Give it a way to ask and keep going.
When the playbook has no answer, PolicyLayer asks the decision owner in Slack and the rest of the run continues. Repeated answers become playbook rules.
Prefer to talk first? Ask about a design partnership
One open question does not stop the run.
PolicyLayer sets aside only the piece of work the playbook cannot answer. The agent completes everything else on this run.
The agent gets what it needed.
The answer went to the agent that needed it, not into a thread nobody will find again.
The owner answers in Slack.
“Yes, waive it. The outage was ours.”
The next run finishes the work.
The agent collects the answer and completes what it set aside.
Answers compound into authority.
Third late-fee question this month, all answered the same way.
Waive late fees up to £15 during confirmed outages. Approve, edit or reject in Slack.
The next signed playbook carries the rule. The agent settles matching work itself.
Add one decision path. Keep the agent you built.
Add it once, then run: the next scheduled session starts from the approved playbook.
- 01
Import your playbook
The rules your agent follows today become playbook version one.
- 02
Connect Slack
Choose where questions and approvals land.
- 03
Add the credential
Reveal your agent key once and store it in Anthropic's credential vault.
- 04
Add PolicyLayer to the agent
Paste the generated MCP server and instructions into your Claude Managed Agent.
Proved on real scheduled runs.
Beside your agent. Not inside its execution path.
Does it replace my agent's existing tools?
No. The agent keeps its model, tools, sandbox and schedule. PolicyLayer supplies company answers and rules.
Does it write to customer systems?
No. PolicyLayer returns words and rules only. Your agent remains responsible for every action.
What if PolicyLayer is unavailable?
The agent falls back to its last signed playbook and gains no new authority.