Routing and Handoffs
The most common shape of a working agent system is not one clever agent. It is a cheap router in front of several narrow specialists, with a hard rule about when to give up and fetch a human.
Why routing beats one big agent
Shorter prompts
A billing specialist does not carry instructions about password resets. Less context, fewer mistakes, lower cost.
Narrow tool access
The refund tool is only reachable from the billing agent. That is a security boundary, not just tidiness.
Cheaper models where it is easy
Classification is easy. Run it on the smallest model you have, and save the big one for the hard specialist.
Somewhere to escalate
Low confidence has an obvious answer: a human. One clean exit beats an agent guessing on the 5% it cannot handle.
Optional: load a real model
Live: a support ticket router
Type a request the way a real person would write it. The router scores it against four queues, picks one, and hands off. Below the confidence threshold it stops and escalates instead of guessing, and you can move that threshold to feel the tradeoff.
The specialists behind this router
| Queue | Owns | Tools it is allowed |
|---|---|---|
| Billing | Charges, refunds, invoices, plan changes | calculator, date_math |
| Technical | Errors, outages, integrations, data problems | json_check, word_count |
| Learning | What to study, course and track questions | search_courses |
| Account | Access, contacts, data deletion, privacy | none, read only by design |
| Human | Anything under the confidence threshold, anything about legal action, and every refund over a set amount | none |
Free from AI School - no signup, everything runs in your browser.