Generic drafts read like every other AI blog, so editors rewrite them from scratch. This one studies your published archive first and writes in a voice that sounds like your team.
sonnet1 weekOpenAIWordPress REST APISupabasen8n
Claude
76ROI
78Scale
$2.5k89Saved
ROI for
README.md
Why this subagent
Generic drafts read like every other AI blog, so editors rewrite them from scratch. This one studies your published archive first and writes in a voice that sounds like your team.
Every time someone edits a draft before publishing, the system saves the change and updates the voice profile. The result is a writer that learns from your corrections and needs less rework each month.
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.
Draft new posts against that profile so the rhythm matches your existing writing.
pending
Capture the human edits made before publish and store the before-and-after pairs.
pending
Fold those edits back into the voice profile so each round drifts closer to how you actually write.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Draft the post in the supplied brand voice profile; mirror its tone and cadence and avoid generic marketing phrasing.
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.