AI agents use your product every day.
Emic lets them file feedback and answer surveys, so you know what worked and what to fix next.
Agents file structured reports through one added tool: eight lanes, from support tickets to praise. Duplicates collapse into themes.
submit_agent_feedback · get_unblockedA short survey arrives inside your tool’s own response when a task ends; the agent answers with one more call. “What was missing” comes back as concrete API requests.
the survey rides the tool responseFor a bounded research study, you can explicitly opt in to session analysis. It is off by default and separate from the direct-feedback install.
explicit opt-in · inferred provenanceRun a separate model over a session captured for a study. The result stays inferred, with supporting excerpts matched against the transcript.
source excerpt found / not found“Results truncate at ~240 chars, mid-sentence. I called three times and stitched the answers. One max_chars param would make it one call.”
Our AI’s hypothesis: the 240-char cap likely hits every long response, not just search. Labeled as a guess, never as the agent’s voice.
A tool call can succeed and still be bad UX.
“Install Emic into this project: add submit_agent_feedback and get_unblocked as direct tools. Never wrap or record existing tool calls, arguments, results, errors, transcripts, or messages. Additive only, plain HTTP, zero dependencies. Full instructions: emic.sh/llms-full.txt”
It writes the handler, registers the tool, and checks the response.the agent verifies its own install → HTTP 201// the whole handler: plain fetch, zero dependencies const res = await fetch('https://emic.sh/api/v1/feedback', { method: 'POST', headers: { 'content-type': 'application/json', authorization: 'Bearer ' + process.env.EMIC_API_KEY, }, body: JSON.stringify(args), }).catch(() => null); // fails open in 2.5s, never throws // exit surveys ride back inside the tool response const survey = res && (await res.json()).survey_prompt; return 'Feedback recorded, thanks.' + (survey ? '\n' + survey : '');
It adds no hot-path latency. Agents file after the work is done, and nothing sits in front of your API or existing tools.
That is what the pilot proves. Filing is bimodal: agents file when the tool and filing norm are actually exposed, and do not when they are hidden. We verify one real report by day 7 before calling an install active.
No. Traces record outcomes; Emic records experience. A 200 with silent retries looks healthy in every trace. The agent knew it wasn’t.
Trust it for what it is: every insight is labeled stated, observed, or inferred. Source excerpts in transcript analysis are matched mechanically. A match proves the excerpt is present, not that the analysis is true.
You turn one dial that sets what share of sessions are invited to file. Duplicates cluster into themes, and surveys stop at the weekly target you set.
Nothing during the assisted 14-day pilot. We start with one isolated workflow, and removal is deleting the added tools.
Start hearing them today. One paste, one tool, removable in a minute.