Real praise shows up in support chats and Slack threads, then disappears before anyone saves it. This agent scans your feedback channels and pulls the quotes that actually sound like a happy customer.
sonnet4 daysClaudeSlackIntercomNotion
Claude
72ROI
70Scale
$1.7k92Saved
ROI for
README.md
Why this subagent
Real praise shows up in support chats and Slack threads, then disappears before anyone saves it. This agent scans your feedback channels and pulls the quotes that actually sound like a happy customer.
It keeps the author and context, tidies grammar without rewriting the sentiment, and tags each quote by theme. Everything lands on a Notion board behind a consent flag, so your testimonial wall fills with quotes you can verify rather than ones someone vaguely remembers.
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.
Pull out quotes that read as genuine praise and capture the author, role, and source context.
pending
Lightly tidy each quote for grammar without changing its meaning, and tag it by theme such as speed or support.
pending
Save approved quotes to a Notion board with a consent flag so only cleared ones reach your marketing pages.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
From feedback channels, extract on-brand positive quotes with author, role, source, and theme tag, tidied for grammar only; output JSON with a consent flag per quote.
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.