It’s finally here! Just got an author proof copy of the designing multi-agent systems book. It’s taken over a year to get this done, and so it’s quite exciting to see it wrapping up!
Digital: buy.multiagentbook.com
Print : - ETA Nov 15 on Amazon
To illustrate this, I’d try to do a “demo a day” over the next week to showcase capabilities of the framework. The video below shows an sample app (DevUI) that ships with Agent Framework for running and debugging your Agent Framework tools.
If you are starting a new AI Agent project - try it out!
Ofcourse, frameworks are only there to simplify aspects of your work - what matters is what you build!
03.10.2025 19:07 — 👍 1 🔁 0 💬 1 📌 0
- Bring your own model, integrate with any agent
- Workflow API that lets you express business or application logic as a computation graph (this is something that was a weak spot for AutoGen)
Some highlights
- Middleware support - write hooks to control agent behaviour great for RAI, security, context engineering etc
- Support for Agents backed by various services - Azure Foundry Agent, OpenAI Responses, Google A2A agents, ofcourse with full MCP support
Agent Framework brings the production ready focus of Semantic Kernel with full C#/Python support, as well as the nimble intuitive interface of AutoGen for rapid experimentation.
github.com/microsoft/ag...
The Semantic Kernel and AutoGen
team have worked hard over the last few months to bring together the best of both frameworks for a much stronger developer experience (and to simplify the choice!). Excited to release Agent Framework in public preview!
azure.microsoft.com/en-us/blog/i...
A the AI field evolves, the value of the ML/AI PhD is changing newsletter.victordibia.com/p/you-have-a...
09.01.2025 21:29 — 👍 1 🔁 1 💬 0 📌 0
There is still more work to be done, and we are all excited to make progress with the community!
I will be writing more and showing more examples - afterall a framework is only useful to the extent that it can be used to easily express ideas.
Async stack, event-based messaging, improved observability and control, a low level extremely flexible core api and a high level api with presets, and an improved autogen studio!
14.01.2025 17:16 — 👍 1 🔁 1 💬 1 📌 0
I am incredibly excited to share the release of AutoGen v0.4.
We have learned alot from all of the emerging simple and complex ways people want to build agents and we believe this version gets us closer to those goals
With AI, we can have software creators that dont understand complex software systems they create. We’d need to explore co-creation setups that minimize this sort of outcomes.
15.01.2025 21:23 — 👍 1 🔁 1 💬 0 📌 0Yes, drivers dont know how car engines work, pilots probably dont know the details of airplane engines … but mechanics and jet engine designers do.
15.01.2025 21:23 — 👍 1 🔁 1 💬 1 📌 0
An interesting conundrum with working with AI tools (e.g., a coding assistant in this case) is that you can genuinely use it to create a complex system which you do not understand.
15.01.2025 21:23 — 👍 1 🔁 1 💬 1 📌 0
Once it is complete and communicated well, it looks straightforward and simple.
It is not.
A walk through of the new v0.4 version of AutoGen Studio.
www.youtube.com/watch?v=oum6...
PSA: Start with a non-agent baseline, invest in tools and evals, before implementing complex agentic behaviours newsletter.victordibia.com/p/4-ux-desig...
14.07.2025 18:59 — 👍 1 🔁 1 💬 0 📌 0
4 UX Design Principles for Semi-Autonomous Multi-Agent Systems
I gave a keynote talk at the June AI.Engineer conf
newsletter.victordibia.com/p/4-ux-desig...
Bonus: I cover lessons from building a multi-agent system from scratch
- How to build long-running agents with a complete Python implementation (an MCP server with a travel agent and research agents that stream updates, request input and are resumable.)
24.07.2025 22:25 — 👍 1 🔁 1 💬 0 📌 0
The article covers:
- How to build agent-to-agent communication with MCP capabilities where MCP hosts and tools both act as intelligent agents
- Four key capabilities that make MCP tools “agentic” – streaming, resumability, durability, and multi-turn interactions
Can You Build Agent2Agent Communication on MCP?
Yes.
I wrote an article about how you can compose some of the recent features within MCP( resumable streams, elicitation, sampling, and notifications ) to implement long running agents (as tools):
devblogs.microsoft.com/blog/can-you...
[1] MCP For Software Engineers | Part 1 : Building Your First Server newsletter.victordibia.com/p/mcp-for-so...
[2] Can You Build Agent2Agent Communication on MCP? Yes! developer.microsoft.com/blog/can-you...
- Resources: Defining server resources, client operations (list/read/subscribe), and real-time update notifications
- Prompts: Creating reusable LLM prompt templates that can be used to modify host application behavior without modifying client/host application code.
MCP For Software Engineers | Part 2: Interactive & Long-Running Tools (Progress streaming, User Input, Cancellation), Resources & Prompts
Most MCP tutorials only show simple request/response patterns. But MCP can handle SO much more! newsletter.victordibia.com/p/mcp-for-so...
Video walkthrough - How to build your first MCP server!
youtu.be/-yrqkwZr3Nc?...
It's taken a while .. but something's cooking ...
if you have enjoyed any of my previous writing, I think you'd find this useful too.
(Comment below if you'd like a link to early access / preorder)
22.09.2025 15:47 — 👍 1 🔁 0 💬 0 📌 0
It's taken a while .. but something's cooking ...
if you have enjoyed any of my previous writing, I think you'd find this useful too.
Video walkthrough - How to build your first MCP server!
youtu.be/-yrqkwZr3Nc?...
[1] MCP For Software Engineers | Part 1 : Building Your First Server newsletter.victordibia.com/p/mcp-for-so...
[2] Can You Build Agent2Agent Communication on MCP? Yes! developer.microsoft.com/blog/can-you...
