User feedback arrives everywhere, in chats, surveys, and app messages, and most of it evaporates. Bugs never reach engineering, feature requests never get counted, and the churn signals hide in the noise until the account is gone.
sonnet4 daysIntercomOpenAILinearSlack
Claude
100ROI
72Scale
$5.3k96Saved
ROI for
README.md
Why this subagent
User feedback arrives everywhere, in chats, surveys, and app messages, and most of it evaporates. Bugs never reach engineering, feature requests never get counted, and the churn signals hide in the noise until the account is gone.
This agent reads each piece of feedback and routes it by type: bugs and requests become Linear issues in the user's own words, praise gets logged, and churn risk pings the account owner in Slack. Nothing useful gets lost, and the product team finally sees what customers are actually asking for.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Sort each item into bug, feature request, praise, or churn risk.
pending
Open or update the matching Linear issue for bugs and feature requests with the user's words.
pending
Escalate churn-risk feedback to the account owner in Slack right away.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Classify a feedback item into bug, feature, praise, or churn risk, and return the routing target and a short rationale.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.