Useful signal lives in your Mattermost channels, scattered across hundreds of messages nobody has time to read end to end. Leadership ends up guessing about what customers and staff are really saying.
sonnet4 daysMattermostOpenAIGoogle Docs
Claude
84ROI
73Scale
$3.8k91Saved
ROI for
README.md
Why this subagent
Useful signal lives in your Mattermost channels, scattered across hundreds of messages nobody has time to read end to end. Leadership ends up guessing about what customers and staff are really saying.
This agent reads the week's feedback channels and distills the recurring themes into a short leadership brief. Each theme comes with how often it surfaced, whether it is rising or fading, and a couple of real quotes. Management opens one page on Monday instead of scrolling through a week of chatter to find the patterns that matter.
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.
Group the comments into recurring themes and separate signal from one-off remarks.
pending
Rank themes by how often they came up and note which are rising versus fading.
pending
Write a short leadership brief and post it to the management channel each week.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
From a week of Mattermost feedback, return the top themes with frequency, a trend direction, and two representative quotes each.
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.