Product teams sit on thousands of tickets and reviews that all hint at the same handful of problems. This automation turns that pile into a short list.
sonnet1 weekZendeskQdrantOpenAIPostgres
Claude
71ROI
82Scale
$2.4k90Saved
ROI for
README.md
Why this subagent
Product teams sit on thousands of tickets and reviews that all hint at the same handful of problems. This automation turns that pile into a short list.
It pulls tickets and reviews, clusters them into recurring themes, and tags each with sentiment and the feature it touches. The output is a ranked digest showing which issues come up most and whether they're rising, so roadmap calls rest on volume instead of the loudest single complaint.
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.
Embed each message and cluster them into recurring themes around bugs, requests, and friction.
pending
Tag each theme with sentiment and the products or features it mentions.
pending
Roll the themes into a ranked digest showing volume and trend since the last run.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Cluster support tickets and reviews into ranked product themes, each tagged with sentiment, volume, and trend.
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.