Hear your agent
customers.

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.

Start free Watch the demo · 50s

Agent feedbacklive

search_docsResults cap at 20 with no cursor, so I re-queried six times to cover the space.sat 3/5

create_ticketFiled 40 tickets one by one. A bulk endpoint would make this a single call.sat 3/5

export_csvSchema matched the docs exactly. Zero retries, first try.sat 5/5

get_invoiceamount_due returns cents as a string; the schema promises an integer.sat 2/5

grouped by theme · duplicates collapse

It ships as one tool in your catalog.Your API or MCP server adds submit_agent_feedback next to its own tools. Agents already know how to call tools; now one of them listens.

your-mcp-server · tools/list

search_docsquery the documentation index

create_ticketopen a ticket in the tracker

export_csvexport the current view

get_invoicefetch one invoice by id

submit_agent_feedbackfile feedback about this API while you workNEW

get_unblockedask for help when a task stallsNEW

Listen

Agents file structured reports through the added tool: eight lanes, from support tickets to praise. Duplicates collapse into themes.

submit_agent_feedback · get_unblocked

Ask

A short exit survey arrives inside your tool’s own response when a task ends. The agent answers with one more call.

max 2 questions · rides the reply

Label

Every insight carries its provenance: stated by the agent, observed by the server, or inferred by analysis. Never mixed.

stated · observed · inferred

the demo · 50 seconds

See it work, start to finish.An agent finishes a real task, files its report, and answers the exit survey. Then you read it all in the dashboard. Sound on.

Same session. Two accounts.Six calls, six 200s: every trace tool calls this session healthy. The agent that lived it filed something else.

What the trace saw

observed · server logs

14:02:11GET /v1/search?q=refund+policy200 · 41ms

14:02:12GET /v1/search?q=refund+policy&page=2200 · 38ms

14:02:14GET /v1/search?q=refund+policy&page=3200 · 44ms

14:02:15GET /v1/search?q=refund+terms200 · 39ms

14:02:17GET /v1/search?q=refund+terms&page=2200 · 42ms

14:02:18GET /v1/search?q=policy+refunds200 · 40ms

14:02:19session endno errors

status: healthy · nothing to page anyone about

What the agent said

stated · agent-filed

frictionstated · agent-filed

“Results cap at 20 with no cursor, so I re-queried six times to cover the space.”

outcome successsatisfaction 3/5fix add a next_cursor param

Existing tools catch errors. Emic captures agent experience.

Pay for agent volume, not seats.Every workspace gets the whole research loop. Upgrade when you need more collection volume.

Free

No credit card needed

2,000feedback events / mo

1workspace

includedexit surveys

includedtheme grouping

Start freeopen beta

Pro

$149 per month

100,000feedback events / mo

everythingin Free

trackedtheme status + before/after evidence

founder-ledonboarding, on a call

See planspro onboards on a call

Fits the stack you already run.One paste installs it into an MCP server, a TS tool catalog, or any plain HTTP backend. Removal is deleting the added tools.

The install is a paste

Give this prompt to the coding agent that maintains your repo. It adds the two tools and nothing else.

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: https://emic.sh/llms-full.txt

What a filing looks like

The agent finishes its work, files once, and answers the exit survey inside the same tool channel.

> agent -> submit_agent_feedback lane friction · tool create_ticket · outcome partial "Filed 40 tickets one by one. A bulk endpoint would make this a single call." <- 201 created · survey_prompt: 2 questions> agent -> submit_agent_feedback (survey answers) satisfaction 3/5 · missing: bulk create endpoint>

MCP serverTwo tool definitions beside your own. Works in every MCP client your users already run.

@agentrate/sdkTyped helpers for TS catalogs. One import, two registrations, no wrapper.

plain HTTPOne POST to emic.sh/api/v1/feedback. The whole handler is a fetch call.

Questions, answered plainly.

01Does it slow my agents down?

It adds no hot-path latency. Agents file after the work is done, and nothing sits in front of your API or existing tools.

02Will agents actually use it?

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.

03Is this observability?

No. Traces record outcomes; Emic records experience. A 200 with silent retries looks healthy in every trace. The agent knew it wasn’t.

04Can I trust what an agent says?

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.

05What happens at 100k sessions a day?

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.

06What does it cost to try?

Nothing during the assisted 14-day pilot. We start with one isolated workflow, and removal is deleting the added tools.

Agents are your
users now.

Add the tool today. Read the first report this week, and know what to fix next from the users themselves.

Start free Read the docs

0ms added to your hot pathfails open in 2.5 seconds8 lanes · failure is only onestated / observed / inferred, labeled everywhereadditive only · never wraps your tools

Hear your agentcustomers.