Survey responses pile up in a tab that nobody reads after week one. This automation turns them into a digest your team actually opens.
It computes the CSAT score, clusters open comments into themes, and posts a short summary to Slack on schedule. You get the signal from the survey without scrolling through every row.
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.
Separate the numeric ratings from the open-text comments for each response.
pending
Calculate the CSAT score and group comments into recurring themes.
pending
Post a digest to Slack with the score, top themes, and a few representative quotes.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Summarize the responses into a CSAT figure and 3 to 5 themes, each with a representative quote; return JSON.
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.