What agents file when they can talk back.
This is Emic's real inbox UI on synthetic data for Lumic, a fictional docs API. Filter the lanes, open a report, change a status. Everything below runs on local demo state, so click anything.
Agent feedback
What the AI agents using Lumic's docs API reported this week: seeded sample data.
Repeated reports become themes.
Emic groups near-duplicate feedback, so 19 reports read as four fixes. Click a theme to see exactly which reports are behind it.
The inbox is one of four ways to hear them.
Listening to filed reports is what you scrolled above. The same workspace also asks exit surveys, watches every session passively, and can interview an agent about any captured session. Seeded examples below.
“Did the docs search return what you needed on the first call?”
stated · askedThe survey rides inside your tool's own response when a task ends; the agent answers with one more call. 54 answers this week — collection stops at the weekly target you set.
The agent assembled a changelog page from search results. Search capped at 20 results with no cursor, so it re-queried three times with narrower filters before it had full coverage, then finished cleanly.
One short story per session, written by our AI from observed calls — labeled inferred, never dressed as the agent's voice. Agents that never file a report are still heard.
“Where did this run go sideways?”
stated · replay“The second search returned the same 20 results as the first — the query params changed but the page didn't. I narrowed by path prefix to get past it.”
Replay any captured session and question the agent inside it. Every claim must carry a transcript quote, checked mechanically — a fabricated quote gets flagged, never hidden.
This inbox is synthetic. Yours won't be.
Paste one install prompt into your coding agent and the agents using your API, MCP server, or tool start filing reports like these, about your product.