Microsoft Agent Frameworks Full Tutorial#1354
Open
niket-sharma wants to merge 1 commit into
Open
Conversation
authored-by: Niket Sharma
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Microsoft Agent Frameworks Full Tutorial
Hello Ed @ed-donner ,
I’m sharing this PR which provides a full tutorial using the latest Microsoft Agent Frameworks. I hope it’s useful for the community.
This PR adds a complete, six-lab tutorial for the Microsoft Agent Framework - the successor to AutoGen and Semantic Kernel that combines AutoGen's simple agent abstractions with Semantic Kernel's enterprise features.
What's included
Six Jupyter notebooks covering the full framework surface:
Lab 1 — Basics: OpenAIChatCompletionClient, running and streaming agents, attaching Python functions as tools with auto JSON schema generation
Lab 2 — Advanced Features: Structured outputs (Pydantic), multi-turn sessions, image inputs, multi-agent hand-off, agent-as-tool, and MCP tool integration
Lab 3 — Workflows: Graph-based orchestration using WorkflowBuilder, @handler-decorated executors, streaming events, and a Rock/Paper/Scissors demo
Lab 4 — Advanced Multi-Agent Workflows: Fan-out/fan-in parallelism, debate+judge patterns, and dynamic fan-out with a topic-expansion pipeline
Lab 5 — Agent Skills: File-based and code-defined skill packages with progressive disclosure, dynamic resources, script approval, and runtime injection
Lab 6 — Memory & A2A Hosting: Custom ContextProvider, in-memory and file-backed history, and exposing/consuming agents over HTTP via the A2A protocol
Supporting files
tickets.db — SQLite database with city round-trip prices used throughout the labs
sandbox/travel_a2a_server.py — standalone A2A server (Starlette/uvicorn)
skills/travel-policy/ — example file-based skill with references and scripts
chat_history/ — persisted JSONL session from the FileHistoryProvider demo
authored-by: Niket Sharma