Skip to main content

Documentation Index

Fetch the complete documentation index at: https://laminar.sh/docs/llms.txt

Use this file to discover all available pages before exploring further.

Laminar is an open-source, OpenTelemetry-native observability platform for AI agents. PII redaction is a project-level switch that runs every span through PII redactor model hosted on Laminar’s infrastructure before storage, replacing names, emails, secrets, phone numbers, and other detected entities with [REDACTED_<LABEL>] placeholders. Once it’s on, raw user data never lands in your trace store, your search index, or anyone else’s eyeballs. Redaction runs at ingest, in line with the rest of trace processing. By the time a span is searchable, in the trace view, or queryable from SQL, it has already been redacted: the original text is never persisted.

​
Enabling it

Go to Project Settings → Security, flip Redact PII from spans on. The change applies to every new span ingested for that project. Existing traces are not rewritten retroactively.
Security tab with the Redact PII from spans toggle in the on position
The toggle is per-project, not per-workspace. A workspace can mix redacted and non-redacted projects (for example, a production project with redaction on and a staging project without).

​
What gets redacted

The redactor runs over the input and output fields of every span: LLM messages, tool-call arguments and results, function inputs and outputs. It detects and replaces:
  • Personal names
  • Email addresses
  • Phone numbers
  • Account numbers, card numbers, and similar identifiers
  • Other entities the model classifies as PII
Each detected entity is replaced with a labelled placeholder, e.g. [REDACTED_PRIVATE_EMAIL], [REDACTED_PRIVATE_PERSON], [REDACTED_ACCOUNT_NUMBER]. The structure of your span input/output (JSON shape, message role fields, tool-call IDs) is preserved: only the offending substrings are rewritten.

​
What is never redacted

Some fields are structurally meaningful and pass through untouched even with redaction enabled:
  • Object keys in JSON inputs and outputs. A key called email stays; the email value gets redacted.
  • Span attributes other than input and output: span name, type, status, duration, token counts, cost, model name.
  • Trace and span IDs, parent IDs, and the message-role / tool-call-id fields the model needs to follow conversation structure.
If you’ve passed a user identifier through setTraceUserId / set_trace_user_id (see User ID), that value is span metadata and is not affected by this toggle. Strip user IDs upstream if your compliance posture requires it.

​
What you’ll see in traces

Traces ingested with redaction on look the same in the transcript view: same structure, same nesting, same tool calls. The difference is in the content cells. A user message that was previously: 
"Hi, my name is Sarah Chen and my email is sarah.chen@example.com"
is stored and rendered as: 
"Hi, my name is [REDACTED_PRIVATE_PERSON] and my email is [REDACTED_PRIVATE_EMAIL]"
The same applies to LLM outputs, tool-call arguments, and tool-call results. Token counts and timing are unchanged. Full-text search hits the redacted text, so a search for the original email returns nothing. That is the point.
Redaction runs at ingest, so flipping the toggle does not retroactively redact existing traces. New traces from the moment the toggle flips are redacted; older traces stay as they were stored.

​
Availability

PII redaction is available on Pro and Enterprise plans on Laminar Cloud. Self-hosted deployments can enable the same toggle by running the redactor alongside the rest of the stack. See the Hosting Options page for setup.

​
Where to go next

Viewing traces

See how redacted spans render in transcript view.

Signals

Define outcome and failure detectors that work over redacted traces.

SQL editor

Query across redacted traces with SQL. Placeholder strings are searchable.

Self-hosting

Run Laminar in your own cluster, including the PII redactor service.