# De-identification

> The two PII detection engines behind Divinci de-identification — Microsoft Presidio and Stanford NER — and how they differ.

Two engines, one contract. Both are run by Divinci — neither needs a key of
your own.

| Engine | Vendor | Role | `hybrid` strategy |
| --- | --- | --- | --- |
| `presidio` | [Microsoft Presidio](https://microsoft.github.io/presidio/) | **Default.** The more accurate detector | Implements the real mix — pseudonymise some categories, redact others |
| `stanford` | [Stanford NER](https://nlp.stanford.edu/software/CRF-NER.html) | Fallback | Treats `hybrid` as plain `redact` |

If the configured engine fails at request time, the other is tried. The
consequence worth knowing before you rely on it: a release that fails over from
Presidio to Stanford **changes redaction style mid-incident** — safely, in the
more conservative direction, but the output looks different.

<Aside type="danger" title="De-identification fails CLOSED">
If neither engine can be reached, messages are rejected with a `503` rather than
passed through un-redacted. That is the correct trade for the feature — an
assistant that silently stops redacting is worse than one that stops answering —
but it means the engines are on the critical path of every message for a release
that enables it.
</Aside>

<Aside type="caution" title="Detectors are tuned for general prose, and your domain may not be">
Presidio's default entity set is aggressive, and in specialised corpora it
removes terms that are not identifiers at all — in a nutrition corpus, for
example, vitamin and compound names and some food terms match its patterns.
Always read redacted output from a sample of your own content before enabling it
on a live release; the damage is invisible in aggregate metrics.
</Aside>

<Aside type="tip" title="Removing a chunk is a weak remedy on its own">
If PII has already been ingested, deleting the offending chunks moves the
needle less than expected, because identifiers recur across a corpus. Treat
re-ingestion with de-identification on as the actual fix.
</Aside>

## See also

- [De-Identification (PII)](/server/de-identification/) — configuration, strategies, categories and failure behaviour in full.
- [Practice Better connector](/cli/connectors/practice-better/) — the connector that de-identifies before indexing.