted model runs across the full range of supported Windows hardware. Once your model has been converted successfully, Foundry Toolkit gives you everything you need to validate, share, and ship: Benchmark results: Every conversion run is automatically tracked in the History Board — giving you an easy way to validate accuracy, latency, and throughput across model variants before you ship. Sample code with Windows ML: Get ready-to-use code showing how to load and inference your converted model with the Windows ML runtime — no boilerplate hunting, just copy and go. Quick Playground via GitHub Copilot: Ask GitHub Copilot to generate a playground web demo for your converted model. Instantly get an interactive experience to validate behavior before integrating into your application. Package as MSIX: Package your converted model into an MSIX installer. Share it with teammates or incorporate into your application. Profiling: See Exactly What Your Model Is Doing Converting a local model is one thing. Understanding how it uses your hardware is another. Foundry Toolkit’s profiling tools give you real-time visibility into CPU, GPU, NPU, and memory consumption — with per-second granularity and a 10-minute rolling window. Three profiling modes cover different workflows: Attach at startup — profile a model from the moment it loads Connect to a running process — attach to an already-running inference session Profile an ONNX model directly — The Toolkit feeds data to the model and runs performance measurement directly, no application or process needed For example, when you run a local model in the Playground, you get detailed visibility into what's happening under the hood during inference — far beyond basic resource usage. Windows ML Event Breakdown surfaces how execution time is spent: a single model execution is broken down into phases — such as session initialization versus active inference — so you know whether slowness is a one-time startup cost or a per-request bottleneck. When you profile any ONNX model directly, operator-level tracing shows exactly which graph nodes and operators are dispatched to the NPU, CPU, or GPU, and how long each one takes. This makes it straightforward to identify which parts of your model are underutilizing available hardware — and where quantization, graph optimization, or EP changes will have the most impact. Fine-Tuning: Make Phi Silica Yours Generic models are capable. Domain-specific models are precise with LoRA (Low-Rank Adaption). Foundry Toolkit's fine-tuning workflow lets you train LoRA adapters for Phi Silica using your own data — no ML infrastructure required. Bring your data, customize your LoRA parameters, and submit a job to the cloud. Foundry Toolkit spins up Azure Container Apps to train your adapter with your own subscription. To validate finetuning quality, the workflow tracks training and evaluation loss curves for your LoRA adapter and cloud inference is available to validate the adapter’s behavior, helping you confirm learning progress and output quality before shipping. Once satisfied, download the adapter and incorporate it into your app for use at runtime. This is the full loop: train in the cloud → run at the edge. Domain adaptation for local AI, without standing up your own training infrastructure. 🚀One Toolkit for Every Stage. Foundry Toolkit for VS Code GA supports every stage of serious AI development: Explore 100+ models without commitment Prototype agents in minutes with no code Build production agents with real debugging, popular frameworks, and coding agent assistance Deploy to Microsoft Foundry with one click and test without leaving VS Code Measure quality with evaluations that fit your existing test workflows Optimize models for specific hardware and use cases All of it, inside VS Code. All of it, now generally available. Install Foundry Toolkit from the VS Code Marketplace → Get Started with Hands on Labs and Samples: https://github.com/Azure-Samples/Foundry_Toolkit_Samples https://github.com/microsoft-foundry/Foundry_Toolkit_for_VSCode_Lab We'd love to hear what you build. Share feedback and file issues on GitHub, and join the broader conversation in the Microsoft Foundry Community.From CI/CD to Continuous AI: The Future of GitHub Automation
Introduction For over a decade, CI/CD (Continuous Integration and Continuous Deployment) has been the backbone of modern software engineering. It helped teams move from manual, error-prone deployments to automated, reliable pipelines. But today, we are standing at the edge of another transformation—one that is far more powerful. Welcome to the era of Continuous AI. This new paradigm is not just about automating pipelines—it’s about building self-improving, intelligent systems that can analyze, decide, and act with minimal human intervention. With the emergence of AI-powered workflows inside GitHub, automation is evolving from rule-based execution to context-aware decision-making. This article explores: What Continuous AI is How it differs from CI/CD Real-world use cases Architecture patterns Challenges and best practices What the future holds for engineering teams The Evolution: From CI to CI/CD to Continuous AI 1. Continuous Integration (CI) Developers merge code frequently Automated builds and tests validate changes Goal: Catch issues early 2. Continuous Deployment (CD) Code automatically deployed to production Reduced manual intervention Goal: Faster delivery 3. Continuous AI (The Next Step) Systems don’t just execute—they think and improve AI agents analyze code, detect issues, suggest fixes, and even implement them Goal: Autonomous software evolution What is Continuous AI? Continuous AI is a model where: Software systems continuously improve themselves using AI-driven insights and automated actions. Instead of static pipelines, you get: Intelligent workflows Context-aware automation Self-healing repositories Autonomous decision-making systems Key Characteristics Feature CI/CD Continuous AI Execution Rule-based AI-driven Flexibility Low High Decision-making Predefined Dynamic Learning None Continuous Output Build & deploy Improve & optimize Why Continuous AI Matters Traditional automation has limitations: It cannot adapt to new patterns It cannot reason about code quality It cannot proactively improve systems Continuous AI solves these problems by introducing: Context awareness Learning from past data Proactive optimization This leads to: Faster development cycles Higher code quality Reduced operational overhead Smarter engineering teams Core Components of Continuous AI in GitHub 1. AI Agents AI agents act as autonomous workers inside your repository. They can: Review pull requests Suggest improvements Generate tests Fix bugs 2. Agentic Workflows Unlike YAML pipelines, these workflows: Are written in natural language or simplified formats Use AI to interpret intent Adapt based on context 3. Event-Driven Intelligence Workflows trigger on events like: Pull request creation Issue updates Failed builds But instead of just reacting, they: Analyze the situation Decide the best course of action 4. Feedback Loops Continuous AI systems improve over time using: Past PR data Test failures Deployment outcomes CI/CD vs Continuous AI: A Deep Comparison Traditional CI/CD Pipeline Developer pushes code Pipeline runs tests Build is generated Code is deployed ➡️ Everything is predefined and static Continuous AI Workflow Developer creates PR AI agent reviews code Suggests improvements Generates missing tests Fixes minor issues automatically Learns from feedback ➡️ Dynamic, intelligent, and evolving Real-World Use Cases 1. Automated Pull Request Reviews AI agents can: Detect code smells Suggest optimizations Ensure coding standards 2. Self-Healing Repositories Automatically fix failing builds Update dependencies Resolve merge conflicts 3. Intelligent Test Generation Generate test cases based on code changes Improve coverage over time 4. Issue Triage Automation Categorize issues Assign priorities Route to correct teams 5. Documentation Automation Auto-generate README updates Keep documentation in sync with code Architecture of Continuous AI Systems A typical architecture includes: Layer 1: Event Sources GitHub events (PRs, commits, issues) Layer 2: AI Decision Engine LLM-based agents Context analysis Task planning Layer 3: Action Layer GitHub Actions Scripts Automation tools Layer 4: Feedback Loop Logs Metrics Model improvement Multi-Agent Systems: The Next Level Continuous AI becomes more powerful when multiple agents collaborate. Example Setup: Code Review Agent → Reviews PRs Test Agent → Generates tests Security Agent → Scans vulnerabilities Docs Agent → Updates documentation These agents: Communicate with each other Share context Coordinate tasks ➡️ This creates a virtual AI engineering team Benefits for Engineering Teams 1. Increased Productivity Developers spend less time on repetitive tasks. 2. Better Code Quality Continuous improvements ensure cleaner codebases. 3. Faster Time-to-Market Automation reduces bottlenecks. 4. Reduced Burnout Engineers focus on innovation instead of maintenance. Challenges and Risks 1. Over-Automation Too much automation can reduce human oversight. 2. Security Concerns AI workflows may misuse permissions if not controlled. 3. Trust Issues Teams may hesitate to rely on AI decisions. 4. Cost of AI Operations Running AI agents continuously can increase costs. Best Practices for Implementing Continuous AI 1. Start Small Begin with: PR review automation Test generation 2. Human-in-the-Loop Ensure: Critical decisions require approval 3. Use Least Privilege Restrict workflow permissions. 4. Monitor and Measure Track: Accuracy Impact Cost 5. Build Feedback Loops Continuously improve models and workflows. Future of GitHub Automation The future is heading toward: Fully autonomous repositories AI-driven engineering teams Continuous optimization of software systems We may soon see: Repos that refactor themselves Systems that predict failures before they occur AI architects designing system improvements Conclusion CI/CD transformed how we build and deliver software. But Continuous AI is set to transform how software evolves. It moves us from: “Automating tasks” → “Automating intelligence” For engineering leaders, this is not just a technical shift—it’s a strategic advantage. Early adopters of Continuous AI will build faster, smarter, and more resilient systems. The question is no longer: “Should we adopt AI in our workflows?” But: “How fast can we transition to Continuous AI?”GitHub Copilot SDK and Hybrid AI in Practice: Automating README to PPT Transformation
Introduction In today's rapidly evolving AI landscape, developers often face a critical choice: should we use powerful cloud-based Large Language Models (LLMs) that require internet connectivity, or lightweight Small Language Models (SLMs) that run locally but have limited capabilities? The answer isn't either-or—it's hybrid models—combining the strengths of both to create AI solutions that are secure, efficient, and powerful. This article explores hybrid model architectures through the lens of GenGitHubRepoPPT, demonstrating how to elegantly combine Microsoft Foundry Local, GitHub Copilot SDK, and other technologies to automatically generate professional PowerPoint presentations from GitHub README files. 1. Hybrid Model Scenarios and Value 1.1 What Are Hybrid Models? Hybrid AI Models strategically combine locally-running Small Language Models (SLMs) with cloud-based Large Language Models (LLMs) within the same application, selecting the most appropriate model for each task based on its unique characteristics. Core Principles: Local Processing for Sensitive Data: Privacy-critical content analysis happens on-device Cloud for Value Creation: Complex reasoning and creative generation leverage cloud power Balancing Cost and Performance: High-frequency, simple tasks run locally to minimize API costs 1.2 Typical Hybrid Model Use Cases Use Case Local SLM Role Cloud LLM Role Value Proposition Intelligent Document Processing Text extraction, structural analysis Content refinement, format conversion Privacy protection + Professional output Code Development Assistant Syntax checking, code completion Complex refactoring, architecture advice Fast response + Deep insights Customer Service Systems Intent recognition, FAQ handling Complex issue resolution Reduced latency + Enhanced quality Content Creation Platforms Keyword extraction, outline generation Article writing, multilingual translation Cost control + Creative assurance 1.3 Why Choose Hybrid Models? Three Core Advantages: Privacy and Security Sensitive data never leaves local devices Compliant with GDPR, HIPAA, and other regulations Ideal for internal corporate documents and personal information Cost Optimization Reduces cloud API call frequency Local models have zero usage fees Predictable operational costs Performance and Reliability Local processing eliminates network latency Partial functionality in offline environments Cloud models ensure high-quality output 2. Core Technology Analysis 2.1 Large Language Models (LLMs): Cloud Intelligence Representatives What are LLMs? Large Language Models are deep learning-based natural language processing models, typically with billions to trillions of parameters. Through training on massive text datasets, they've acquired powerful language understanding and generation capabilities. Representative Models: Claude Sonnet 4.5: Anthropic's flagship model, excelling at long-context processing and complex reasoning GPT-5.2 Series: OpenAI's general-purpose language models Gemini: Google's multimodal large models LLM Advantages: ✅ Exceptional text generation quality ✅ Powerful contextual understanding ✅ Support for complex reasoning tasks ✅ Continuous model updates and optimization Typical Applications: Professional document writing (technical reports, business plans) Code generation and refactoring Multilingual translation Creative content creation 2.2 Small Language Models (SLMs) and Microsoft Foundry Local 2.2.1 SLM Characteristics Small Language Models typically have 1B-7B parameters, designed specifically for resource-constrained environments. Mainstream SLM Model Families: Microsoft Phi Family (Phi Family): Inference-optimized efficient models Alibaba Qwen Family (Qwen Family): Excellent Chinese language capabilities Mistral Series: Outstanding performance with small parameter counts SLM Advantages: ⚡ Low-latency response (millisecond-level) 💰 Zero API costs 🔒 Fully local, data stays on-device 📱 Suitable for edge device deployment 2.2.2 Microsoft Foundry Local: The Foundation of Local AI Foundry Local is Microsoft's local AI runtime tool, enabling developers to easily run SLMs on Windows or macOS devices. Core Features: OpenAI-Compatible API # Using Foundry Local is like using OpenAI API from openai import OpenAI from foundry_local import FoundryLocalManager manager = FoundryLocalManager("qwen2.5-7b-instruct") client = OpenAI( base_url=manager.endpoint, api_key=manager.api_key ) Hardware Acceleration Support CPU: General computing support GPU: NVIDIA, AMD, Intel graphics acceleration NPU: Qualcomm, Intel AI-specific chips Apple Silicon: Neural Engine optimization Based on ONNX Runtime Cross-platform compatibility Highly optimized inference performance Supports model quantization (INT4, INT8) Convenient Model Management # View available models foundry model list # Run a model foundry model run qwen2.5-7b-instruct-generic-cpu:4 # Check running status foundry service ps Foundry Local Application Value: 🎓 Educational Scenarios: Students can learn AI development without cloud subscriptions 🏢 Enterprise Environments: Process sensitive data while maintaining compliance 🧪 R&D Testing: Rapid prototyping without API cost concerns ✈️ Offline Environments: Works on planes, subways, and other no-network scenarios 2.3 GitHub Copilot SDK: The Express Lane from Agent to Business Value 2.3.1 What is GitHub Copilot SDK? GitHub Copilot SDK, released as a technical preview on January 22, 2026, is a game-changer for AI Agent development. Unlike other AI SDKs, Copilot SDK doesn't just provide API calling interfaces—it delivers a complete, production-grade Agent execution engine. Why is it revolutionary? Traditional AI application development requires you to build: ❌ Context management systems (multi-turn conversation state) ❌ Tool orchestration logic (deciding when to call which tool) ❌ Model routing mechanisms (switching between different LLMs) ❌ MCP server integration ❌ Permission and security boundaries ❌ Error handling and retry mechanisms Copilot SDK provides all of this out-of-the-box, letting you focus on business logic rather than underlying infrastructure. 2.3.2 Core Advantages: The Ultra-Short Path from Concept to Code Production-Grade Agent Engine: Battle-Tested Reliability Copilot SDK uses the same Agent core as GitHub Copilot CLI, which means: ✅ Validated in millions of real-world developer scenarios ✅ Capable of handling complex multi-step task orchestration ✅ Automatic task planning and execution ✅ Built-in error recovery mechanisms Real-World Example: In the GenGitHubRepoPPT project, we don't need to hand-write the "how to convert outline to PPT" logic—we simply tell Copilot SDK the goal, and it automatically: Analyzes outline structure Plans slide layouts Calls file creation tools Applies formatting logic Handles multilingual adaptation # Traditional approach: requires hundreds of lines of code for logic def create_ppt_traditional(outline): slides = parse_outline(outline) for slide in slides: layout = determine_layout(slide) content = format_content(slide) apply_styling(content, layout) # ... more manual logic return ppt_file # Copilot SDK approach: focus on business intent session = await client.create_session({ "model": "claude-sonnet-4.5", "streaming": True, "skill_directories": [skills_dir] }) session.send_and_wait({"prompt": prompt}, timeout=600) Custom Skills: Reusable Encapsulation of Business Knowledge This is one of Copilot SDK's most powerful features. In traditional AI development, you need to provide complete prompts and context with every call. Skills allow you to: Define once, reuse forever: # .copilot_skills/ppt/SKILL.md # PowerPoint Generation Expert Skill ## Expertise You are an expert in business presentation design, skilled at transforming technical content into easy-to-understand visual presentations. ## Workflow 1. **Structure Analysis** - Identify outline hierarchy (titles, subtitles, bullet points) - Determine topic and content density for each slide 2. **Layout Selection** - Title slide: Use large title + subtitle layout - Content slides: Choose single/dual column based on bullet count - Technical details: Use code block or table layouts 3. **Visual Optimization** - Apply professional color scheme (corporate blue + accent colors) - Ensure each slide has a visual focal point - Keep bullets to 5-7 items per page 4. **Multilingual Adaptation** - Choose appropriate fonts based on language (Chinese: Microsoft YaHei, English: Calibri) - Adapt text direction and layout conventions ## Output Requirements Generate .pptx files meeting these standards: - 16:9 widescreen ratio - Consistent visual style - Editable content (not images) - File size < 5MB Business Code Generation Capability This is the core value of this project. Unlike generic LLM APIs, Copilot SDK with Skills can generate truly executable business code. Comparison Example: Aspect Generic LLM API Copilot SDK + Skills Task Description Requires detailed prompt engineering Concise business intent suffices Output Quality May need multiple adjustments Professional-grade on first try Code Execution Usually example code Directly generates runnable programs Error Handling Manual implementation required Agent automatically handles and retries Multi-step Tasks Manual orchestration needed Automatic planning and execution Comparison of manual coding workload: Task Manual Coding Copilot SDK Processing logic code ~500 lines ~10 lines configuration Layout templates ~200 lines Declared in Skill Style definitions ~150 lines Declared in Skill Error handling ~100 lines Automatically handled Total ~950 lines ~10 lines + Skill file Tool Calling & MCP Integration: Connecting to the Real World Copilot SDK doesn't just generate code—it can directly execute operations: 🗃️ File System Operations: Create, read, modify files 🌐 Network Requests: Call external APIs 📊 Data Processing: Use pandas, numpy, and other libraries 🔧 Custom Tools: Integrate your business logic 3. GenGitHubRepoPPT Case Study 3.1 Project Overview GenGitHubRepoPPT is an innovative hybrid AI solution that combines local AI models with cloud-based AI agents to automatically generate professional PowerPoint presentations from GitHub repository README files in under 5 minutes. Technical Architecture: 3.2 Why Adopt a Hybrid Model? Stage 1: Local SLM Processes Sensitive Data Task: Analyze GitHub README, extract key information, generate structured outline Reasons for choosing Qwen-2.5-7B + Foundry Local: Privacy Protection README may contain internal project information Local processing ensures data doesn't leave the device Complies with data compliance requirements Cost Effectiveness Each analysis processes thousands of tokens Cloud API costs are significant in high-frequency scenarios Local models have zero additional fees Performance Qwen-2.5-7B excels at text analysis tasks Outstanding Chinese support Acceptable CPU inference latency (typically 2-3 seconds) Stage 2: Cloud LLM + Copilot SDK Creates Business Value Task: Create well-formatted PowerPoint files based on outline Reasons for choosing Claude Sonnet 4.5 + Copilot SDK: Automated Business Code Generation Traditional approach pain points: Need to hand-write 500+ lines of code for PPT layout logic Require deep knowledge of python-pptx library APIs Style and formatting code is error-prone Multilingual support requires additional conditional logic Copilot SDK solution: Declare business rules and best practices through Skills Agent automatically generates and executes required code Zero-code implementation of complex layout logic Development time reduced from 2-3 days to 2-3 hours Ultra-Short Path from Intent to Execution Comparison: Different ways to implement "Generate professional PPT" 3. Production-Grade Reliability and Quality Assurance Battle-tested Agent engine: Uses the same core as GitHub Copilot CLI Validated in millions of real-world scenarios Automatically handles edge cases and errors Consistent output quality: Professional standards ensured through Skills Automatic validation of generated files Built-in retry and error recovery mechanisms 4. Rapid Iteration and Optimization Capability Scenario: Client requests PPT style adjustment The GitHub Repo https://github.com/kinfey/GenGitHubRepoPPT 4. Summary 4.1 Core Value of Hybrid Models + Copilot SDK The GenGitHubRepoPPT project demonstrates how combining hybrid models with Copilot SDK creates a new paradigm for AI application development. Privacy and Cost Balance The hybrid approach allows sensitive README analysis to happen locally using Qwen-2.5-7B, ensuring data never leaves the device while incurring zero API costs. Meanwhile, the value-creating work—generating professional PowerPoint presentations—leverages Claude Sonnet 4.5 through Copilot SDK, delivering quality that justifies the per-use cost. From Code to Intent Traditional AI development required writing hundreds of lines of code to handle PPT generation logic, layout selection, style application, and error handling. With Copilot SDK and Skills, developers describe what they want in natural language, and the Agent automatically generates and executes the necessary code. What once took 3-5 days now takes 3-4 hours, with 95% less code to maintain. Automated Business Code Generation Copilot SDK doesn't just provide code examples—it generates complete, executable business logic. When you request a multilingual PPT, the Agent understands the requirement, selects appropriate fonts, generates the implementation code, executes it with error handling, validates the output, and returns a ready-to-use file. Developers focus on business intent rather than implementation details. 4.2 Technology Trends The Shift to Intent-Driven Development We're witnessing a fundamental change in how developers work. Rather than mastering every programming language detail and framework API, developers are increasingly defining what they want through declarative Skills. Copilot SDK represents this future: you describe capabilities in natural language, and AI Agents handle the code generation and execution automatically. Edge AI and Cloud AI Integration The evolution from pure cloud LLMs (powerful but privacy-concerning) to pure local SLMs (private but limited) has led to today's hybrid architectures. GenGitHubRepoPPT exemplifies this trend: local models handle data analysis and structuring, while cloud models tackle complex reasoning and professional output generation. This combination delivers fast, secure, and professional results. Democratization of Agent Development Copilot SDK dramatically lowers the barrier to building AI applications. Senior engineers see 10-20x productivity gains. Mid-level engineers can now build sophisticated agents that were previously beyond their reach. Even junior engineers and business experts can participate by writing Skills that capture domain knowledge without deep technical expertise. The future isn't about whether we can build AI applications—it's about how quickly we can turn ideas into reality. References Projects and Code GenGitHubRepoPPT GitHub Repository - Case study project Microsoft Foundry Local - Local AI runtime GitHub Copilot SDK - Agent development SDK Copilot SDK Getting Started Tutorial - Official quick start Deep Dive: Copilot SDK Build an Agent into Any App with GitHub Copilot SDK - Official announcement GitHub Copilot SDK Cookbook - Practical examples Copilot CLI Official Documentation - CLI tool documentation Learning Resources Edge AI for Beginners - Edge AI introductory course Azure AI Foundry Documentation - Azure AI documentation GitHub Copilot Extensions Guide - Extension development guide
