| |
Mastering AI Agents
|
| With Matheus Pagani (Founder/CEO, Venture Miner), Nnenna Ndukwe (Dev Relations, Qodo), David Parry (Dev Advocate, Qodo), Daniel OBrien (Solns Enggr, Qodo). |
| Venue, To Be Announced |
|
Sep 16 (Tue) , 2025 @ 07:00 PM
| |
FREE |
|
|
|
|
|
|
|
|
| |
| DETAILS |
|
Hands-On Lab: Building AI-Powered Agents for Your SDLC
Building AI-Powered Agents for Your SDLC with Qodo
The Agent MCP Workshop is a hands-on, instructor-led experience that takes developers from zero to building Python-based AI agents that integrate seamlessly into their software development lifecycle (SDLC). At the core is the Model Context Protocol (MCP) - the emerging standard for how agents communicate with tools & with each other.
We'll start by preparing your Python environment, then progressively build an MCP server that powers real agent behaviors. Each branch of the repo corresponds to a new milestone: from handling simple requests, to registering tools, to enabling full agent workflows. Along the way, you'll learn how AI agents exchange context, trigger actions, & debug interactions at the protocol level.
This isn't just theory. It's a guided build-along, where your code evolves into a fully functioning, testable MCP-compatible agent system.
What You'll Learn
AI Agent Fundamentals: What makes an AI agent different from traditional automation, & why MCP matters for interoperability.
Python in Practice: Implementing JSON-RPC messaging & process communication to give your agent real-world capabilities.
Tool & Workflow Integration: How agents register, expose, & orchestrate tools across the SDLC (testing, CI/CD, code review, & beyond).
Debugging Agent Behavior: Techniques for tracing communication, routing requests, & fixing broken interactions.
End-to-End Build: By the end, you'll have a working Python MCP agent server you can extend & integrate into your own developer workflows.
Key Takeaways
A clear mental model of how AI agents work & why MCP is the standard powering the ecosystem.
A fully functional Python MCP agent server, built step-by-step during the workshop.
Reusable debugging patterns to accelerate future AI agent projects.
The confidence to extend, integrate, & contribute to real-world agentic systems for the SDLC.
|
|
|
|
|
|
|
|
