Feedback that
fixes itself.
Error trackers turn a stack trace into a fix. Nothing turns “the export button is weird on mobile” into one. fdbck triages what your users actually report and opens a draft pull request — with your own agent, on your own machine.
Free to start · no credit card · fixes are never metered
“When i tap the Approve button up top, it 'flashes' and remains there, the Status in the Details. The In Progress in the sidenav increments +1 but the Inbox doesn't increment -1”
Approve button fails to update item status/counts on activity detail page
…/[id]/RunLogAction.tsx+13Collect, triage, plan, ship
The work happens on your machine, with your own agent and your own credentials — fdbck never sees your code or your keys.
Collect
A script tag drops a feedback button into your app, or connect Zendesk, Intercom and Slack and tag what matters. Every report carries the page, the steps taken, and a PII-scrubbed snapshot.
Triage
Bug or feature, severity, confidence — on every report, ranked in an action-first inbox. Duplicates roll up into one item that carries the demand of all of them.
Plan
Work that is big or unclear gets a written approach first: what to build, which files, what still needs you to decide. You approve the plan, not the pull request.
Ship
Your own agent writes the fix on your machine, runs your test suite, and opens a draft PR — then tells the people who asked for it when it lands.
Everyone else stops at the ticket
Feedback tools organise a request and hand it to you. Coding agents write code from an issue you already wrote. Error trackers only see what crashed. fdbck is the part in between.
| Tool | Starts from | Ends at |
|---|---|---|
| Canny, Productboard | A typed request | A prioritised ticket |
| Sentry Seer | An error event | A patch |
| LogRocket | A session replay | Reproduction steps |
| Claude Code, Codex | An issue you wrote | A diff |
| fdbck | A typed request | A reviewed draft PR |
Every product above is good at what it was built for. The row that matters is the one nobody else spans.
Built to be trusted unattended
A public board people actually use
Voting, search, trending and a changelog, on your own domain. Shipped items link to the PR that fixed them, and everyone who voted gets told.
Bring your backlog with you
Import from UserVoice, Canny, Productboard, Jira or Zendesk in one upload. Vote counts come with it, so what people already asked for stays on top.
Live from the tools you already run
Zendesk, Intercom and Slack stream in over signed webhooks. Tag a ticket or react to a message and it lands in triage.
Fixes that had to prove themselves
Every fix runs in an isolated worktree and can run your test suite before the PR opens. Optional auto-merge, gated on evidence rather than confidence alone.
Multi-repo, multi-agent
Connect as many repos as you like. Run Claude Code, Codex or Gemini, and give one worker triage while another does the heavy coding.
Scriptable end to end
An MCP server for your editor, a REST API, and a CORS board API if you would rather build the board UI yourself.
Nothing ships without you
of fix attempts finish and produce a pull request. Runs paused by your agent's own usage limits retry rather than counting as failures.
model keys stored. The work runs on your machine with your subscription, so fixes and PRs are never metered or charged per use.
Every PR opens as a draft against an isolated branch, labelled and linked back to the report. Auto-merge is off until you turn it on.
fdbck stores no model keys, and never sees your source.
A small local worker does all the model and git work on your machine, with your own Claude, Codex, or Gemini and your own GitHub credentials. fdbck holds the feedback and the state of your queue — not your code, your history, or your logins.