community-automations/customer-insights

Research & Intel

PublicClaude subagent

Customer Insights

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
ClaudeClaude
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

    • Read

      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.

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.