Browse all guides

Run customer support with AI agents and human approval

For: small teams who want fast first responses without letting a bot talk to customers unchecked. You get: every request as a ticket, an agent that does the first pass, and a person who signs off on each customer reply.

The setup

StepWhereWhy
1. Open SupportModules → SupportA branded portal. Each request becomes a case and a ticket.
2. Choose the intake laneModules → Support: pick a board and laneAll new requests start in one lane.
3. Connect an agentWorkspace Settings → Agent ConnectionsGive it projects:read and projects:write and a grant for this project only.
4. Keep replies human-approvedAgent replies to customers need approval (on by default)An agent's customer reply waits in AIr Traffic Control until a project admin approves it.
5. Add rulesWorkspace Settings → AutomationsFor example, set a priority when a ticket enters the intake lane, or archive tickets 30 days after they are complete.

How it runs day to day

  1. A customer writes in through the portal.
  2. The agent reads the new case, sets the priority, adds a private note with what it found, and prepares a reply.
  3. A project admin reviews the reply in AIr Traffic Control and approves it. Nothing reaches the customer before that.
  4. If the case needs product work, the agent or a person creates a child Bug or Task from the Support tab. It stays linked to the case.
  5. When the fix ships, reply to the customer and resolve the case. ToDoddle blocks completing the ticket while the conversation is still open.

Tips

  • Private notes are never shown to customers. They are where the agent and the team think out loud.
  • Use Mark as spam or Block sender for abuse. Both can be undone.
  • Agents only see projects you grant. Start with one project.

Updated 2026-11-10. Owned by product.