Agent Monitor rules

Create rules to detect and block dangerous agent actions. Access rules at Agent Monitor Rules.

Built-in detection

Category	What it detects
Secrets	API keys, access tokens, credentials being sent to models
PII	Personally identifiable information in agent interactions
Prompt injection	Potential injection attempts in prompts
Tool permissioning	Unauthorized tool access attempts

Custom rules

Create organization-specific rules under the Organization Rules section.

Tool arguments rules

Match tool calls with specific argument patterns:

1. Click + New tool arguments rule
2. Set the tool pattern (e.g., Bash, Read|read)
3. Define argument conditions (e.g., command: kubectl.*secret)
4. Choose an action

Pattern rules

Match message content using regex:

1. Click + New regex rule
2. Define the pattern to match
3. Choose an action

Actions

Action	Effect
None (flag only)	Logs the action without blocking. Review at Live Activity.
Change response	Modifies the tool call to prevent execution
Slack notification	Sends an alert to a Slack channel

Manage rules

Edit or delete rules using the settings icon next to each rule.