Feith is FedRAMP Moderate Authorized · High In Process Read the release
Feith
AI in Feith · Redaction

Redaction the AI suggests, and a reviewer signs off.

AI Redaction reads each document and proposes masks for FOIA exemptions, CUI, PII, and any category your legal team configures, each with the exemption code and the reasoning behind it. Nothing is applied until a reviewer accepts, edits, or rejects it.

0 Redactions applied on their ownEvery mask waits for a reviewer to accept, edit, or reject
9 FOIA exemptions, (b)(1)–(b)(9)Plus CUI, PII, and any category your legal team configures
1 Reason on every suggestionThe exemption code and the reasoning, attached to each mask
Years In FOIA productionAI extends Feith Find-and-Redact, proven on FOIA work for years
What it does

Every redaction is the reviewer's call.

AI Redaction is built on top of Feith's Find-and-Redact, in production for FOIA work for years. The AI layer extends it: every proposed mask arrives with its exemption code and the reasoning behind it, and nothing is applied until a human reviewer signs off.

  • Suggestions only, never automatic application. The reviewer is the deciding party on every redaction.
  • Exemption definitions are editable by your legal team. The (b)(4) that applies at one agency isn't the same as at another.
  • Exemptions can be switched off. If your agency doesn't use (b)(1), it never appears in the workflow.
  • Built on Feith's Find-and-Redact, in FOIA production for years. The AI suggestions extend a proven capability.
  • Works beyond FOIA. The same engine handles CUI screening, PII detection, and any sensitive-content review you configure.
High-confidence detections can route straight to review, but the reviewer's decision, accept, edit, or reject, is what releases the record.
Worked example
How it works

Detected, reasoned, and held for review: nothing released on its own.

AI Redaction reads each document and consults your agency's own exemption set (editable, and switchable per exemption) to propose masks. Every suggestion waits for a reviewer; their decision is what releases the record.

Why it's different

The reviewer stays in charge

Nothing is masked automatically. The reviewer's accept, edit, or reject is the decision that releases the record.

Reasoned, not opaque

Every suggested mask carries its exemption code and the reasoning behind it, ready to defend on appeal.

Tuned to your agency

Exemption definitions are editable and individually switchable, so the workflow matches how your office reads the statute.

In practice

One engine, many review types.

FOIA is where most agencies start, but the same suggest-then-approve flow handles every kind of sensitive-content review.

FOIA exemptions

(b)(1)–(b)(9), including (b)(6) personal privacy and (b)(7)(C)

Accept, edit, or reject each suggested mask.

CUI screening

Controlled-unclassified categories, at the marking level

The same suggest-then-approve flow.

PII detection

Names, dates of birth, SSNs, badge and case identifiers

The reviewer confirms before release.

Custom categories

Any sensitive-content rule your legal team configures

Exemption definitions are editable per agency.

The rest of the set

Five more capabilities, one boundary.

Every capability shares the same permission model, the same audit trail, and your choice of large language model.

Get started

Release faster, with the reviewer still in charge.

Bring a sample FOIA case or a sensitive document set. We'll run AI Redaction live and show the exemption reasoning behind every suggested mask, and the reviewer's accept, edit, or reject on each.

Request a walkthrough