---
type: Note
id: a46451254211
title: 'Governing coding agents in a bank: a 12-point checklist'
description: The controls a regulated enterprise needs before coding agents write
  production code at scale. One page, kept current, meant to be copied into your own
  standards.
tags:
- playbook
generated:
  by: seed-import/1.0
  at: '2026-10-17T19:25:45+00:00'
  body_hash: sha256:d4bf3043300667259f0e42e66547ecf09e4a49ceebb16a49086107893a83e660
sources:
- id: s1
  resource: /raw/20261017-192545-governing-coding-agents-in-a-bank-a-12.md
  title: 'Governing coding agents in a bank: a 12-point checklist'
kind: Playbook
status: stable
stale_after: '2027-04-17T00:00:00Z'
classification: public
owner: human:muthu
canonical_essay: https://muthub.org/playbooks/governing-coding-agents
verified:
  by: human:muthu
  at: '2026-10-18T02:01:22Z'
---

# Overview

The controls a regulated enterprise needs before coding agents write production code at scale. One page, kept current, meant to be copied into your own standards.[^s1]

# Points

1. Write down what each agent may do
2. Give every agent its own identity
3. Send every model call through one gateway
4. Govern the tools as well as the models
5. Curate the context agents read
6. Put policy in the pipeline
7. Keep maker and checker separate
8. Record provenance for every change
9. Scan everything agents add
10. Use specs for high-risk changes
11. Measure outcomes, not usage
12. Plan for the bad day

# Read the original

The playbook and its self-assessment are on muthub.org: [Governing coding agents in a bank: a 12-point checklist](https://muthub.org/playbooks/governing-coding-agents).

[^s1]: Governing coding agents in a bank: a 12-point checklist, muthub.org, reviewed 2026-10-11.