Agentic AI › Running
Operate
What is running, what is waiting on somebody, and what it produced.
In Agentic AI → Running · 6 screens
WorkspaceMonitorWhat the agents are doing, what has stopped for a decision, and the trace of any run read as the narrative it is rather than as four separate tables.OpenViewAgent RunsEvery run, with what it did, what it cost and what stopped it. A run is not a record somebody edits — it is the account of what happened.OpenViewAgent ApprovalsWhat is waiting on a person. A run stops here and survives a restart while it waits; an approval nobody answers expires rather than hanging.OpenViewDelegated TasksWork an agent handed to a licensed Claude worker because it was too big for one model turn. Claim one to get a worker token and the connection for Claude Code, the Agent SDK or a managed agent; the worker reaches this company only through the agent's own tool grants, guardrails and approvals, and every call is recorded.OpenViewWhat Agents ProducedEvery record created, message sent, proposal made and finding recorded. Accepting a proposal creates the record THROUGH THE API with your name on it, not the agent — which is where most of the value of a suggest-level agent actually lands.OpenViewTool CallsEvery 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.Open
Columns, fields and actions
| Screen | Kind | What it is | Columns | Fields | Actions |
|---|---|---|---|---|---|
| Monitor | Workspace | What the agents are doing, what has stopped for a decision, and the trace of any run read as the narrative it is rather than as four separate tables. | 0 | 0 | 0 |
| Agent Runs | Read-only list | Every run, with what it did, what it cost and what stopped it. A run is not a record somebody edits — it is the account of what happened. | 22 | 0 | 6 |
| Agent Approvals | Read-only list | What is waiting on a person. A run stops here and survives a restart while it waits; an approval nobody answers expires rather than hanging. | 15 | 0 | 2 |
| Delegated Tasks | Read-only list | Work an agent handed to a licensed Claude worker because it was too big for one model turn. Claim one to get a worker token and the connection for Claude Code, the Agent SDK or a managed agent; the worker reaches this company only through the agent's own tool grants, guardrails and approvals, and every call is recorded. | 13 | 0 | 8 |
| What Agents Produced | Read-only list | Every record created, message sent, proposal made and finding recorded. Accepting a proposal creates the record THROUGH THE API with your name on it, not the agent — which is where most of the value of a suggest-level agent actually lands. | 12 | 0 | 3 |
| Tool Calls | Read-only list | 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. | 11 | 0 | 0 |