My lecture at MIT!✨. From Physics to Linear Algebra & Machine learning, I have learned a lot from MIT!. Yesterday, I had the honour of delivering a guest lecture on The state of AI Engineering, exploring:. - Prompt Engineering.- Retrieval Augmented Generation. - Fine-Tuning

If you found it insightful, reshare with your network. Find me → @akshay_pachaar ✔️.For more insights and tutorials on LLMs, AI Agents, and Machine Learning!.

So, that's how you can build and deploy your own Agent network using A2A protocol. To recap:.- MCP connects agents to external tools.- A2A enables agent to agent collaboration. I hope you enjoyed this tutorial! 🥂

For didactic purpose we've kept these agents very simple but they can be anything your want. Below, we send another query and again get the correct output. Check this👇

Querying the agent network. With that, we can send a query to our network and see if it is being routed to the appropriate Agent. Below, we have a query to compute the Tangent, and our router directed it correctly. Check this code👇

Next comes, client-side Agent integration. Now that Agents have been hosted and deployed, a client can integrate them into their existing applications. We also add a router to intelligently direct queries. Here's how we do it 👇

And finally, build and deploy the third agent, a Tangent Agent. Here's the full code👇

Similarly we'll build and deploy Cosine Agent. Here's the full code👇

Deploying the agent. Finally, in the main body of the agent, we deploy the Agent:. Check this code👇

Handling tasks. An Agent can have multiple skills. Thus, a handle_task method accepts the input task, uses the available skills, and returns the output. In our case, we simply invoke the Sine skill method after parsing the input. Check this code👇

Adding skills to the Agents. Each Agent has some skills that it can expose to other Agents. So the class must declare a method with the skill decorator. For instance, a skill of our SineAgent is that it can compute the Sine of a number. Here's how we do it 👇

Let's start by learning how to serve an Agent. - Create an Agent class that inherits from A2AServer. - Decorate the class with the agent decorator, specifying the agent's name, description, and version. Check this out👇

Before we code, some key concepts to understand:. 1. Agent Server: Hosts individual agents.2. Client Agent: Connects to multiple servers.3. Router: Routes queries to right agent. And here's what we'll do:.- Server 3 agents.- Build a client.- and a router

How does A2A fit with MCP?. Agentic apps need both:.- MCP connects agents to external tools.- A2A enables agent to agent collaboration. Visual below shows A2A and MCP collaboration. We've covered MCP before; today we'll focus on a hands-on A2A example.

What is A2A?. A2A (Agent2Agent) enables multiple AI agents to work together on tasks without directly sharing their internal memory, thoughts, or tools. Instead, they communicate by exchanging context, task updates, instructions, and data.

Before diving in, here's what we'll do:. - Understand A2A in simple terms. - Briefly compare A2A and MCP.- Next, we'll build three Agents and serve them locally. - Finally, we'll talk to them via the Agent2Agent protocol by Google. Let's dive in! 🚀

Agent2Agent Protocol, clearly explained (with code example):.

7 MCP projects for AI Engineers:. (with video tutorials)

If you found it insightful, reshare with your network. Find me → @akshay_pachaar ✔️.For more insights and tutorials on LLMs, AI Agents, and Machine Learning!.

This graphic summarises all the projects covered here. You can also watch them in my YouTube playlist:.

7️⃣ MCP-powered deep researcher. ChatGPT has a deep research feature. It helps you get detailed insights on any topic. Learn how you can build a 100% local alternative to it. Full walkthrough:.