Most of your inbox is routine: confirmations, scheduling, simple questions you answer the same way every time. Handling each one by hand is a steady drain, but full automation feels risky when one wrong send could matter.
sonnet1 weekGmailOpenAIGoogle DriveSlack
Claude
92ROI
73Scale
$3.8k92Saved
ROI for
README.md
Why this subagent
Most of your inbox is routine: confirmations, scheduling, simple questions you answer the same way every time. Handling each one by hand is a steady drain, but full automation feels risky when one wrong send could matter.
This agent reads, drafts, and replies, but only auto-sends when it is confident; anything sensitive or unclear comes to you in Slack with its reasoning attached. The easy mail clears itself while you keep a hand on everything that could go wrong. You spend your attention on the messages that genuinely need 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.
For routine, low-risk emails, draft a grounded reply from your docs and prior threads.
pending
Auto-send replies that clear a confidence bar, and hold the rest as drafts for you.
pending
Hand anything sensitive or unclear to you in Slack with the thread and its reasoning.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Triage an email, then either auto-send a grounded reply above the confidence bar or return a draft plus a handoff note below it.
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.