Agents
The Agent activity & governance page gives you visibility into what your organization's AI agent team is doing at the policy boundary. It surfaces two feeds — policy decisions and agent actions — scoped to your organization.
This view is references and metadata only by design: it shows content references and metadata (such as a content reference or a target reference), and never stores or displays raw agent or prompt content.
Accessing Agents
Open Agents from the dashboard sidebar. Viewing agent activity requires the Audit viewer permission. The Manage agent teams button in the page header opens Agent Teams.
The Two Feeds
The page has two tabs:
Policy decisions
Each row is a verdict recorded when an agent's traffic was evaluated at the LLM/policy boundary. Every decision shows:
| Column | Description |
|---|---|
| Time | When the decision was recorded |
| Agent | The agent slug, its mode, and (if present) the trigger |
| Policy | The policy type or policy names that applied |
| Verdict | Allow, Would block, Block, or Error |
| Reference | A content reference (no raw content) |
| Latency | Evaluation latency in milliseconds, when available |
Verdicts:
- Allow — the traffic passed.
- Would block — the policy matched in observe (shadow) mode; the action was recorded but not blocked.
- Block — the policy matched in enforce mode; the action was blocked.
- Error — the check ran but could not reach a verdict (for example, a proxy error, network error, or timeout). These are recorded for audit completeness, not dropped.
A posture summary above the feed shows the count of each verdict type across your organization's recent decisions.
Agent actions
Each row is a single tool execution by an agent:
| Column | Description |
|---|---|
| Time | When the action occurred |
| Agent | The agent slug and its identity |
| Action | The action (tool) type |
| Target | A bounded target reference (no raw args) |
| Outcome | Success, Error, or Blocked |
Filtering and Search
Both feeds support:
- Search across agent, policy/action, and reference fields.
- Team filter — scope both feeds to a single agent team (shown once your organization has at least one team).
- Agent filter — scope to a single agent slug.
- Verdict filter (decisions) / Outcome filter (actions). Outcome values are success, error, and blocked.
- Sortable columns — click a sortable header to sort by that column.
Click any row to open a detail drawer with the full (references-only) record. Each feed is paginated at 25 rows per page over a recent window, and you can link straight to a feed with ?tab=decisions or ?tab=actions.
Related Topics
- Agent Teams - Create teams and issue credentials
- Activity & Audit Logs - Organization audit history
- Policy Overview - Configure the policies agents are evaluated against