Mika got to speak at Resend's DevTool Night about what makes developer tools agent-ready, and what changes when your primary user isn't a human reading your docs, but an agent acting on them. Here's the full talk.
Key takeaways
- Docs is priority #1 Agents read your docs before they ever touch your product. If the docs are incomplete or ambiguous, the agent is lost before it starts.
- Authentication is the biggest friction point Auth is where agent runs stall most often: hidden prerequisites, unset keys, and OAuth flows that quietly assume a human is at the keyboard.
- Error messages make or break recovery A vague or misleading error sends an agent spiraling; a precise, actionable one lets it self-correct. Your errors are documentation.
- CLIs often assume a human is present Interactive prompts, TTY checks, and "press y to continue" break agents that have no way to answer back.
- Discoverability determines whether agents find you at all llms.txt, typed SDKs, MCP servers, machine-readable specs. If an agent can't discover your surface, it reaches for a competitor it already knows.
- Better for agents, better for humans Almost everything that makes a tool agent-ready, from clear docs to precise errors to sane defaults, makes it better for human developers too.
These come out of what we see every day at 2027.dev: thousands of Agent Experience evals across 100+ developer tools. If you want to know how agent-ready your own tool is, we can show you.
A big thank you to the team at Resend for hosting us! 🙏