AI coding agents now open PRs, edit workflows, write migrations, and trigger deploys. The hard question is no longer who wrote this code β it's should this action execute? Decionis answers it before anything runs: allow, block, or escalate.
Who wrote this code?
Code review, ownership, and ADRs answered authorship. Humans were the bottleneck, so review kept pace.
Who authorized this action?
Agents propose and execute faster than anyone can review. The control point moves from authorship to authority β a verdict before execution.
A PR, a workflow edit, a migration, a deploy β anything an agent generates flows into your pipeline.
Against policy, required approvers, branch and environment, and risk β before the action executes.
A signed Decision Dossier records why, who approved, and which policy applied. Block holds it for a human.
One verdict before execution β allow, block, or escalate. Composes into any pipeline step.
Watch what your agents would have triggered without failing a build. Observe first, enforce when convinced.
A signed, verifiable record of every agent action: why, who approved, which policy, what risk.
Add the GitHub Action to the workflow your agents' PRs trigger. It detects agent-generated changes and posts a verdict on the PR β blocking or escalating the risky ones until a human signs off, while low-risk changes sail through.
- uses: decionis/govern@v1
id: gate
with:
api-key: ${{ secrets.DECIONIS_API_KEY }}
org-id: ${{ secrets.DECIONIS_ORG_ID }}
workflow-key: ai_change_gate
action: ai-generated-pr
comment-pr: 'true'
payload: |
{ "author": "${{ github.actor }}", "agent_generated": true }No credit card, no call.