A busy Gmail account becomes a wall of unsorted mail. Filters only catch what you predicted in advance, so anything new lands unlabeled and the careful taxonomy you built slowly stops meaning anything.
sonnet2 daysGmailOpenAI
Claude
100ROI
68Scale
$4.7k94Saved
ROI for
README.md
Why this subagent
A busy Gmail account becomes a wall of unsorted mail. Filters only catch what you predicted in advance, so anything new lands unlabeled and the careful taxonomy you built slowly stops meaning anything.
This agent reads each message as it arrives and applies the right label from your own taxonomy based on what the email is actually about, not just a sender rule. Newsletters, client threads, and invoices sort themselves the moment they land. You open an inbox that is already organized the way you organize it.
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.
Read the sender, subject, and body to understand what the email is about.
pending
Match it to your existing label taxonomy and pick the closest fit.
pending
Apply the label on arrival and leave the message in the inbox for you to read.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Read a new email and return the single best-fit label from the user's existing taxonomy, with no new labels invented.
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.