Human-in-the-loop PII redaction
Arbiter is the human-review surface for redaction pipelines. Reviewers see every detected PII span in context, accept or override the automated decision, and apply structured exemption codes that flow back into your audit trail. Built for AI training-data preparation, healthcare de-identification, legal e-discovery, and any workload where automated detection has to be the last 95 percent — not the last word.
Every detected PII span appears in context with an accept / override / exempt workflow. Automated detection covers most of the volume; Arbiter handles the cases that need human judgment without forcing reviewers to read every document end to end.
Find documents by content, by detected entity type, by reviewer status, or by any combination. Filter to needs review, exempted last week, or reviewed by alice@ with the same query interface.
When a detected entity shouldn't be redacted — a medical condition that's also a famous person's name, public-record content, an organization name that's not actually PII — apply an exemption code with a reason. The codes flow into the audit trail for downstream compliance review.
Import documents from OpenSearch, Elasticsearch, any RDBMS, or local files. The same review workflow regardless of where the source data lives.
Detection comes from the same Philter API that powers your automated pipeline. Same policies, same entity types, same confidence scores — Arbiter adds the human-decision layer on top of an automated foundation.
Per-reviewer throughput, per-entity-type exemption rates, per-document review status, time-to-completion histograms. The artifact your compliance team actually wants to see when they ask how the human-review layer is performing.
Three ways to get going — deploy the open source yourself, spin it up from a cloud marketplace, or work with our team directly. Pick the path that fits.