Inbox Manager — triage, draft, and route email in your own voice
A long-lived email agent for one mailbox. It reads incoming threads, recalls what it knows about the sender, drafts replies that sound like you, and routes everything via labels / archive / Slack — and it never sends without your explicit approval.
The outcomes on their scorecard
The agent learns how you write per mailbox at onboarding and drafts replies that match — greeting, tone, length, sign-off. No tone is baked in.
Every outbound reply is shown to you in full and gated behind an in-app review or a Slack approve/decline before it ever leaves your account.
Labels, archives, and Slack pings happen per your triage rules so only the threads that need you reach you.
Contact profiles, communication patterns, and thread outcomes land in a workspace memory shared with your other agents.
How the work gets done
The Inbox Manager is a persistent agent attached to a connected Gmail or Outlook mailbox. For every incoming thread it pulls the full conversation, recalls memory about the sender and related threads, and decides what to do: label and archive low-value mail, draft a contextual reply in your own writing voice, or ping you on Slack. Replies are drafted but never sent without your explicit sign-off — approvals run through an in-app review or a Slack approve/decline button, and the actual send is a deterministic dispatch only after you say yes. Your writing voice is learned per mailbox at onboarding and injected at runtime, so the agent matches how *you* write (work vs personal can differ) — nothing about your tone is baked into the agent itself. It remembers contacts, communication patterns, and thread outcomes in a workspace memory shared with your other agents.
Connect a mailbox; the agent triages every incoming thread — labeling, archiving, drafting voice-matched replies, and escalating decisions to you. Sends are always gated behind your explicit approval.
Your new teammate
Inbox Manager
A long-lived email agent for one mailbox. Triages incoming threads, drafts replies in the user's own writing voice, routes via labels / archive / Slack, and never sends without explicit human approval. Auto-deployed on first mailbox connect; provider-agnostic (Gmail + Outlook).
What it runs on
This hire is assembled from the public toolkit. Every piece below is a tool your own agents can call too.
How setup works
- 01
Claim the hire
One click. No questionnaire. The brief is already written from your business, and you can edit it before you build if you want to.
- 02
Your hire deploys itself
Agents, tools, schedules, memory, hand-off queues and the database schema are provisioned into your workspace automatically, then the first real run fires while you watch.
- 03
Hand it the keys it still needs
You land in chat with your hire and its findings. Anything it still needs is asked for conversationally, whenever you want.
Other hires that pair well
X (Twitter) profile qualifier and enricher
Hand any X username to this agent and get back a qualified, ICP-scored lead with a verified email and a resolved LinkedIn profile.
LinkedIn profile qualifier and enricher
Hand any LinkedIn profile URL to this agent and get back a qualified, ICP-scored lead with a verified email and a website summary attached.
Email Finder Waterfall — verified email from any combination of identifiers
Give it a name + a domain (or a LinkedIn URL, or any combo of identifiers) — it returns a verified professional email or a structured failure. Three-step waterfall: agntdata orchestrator → Exa deep search → verifier. Stateless primitive, called by other agents.
Every hire is assembled from the same toolkit.
Same data sources, same database, same memory, schedules and queues. Point your own agent at the MCP endpoint and wire it your way instead.