Agentic AI › Operate
Tool Calls
Every call an agent made and what let it through. This column — grant, approval or guardrail — is what turns this table from a log into evidence.
Where to find it
- Module: Agentic AI
- Group: Running
- Section: Operate
- Screen: Tool Calls
Address in the console: /agentic/tool-calls
Read-only list · 11 columns
This list is read-only: its records are written by the work that produces them. A correction, where one is possible at all, is made where the record was created.
What the list shows
These are the columns of the list, in the order they are drawn. Any of them can be sorted on, filtered on, hidden, or exported.
| Column | Kind | Field name |
|---|---|---|
| When | Date and time | called_at |
| Run | Code | run_no |
| Agent | Text | agent_name |
| Tool | Text | tool_name |
| Origin | Status | tool_kind |
| Status | Status | status |
| Allowed by | Status | authorized_by |
| Refused because | Text | denied_reason |
| Changed data | Yes or no | is_write |
| ms | Number | duration_ms |
| Result | Text | result_summary |
The rules that apply here
Everything on this screen obeys the platform rules rather than rules of its own. The ones worth knowing before you use it:
- Narrowing a list — search, conditions, sort, totals, export and saved views.
- What may be changed — the five grounds a record may not be edited on.
- Companies and business units — what the switcher above this list is doing to it.