Agentic AI › Reporting
Reporting
What the agents cost, what they produced, and how much of it was kept.
In Agentic AI → Reporting · 8 screens
| Screen | Kind | What it is | Columns | Fields | Actions |
|---|---|---|---|---|---|
| Reports & Analytics | Report | The report catalog for this module, and the models behind it — dimensions and key figures you can rearrange, filter, total and export. | 0 | 0 | 0 |
| Predictive & Prescriptive | Report | Where this module’s measures are heading, how much that projection is worth, and what to do about it while there is still time. | 0 | 0 | 0 |
| Was It Worth It | Report | What each agent produced, how much of it a person kept, and what it cost to find out. A proposal nobody accepted is the same cost and none of the value. | 0 | 0 | 0 |
| Spend by Agent | Report | Model spend by agent and by month, with the tokens behind it. | 0 | 0 | 0 |
| Autonomy Ladder | Report | Where each agent sits, how long it has been there, and whether its record supports moving it up. | 0 | 0 | 0 |
| Approval Latency | Report | How long agents wait for people, by approver and by kind. The number that decides whether an approve-level agent is usable at all. | 0 | 0 | 0 |
| Connection Reliability | Report | Which outside systems answer, how fast, and how often they do not. | 0 | 0 | 0 |
| Guardrail Pressure | Report | Which limits are actually biting. A guardrail that never fires is either well set or pointing at nothing, and this is how you tell. | 0 | 0 | 0 |