Never answer your agent twice.
Your agent asks. The right person answers in Slack. Approval turns that answer into versioned policy for every agent you run.
Claude Code 
Codex 
Cursor 
GitHub Copilot 
VS Code 
Gemini What the playbook misses reaches a person.
PolicyLayer holds your company’s authorised playbooks; agents reach them over MCP. Uncovered decisions route to their owner in Slack. The answer resolves the case and, once approved, becomes policy for every agent.
The question goes to Customer Operations. The agent keeps working.
Seven rules. Half as many cases needed a person.
Across more than 50 real support cases, repeated human decisions became seven approved rules. These are results from the next 20 cases.
Half as many interruptions after seven approved rules.
The same people stopped being interrupted.
Approved from real decisions, not written up front.
Agents can ask. Only people can decide.
Until a reusable rule is approved, the answer grants no authority anywhere else.
A named person approves, edits or rejects the exact rule before it reaches another agent.
If PolicyLayer is unavailable, agents gain no new authority and fall back to the last signed playbook.
A question becomes an answer. An answer becomes a rule.
Customer asks for a £40 refund after Tuesday's outage. The playbook covers refunds only to £25.
Customer wants their data deleted but has an open dispute.
Hold the deletion until the dispute closes, then delete within 30 days.
One MCP surface. Four small tools.
Keep your model, framework and tools. PolicyLayer handles only the words and rules that govern what the agent may decide.
Load the latest signed company playbook.
Route an uncovered decision to its owner.
Return the answer, owner and context.
Turn a decision into a rule proposal.
Paste the endpoint into your MCP config. That is the whole integration.
Your model, framework and every existing tool stay exactly as they are.
Start with one agent. Add the fleet when the playbook has earned it.
Your company already knows the answers.
Runbooks, policy docs, or the rules buried in your system prompts: PolicyLayer turns them into proposed rules, each routed to its owner to sign.
Agents keep working exactly as they do today. PolicyLayer watches the decisions being made and surfaces the repeated ones worth turning into rules.
One authority layer. Different agent workflows.
Refunds, fee waivers and policy exceptions become reusable after the right person approves them.
See the decision loop →Claude Code, Codex and Cursor start from the same approved rules without files drifting apart.
Explore coding agents →Route uncovered decisions to owners while long-running agents keep working on everything else.
Explore managed agents →The four things people ask.
No. The case parks, the agent keeps working, and it collects the answer in a later session. Silence never becomes permission.
The playbook you give it and the questions your agents ask. Never your code, your customers, or your tools.
Agents fall back to the last signed playbook. Failure always means less autonomy, never more.
A named person, every time. Every rule records who approved it, what it covers, and when it took effect.