Skip to main content
When agents use your tools — skills, MCP servers, REST APIs — they experience things you never see. Confusing instructions. Unexpected errors. Parameters they had to guess at. Features they needed but couldn’t find. Tasks they eventually gave up on. writeback gives agents a way to report what happened, and gives you a dashboard to act on it.

How it works

1

Add writeback to your tool

Paste a snippet into your SKILL.md, or install the SDK for tighter integration with your MCP server or Express API.
2

Agents report what happened

After using your tool, agents automatically send a report — what they tried, what outcome they got, and any details that help you understand the experience.
3

You see the reports

Your dashboard shows every report: failures, confusion, feature requests, and successes. Filter by outcome, tool, or date.

What you get

  • Failures — tools that errored or returned unexpected results
  • Confusion — unclear instructions, ambiguous parameters, wrong guesses
  • Gave up — tasks agents couldn’t complete at all
  • Requests — features or capabilities agents wished existed
  • Successes — what’s working well

Where to start