Workflow Run Record
Each accepted FactVerse AI Agent workflow run should leave a clear record. The record helps operators review decisions, engineers improve workflows, and customers trace how an answer or action was produced.
Record structure
| Section | Required content |
|---|---|
| Request | User request, workflow type, boundary, time window, and expected output. |
| Access | Endpoint, visible tool set, scopes used, and client identity. |
| Evidence | Source systems, records, timestamps, documents, scene versions, and tool outputs used. |
| Analysis | Facts, assumptions, limitations, missing data, and generated recommendation. |
| Review | Reviewer, decision, required changes, and approval state. |
| Action | Draft or accepted work order, inspection task, scenario package, or validation record. |
| Feedback | Field result, correction, false positive, repaired data, or follow-up note. |
Template
Workflow:
Boundary:
Time window:
Requested by:
Review owner:
Endpoint and scopes:
Runtime-visible tools:
Source evidence:
- Source:
Record:
Timestamp:
Notes:
Generated output:
- Confirmed facts:
- Assumptions:
- Missing data:
- Recommendation:
Review decision:
- Accepted / revised / rejected:
- Reviewer:
- Reason:
- Follow-up:
Final record:
- Work order / inspection / scenario / validation ID:
- Feedback captured:
- Next review date:
Workflow-specific fields
| Workflow | Add these fields |
|---|---|
| Facility operations | Site, area, asset ID, alarm IDs, inspection IDs, work-order IDs, affected nearby equipment, and operator notes. |
| Predictive maintenance | Equipment ID, component, operating mode, signal window, health or anomaly output, maintenance history, and engineer feedback. |
| Physical AI | Scene version, asset versions, simulation backend, SimReady issues, assumptions, validation notes, and reuse target. |
Review states
| State | Meaning |
|---|---|
| Draft | Agent output is available but has not been reviewed. |
| Needs data correction | Output is blocked by missing, stale, or mismatched source data. |
| Needs engineering review | Output depends on assumptions, compute results, or domain interpretation. |
| Accepted with limits | Reviewer accepts the output for a defined boundary and records limitations. |
| Accepted for action | Reviewer approves the draft action or handoff record. |
| Rejected | Reviewer rejects the output and records the reason. |
Evidence rules
- Keep source timestamps visible.
- Keep generated recommendations separate from confirmed facts.
- Record the endpoint and scopes used by the client.
- Keep draft actions separate from approved actions.
- Capture reviewer corrections so future runs can improve.
- Do not reuse a Physical AI result without scene version, asset version, and validation notes.
Example record summary
| Field | Example |
|---|---|
| Workflow | Predictive maintenance review |
| Boundary | Site A, compressed air system, compressor C-03, last 14 days |
| Evidence | Signal trend, anomaly output, inspection record, work-order history, and maintenance note |
| Output | Bearing temperature trend increased, vibration signal has two missing intervals, inspection recommended before planned shutdown |
| Review | Maintenance engineer accepted inspection recommendation and marked missing vibration intervals for data correction |
| Feedback | Inspection found lubrication issue; work order closed with parts and field notes attached |