Home

/

Keep PII Out of Your LLM

/

Azure AI Language PII, in detail

Azure AI Language PII, in detail

Appendix B
Appendix
3
min read

Azure AI Language PII, in detail

Feature types: Text PII (synchronous, string payloads), Conversation PII (turn-based transcripts, asynchronous), Document PII (native .pdf, .docx, .txt, asynchronous, preserves structure and emits JSON metadata).

SDKs: C#, Java, JavaScript, Python, plus REST.

Redaction: redactionPolicies parameter from API version 2025-11-15-preview, multiple policies per request.

Output: entity categories with confidence scores. No customisation of the model on your data.

Guidance: use GA API versions in production; do not mix payload examples across versions.

Data handling (verified 14 September 2026): no storage or processing outside your deployment region; all content encrypted at rest; up to 48 hours temporary storage for catastrophic-failure debugging, governed by LoggingOptOut — which defaults to true on the PII and health endpoints, so it does not apply to PII calls.

Choosing a safeguard (Chapter 8, condensed)

#SafeguardReversiblePreserves coreferenceTypical use
1RemoveNon/aDefault; the field was not needed
2RedactNoNoOne-shot classification
3MaskNoNoHuman-facing confirmation
4GeneraliseNoNoAnalytics, banded reasoning
5PseudonymiseYesYesConversational work, the default
6SurrogateYesYesWhere natural text matters
7Format-preserving encryptYesYesDownstream format validation
8SynthesiseNon/aTest and demo data

Effort versus reduction

ControlEffortReduces
Field projectionHoursEvery entity in the fields you drop, structurally
Turn off prompt loggingHoursThe largest personal data store most teams have
Deterministic layerDaysHighest-consequence identifiers, near-certainty
Log sink redactionHoursIncidental telemetry exposure
Output host allowlistHoursRendered exfiltration
Provider zero data retentionA procurement conversationProvider-side persistence
Retrieval permission filterHoursCross-tenant retrieval
De-identify at ingestionDaysBulk exposure in the vector index
Model-based detectorWeeks, plus operationsAbout half of what remains
Round trip with vaultWeeksReal values at the provider

The ordering is the argument of the book. The most expensive row is the least effective, and it should be sized against what is left after the cheap rows, not against the original problem.

Ageing notes

Fastest to age: provider retention terms (changed at least twice during 2026), maintenance status, API preview version names, package download counts.

Slower: accuracy figures, latency characteristics, the shape of the trade-offs.

Effectively stable: checksum algorithms, the ladder of safeguards, the five doors, the fact that in-distribution scores do not predict out-of-distribution performance.

Re-verify anything in the first group before you rely on it, and print the date you checked.

the-leak-you-cant-see
blast-radius
what-counts-as-pii
the-five-doors
the-accuracy-reckoning
the-hybrid-that-does-not-work
deterministic-detection
npi-in-c
the-three-way-choice
calling-the-analyzer-from-c
measuring-your-own-demo-gap
choosing-the-operating-point
the-ladder-of-safeguards
pseudonymisation
the-round-trip
restoring-safely
when-masking-breaks-the-task
plausibility-hazard
the-architecture-that-holds
the-reference-architecture
dont-send-it-at-all
structure-beats-prose
the-gateway
failure-is-a-policy-decision
the-sidecar-you-can-trust
egress-deny-it-at-the-network
rag-and-agents
de-identify-before-you-embed
dual-model-separation
the-boring-controls
evidence-and-the-first-thirty-days
week-two-the-chokepoint-and-the-fast-layer
entity-catalogue-and-c-validators
mbi-positional-rules
tooling-at-a-glance
azure-ai-language-pii-in-detail
container-trust-checklist
sources
azure-ai-language
provider-retention

Download the full PDF for free?

Free download — no account required

Get the PDF
Get the PDF
Related Chapters
Free Download
Get the full PDF
All pages, including all code examples, diagrams, and the appendix reference card.
No spam. Unsubscribe at any time.
Your email won't be shared.
Oops! There's a problem with your request. We're working on fixing it. Please try again later.