---
title: "Deriv: payment requests handled by a Slack agent where no model decides about money"
date: 2026-10-14
url: "https://morningtokens.com/workflows/deriv-payment-requests-handled-by-a-slack-agent/"
source: "https://x.com/DerivPeople/status/2109926122435776860"
issue: "https://morningtokens.com/issues/2026-10-14/"
---

# Deriv: payment requests handled by a Slack agent where no model decides about money

## How does this AI workflow work?

- **Replaces:** 20 to 40 internal payment requests a day, each taking 20 to 40 minutes of checking balances, status and history across 4 to 5 systems before executing and replying.
- **What to connect:** a Slack agent with a structured request form, read-only verifiers per scenario (40+), and an ordered rule ladder that decides execute, reject, escalate or "needs more info". The language model only writes the explanation for the reviewer, with a template fallback; a separate rule-based monitor alerts on suspicious patterns. First six weeks: 779 cases, about 254 hours saved, handling time down to under 2 minutes.
- **Who it's for:** finance, payments and operations teams, and anyone automating money or compliance steps.

Source: https://x.com/DerivPeople/status/2109926122435776860

From the Morning Tokens issue of 2026-10-14: https://morningtokens.com/issues/2026-10-14/