Money movement
Refunds decided by policy, approved by a person when it matters
Refunds are the clearest case for human in the loop. Nobody wants a model moving money unsupervised, and nobody wants a person hand-checking a $12 return either. A threshold on an edge is the whole difference.
Teams either automate nothing and pay someone to apply a written policy, or automate everything and find out the failure mode from a chargeback report. What's missing is a step that stops and asks, without throwing away everything the run already worked out.
per resolution is what per-outcome support vendors charge, and that's on top of a helpdesk seat.
Intercom Fin published pricing, 2026
The flow
What runs when the message arrives.
Every step below is a real node type on the canvas, and the log underneath is the execution it produces. A branch the run didn't take stays dark, same as it would in the console.
- 01agent.invokerefund-triage · ses_9f3aqueued
- 02llm.calltool: orders.get412ms
- 03tool.httpGET /v1/orders/8821200 · 128ms
- 04bucket.searchrefund-policy · semantic4 hits · 24ms
- 05conditiontotal > 200 → true1ms
- 06human.waitinbox · confirmpaused
- 07human.answerconfirm → yes2.1s
- 08agent.returnrefund applied · $2401.24s
What it uses
What this leans on.
The policy is a document, not a prompt
Import the refund policy into a semantic bucket and let the run search it. Updating the policy means re-importing a file, not editing an agent.
Four ways a person can answer
Free text, one of a set of choices, a yes or no, or an object matching a JSON Schema. So an approval can carry a corrected amount rather than just consent.
Waiting is not a running execution
A parked run resumes from its step when the answer arrives, and bills as one execution however long it sat there.
Counters that do not race
`{inc(1)}` on a bucket field is applied by the store, so refunds-this-month stays correct under concurrent writers with no read-modify-write.
What it meters
One execution whether it settles automatically or waits two hours for an approval, plus one semantic search against the policy.
More
Other things people build.
Revenue
Cancellation and retention
Screen the message, read the account, and make a retention offer worth making, with a human approving anything that costs real money.
ReadSales
Lead qualification
Enrich the form submission, score it against your criteria, write it to the CRM and route it. Triggered by the webhook your form already sends.
ReadBack office
API orchestration
Turn a sequence of internal API calls into one request. Templated, branching and recorded, with no model anywhere in it.
Read