Welcome, quick intro to the Coding Agents Lunch & Learn, and a brief overview of today’s topic and discussion.

Welcome & Community Intro

Founder

AI Engineer

ML Developer Relations Engineer

Satyam explores how coding agents can use agents.md to capture and preserve useful knowledge from their work, creating better context for future tasks and more effective agent workflows.

Self-improving agents.md: Let your coding agent leave behind knowledge, not just code - Satyam Soni

DevEx Engineer

Open discussion and Q&A around self-improving agents.md, coding-agent workflows, and what knowledge agents should leave behind after completing a task.

Community Discussion & Q&A

Chief Happiness Engineer

Day 1

Session 27 of the Coding Agents Lunch & Learn

, our weekly community gathering for anyone interested in coding agents, agentic AI, AI-powered developer tools, and the rapidly evolving world of software development.

, a DevEx engineer and CNCF Ambassador working across agentic AI, MCP, and developer platforms, for a discussion on 

“Self-improving agents.md: Let your coding agent leave behind knowledge, not just code.”

 files are becoming an important way to give agents context, project-specific instructions, and guidance on how to work within a codebase. But what if those instructions didn’t have to remain static?

 - allowing coding agents to capture useful knowledge from their work and leave behind better context for future agent sessions, rather than simply producing code and moving on.

We’ll discuss how agents can learn from previous tasks, what knowledge is worth preserving, and how this approach could make coding-agent workflows more consistent and effective over time.

, combining Satyam’s talk with community discussion and Q&A. We’ll also explore a simple challenge:

If your coding agent could leave behind one piece of knowledge after every task, what should it be?

Bring your questions, ideas, and your own experiences with 

 and coding agents. Whether you’re already building with coding agents or just experimenting with AI-powered developer workflows, come learn from the community and join the conversation.

Coding Agents Lunch & Learn Session 27: Making Agents.md More Effective

Stage 1

Free Ticket

Track 1

Home

Forum

Events

Content

Collections

People

Contributors

Albums

Clubs

Chat

Channels

Tools

Help

The Agentic AI Foundation (AAIF) is a Linux Foundation hosted, vendor-neutral community creating open standards for transparent, interoperable AI agents across ecosystems.

Agentic AI Foundation

Your Privacy Choices

It looks like there is no account associated with the email you provided. The event is for members only. Please complete the application to join our community first.

Thank you for your interest in joining us

Thanks for your interest in joining the event. However, your account is still pending. Once it's approved, you'll be able to register for the event. Please contact us via help@mlops.community if you need support.

Pending Approval

Login to the Agentic AI Foundation community to connect with others, attend community events, and more!

Login or Sign Up for even more

To unlock all parts of the community and get the best experience, complete your profile.

Hey, complete your profile

It looks like there is no account associated with the email you provided. Please complete the application to join our community.

Thank you for your interest in joining Agentic AI Foundation.

Thanks for your interest in joining Agentic AI Foundation. We will review your request shortly and email you once it's approved. Meanwhile, please feel free to contact us via help@mlops.community for any questions.

Coding Agents Lunch & Learn Session 27: Making Agents.md More Effective

Speakers

Agenda

Attendees