Join us for Session 26 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.
This week, we’re joined by Satyam Soni, a DevEx engineer and CNCF Ambassador working across agentic AI, MCP, and developer platforms, for a discussion on agents.md and how to make it more effective for coding agents.
As coding agents become more capable, developers are increasingly using instruction files like agents.md to give agents context, establish project-specific rules, and guide how they work within a codebase. But what makes these instructions actually useful? And how can we move beyond simply writing guidelines toward making them more effective in practice?
Satyam will share what he’s learned from building a CLI for agents.md , exploring how developers can create, manage, and use agent instructions more effectively when working with coding agents.
We’ll discuss how agents.md can shape agent behavior, what makes a good instruction or rule, and some of the practical challenges that come with giving coding agents the right context without overwhelming them.
This will be a loose, conversational session rather than a tightly structured presentation. We’ll hear from Satyam about the thinking behind the CLI, what he’s learned from building it, and how these ideas can help developers get more consistent and useful results from coding agents.
We’ll then open things up for questions, discussion, and community conversation around agents.md , coding-agent instructions, developer workflows, and practical ways to improve agent behavior.
We’ll also have a community discussion around a simple challenge:
If you could only add one rule to an agents.md, what would it be?
The goal is to come up with rules that are generic, focused, concise, and practically useful, something that could make a real difference when working with coding agents.
Whether you’re building coding agents, experimenting with AI developer tools, working with agents.md, or simply curious about how developers are adapting their workflows around AI coding assistants, come join us to learn from builders, share ideas, and hang out with the community.
Bring your lunch, bring your questions, and bring your best agents.md rule.
