detect_drift

Active

declared in 0.8.0

DRIFT DETECTION — audit a batch of AI-stated facts against live ground-truth in one call. Pass `claims` (a list of statements an LLM produced) or `text` (a paragraph that's split into claims); each is fact-checked and graded — drifted / confirmed / unverifiable, with a severity — plus a summary (drifted_count, overall). Use it to self-audit an answer before sending it. Args: claims: list of statements to check. text: alternatively, a paragraph that gets split into claims. Every value is returned in an Ed25519-signed, provenance-stamped envelope (source and observation time) you can verify offline against /.well-known/keys, no account required.

Parameters schema

{
  "type": "object",
  "title": "detect_driftArguments",
  "properties": {
    "text": {
      "type": "string",
      "title": "Text",
      "default": ""
    },
    "claims": {
      "type": "array",
      "items": {},
      "title": "Claims",
      "default": null
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.50.

Parent server

ai.dynamicfeed/dynamic-feed

1/7 registries

View full server →