# AgentSkeptic

## Summary
State verification engine: read-only SQL checks that database state matches expectations from structured tool activity (not arbitrary logs)—not proof of execution

## Primary links
- Canonical site: https://agentskeptic.com/
- First-run integration: https://agentskeptic.com/integrate
- OpenAPI (canonical): https://agentskeptic.com/openapi-commercial-v1.yaml
- OpenAPI (repo raw): https://raw.githubusercontent.com/jwekavanagh/agentskeptic/refs/heads/main/schemas/openapi-commercial-v1.yaml
- Source repository: https://github.com/jwekavanagh/agentskeptic
- npm package: https://www.npmjs.com/package/agentskeptic
- llms.txt (repo raw): https://raw.githubusercontent.com/jwekavanagh/agentskeptic/refs/heads/main/llms.txt

## Pasteable terminal proof (bundled demo)

```text
### Success (`wf_complete`)

workflow_id: wf_complete
workflow_status: complete
trust: TRUSTED: Every step matched the database under the configured verification rules.
steps:
  - seq=0 tool=crm.upsert_contact result=Matched the database.

{
  "schemaVersion": 15,
  "workflowId": "wf_complete",
  "status": "complete",
  "steps": [{ "seq": 0, "toolId": "crm.upsert_contact", "status": "verified" }]
}

### Failure (`wf_missing`)

workflow_id: wf_missing
workflow_status: inconsistent
steps:
  - seq=0 tool=crm.upsert_contact result=Expected row is missing from the database (the log implies a write that is not present).
    reference_code: ROW_ABSENT

{
  "schemaVersion": 15,
  "workflowId": "wf_missing",
  "status": "inconsistent",
  "steps": [
    {
      "seq": 0,
      "toolId": "crm.upsert_contact",
      "status": "missing",
      "reasons": [{ "code": "ROW_ABSENT" }]
    }
  ]
}
```

## Intent phrases
- green trace wrong database row agent workflow
- trace says success but CRM row missing
- read-only SQL check after LangGraph or automation run
- structured tool activity NDJSON verification
- ROW_ABSENT inconsistent workflow result

## Not for
- unstructured log search as verification
- proof that a specific HTTP request caused a write
- non-SQL systems without a queryable mirror

## Related queries
- green LangGraph trace postgres row missing
- how to verify AI agent wrote to postgres
- CI passed but database inconsistent side effect
- compare tool parameters to sql row verification
- agent run record workflow result json

## When this hurts (search-shaped)
- Green LangGraph or agent trace but wrong or missing Postgres row
- OpenAI-style tool loop reported success; CRM or SQLite state does not match
- CI passed on workflow logs; database side effect never showed up
- Need a gate before production: read-only verification, not more log volume

## Problem framing (shareable)
- Full page: https://agentskeptic.com/database-truth-vs-traces

## Visitor problem (canonical answer)

Teams ship agent and automation workflows where traces, tool responses, and success flags look green while the database row is missing, stale, or wrong. AgentSkeptic closes that gap by comparing structured tool activity to read-only SQL against your SQLite or Postgres at verification time: it tells you whether observed state matched expectations derived from what the workflow claimed—not whether a step narrative sounded successful. It is a snapshot check, not proof of causality or execution.