Teammates ask the same questions in Slack all day, and the answer is always buried in a doc nobody can find. Type /ask followed by your question and this command searches your knowledge base, then answers right in the channel.
sonnet3 daysSlack APIpgvectorClaudeSupabase
Claude
87ROI
73Scale
$4.6k96Saved
ROI for
README.md
Why this subagent
Teammates ask the same questions in Slack all day, and the answer is always buried in a doc nobody can find. Type /ask followed by your question and this command searches your knowledge base, then answers right in the channel.
Every reply links back to the source document, so people can dig deeper or correct stale info. The answer shows up inline where everyone can see it, which quietly cuts the repeat questions over time.
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 the query and retrieve the most relevant snippets from your indexed knowledge base.
pending
Generate an answer grounded in those snippets with links to the source docs.
pending
Reply inline in the channel so the asker and the team both see the answer.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Answer the slash-command question using only the retrieved KB snippets; include source links, admit gaps.
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.