Judgment record
CASE PL-0051 Playbook silent Question routed
Should we waive this £15 late fee?
Charged during a confirmed outage. PolicyLayer routes the question, parks the case and lets the agent keep working.
The system of record for AI agent authority
Never answer your agent twice.
When its playbook has no answer, PolicyLayer sets the case aside and asks the person who owns that decision. Your agent keeps working. Human approval turns the answer into a rule every agent can reuse.
Connect your agent ↗
Prefer to talk first? Ask about a design partnership
- 01Your team answers once
- 02The agent handles more on its own
- 03Every run starts smarter
Ask once. Approve once. Reuse the rule.
The judgment loop
PLAYBOOK v2 · 05 STEPS The result The next time the same case comes up, the answer is already there.
01 / 05 · Playbook ready
The agent could waive the fee. It didn’t know when it should.
A customer was charged a £15 late fee after trying to pay during a confirmed outage. The support agent could waive the fee, but its playbook did not say when it should.
Using a Claude Managed Agent? See the exact run → The unresolved case No rule covers this
Should we waive this £15 late fee?
The agent could waive the fee. PolicyLayer parked this case because the playbook did not say whether it should.
“Yes, waive it. The outage was ours.”
The rule this case helped produce
The answer settled this case. Human approval made the rule reusable.
The decision owner approved the limit. PolicyLayer added it to the next playbook, so the agent can point to the rule it followed.
Measured result
Seven approved rules cut the agent’s need for human judgment in half.
Across more than 50 support cases, human decisions produced seven approved rules. In the next 20, the share needing human judgment fell from 40% to 20%, repeat questions fell from six to zero, and the agent never acted beyond its rules.
Cases requiring human judgment
40% Before
20% After seven rules
Repeat questions6 → 0
Approved rules7
Actions without playbook coverage0
Only human approval changes the playbook.
PolicyLayer can capture answers and draft rules. Agents receive new authority only after a person approves it.
An answer applies only to the case that asked for it.
Until a rule is approved, the answer cannot grant authority in another case.
Rules exist only after a named human approves them.
PolicyLayer drafts from repeated decisions. A person approves, edits or rejects every rule.
Every agent using a playbook runs the same signed version.
Approved rules go into the next version of the playbook, which reaches every agent that uses it.
Unreachable means less autonomy, never more.
If PolicyLayer is unavailable, the agent falls back to its last signed playbook and gains no new authority.
Your company owns every playbook version.
Export every version and keep the same company judgment when you change model or provider.
Three MCP tools.
Keep your agent’s model, tools and schedule. Add three PolicyLayer tools; handle questions and approvals in Slack.
Running a Claude Managed Agent? See the exact setup →get_playbook Load the latest signed company playbook.
ask_policy Park the unresolved case and route one question to its decision owner.
get_answer Return the decision with its owner and context.
Existing agent → PolicyLayer MCP → Decision owners in Slack
Any model. Any agent framework. One company playbook.
PolicyLayer uses standard MCP. Your playbook stays intact across models, frameworks and MCP clients.
Automate the work that actually moves the business.
PolicyLayer expands the work agents can complete without outrunning company judgment. That means fewer stalled opportunities, less work waiting on senior people and fewer costly mistakes.
Answers become rules. Rules widen what the agent may do. The agent finishes more work.
Keep deals moving while the opportunity is live.
Move opportunities forward faster by giving agents authority to resolve more decisions in the moment.
Complete more work without another human queue.
Increase throughput while reserving senior judgment for genuinely new decisions.
Keep valuable work inside company policy.
Expand agent autonomy while keeping decisions consistent, accountable and within clear boundaries.
Agents are going to run the world’s companies. PolicyLayer is how company judgment becomes machine authority.
PolicyLayer is the system of record for AI agent authority.
Connect your agent ↗
Prefer to talk first? Ask about a design partnership