For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
- Three engines, chosen with
pii_engine: kev (the default) runs the Kev classifier model on Captain’s infrastructure. jev runs TypeSafe’s hosted Jev model, slightly more accurate with best-effort availability. presidio is the legacy pattern engine for the built-in categories only. See Engines.
kev by default, with no fallback: {"mask_pii": true} masks with kev. If kev cannot mask a file, that file fails to index and the rest of the job continues. Nothing is published partially masked.- Ordered fallbacks for
jev: pii_fallback takes an object, {"engines": [...], "retry_budget_seconds": 60}. List any of jev-openrouter, jev-ai-gateway and kev in the order to try them. Custom fields and instructions stay applied on every fallback, and presidio is never a fallback. See Fallback.
- Per-file engine report: each file in Get PII Report carries
requested_engine, used_engines, fallback_used, fallback_reason, coverage, model and image_redaction.
- Audio and video are skipped when masking: with
mask_pii: true, audio and video files are not indexed and the job lists them as skipped.
