Features

One private index. Every file type.

FileFerret turns a firm’s scattered documents, scans, recordings, and video into a single searchable archive — with AI that explains what it finds and shows its work.

Real queries tax documents from 2023ai_sentiment:negative**invoice*recorded calls about the Acme matterai_topic_tag:tax**.pdf signed by the client

fileferret.local · A plain-language search answered

A plain-language search answered. Asking for “2023 tax return” in plain language, and the ranked, scored documents that come back — each with the passage that matched. The live demo, not a mockup. Narrated — captions available.

fileferret.local · Results into a matter, in one action

Results into a matter, in one action. Picking the documents that matter out of a result set and adding them to an engagement in a single action. The live demo, not a mockup. Narrated — captions available.

fileferret.local · The workspace you return to

The workspace you return to. Current matters and every past search stay in view down the side, so picking up yesterday’s work does not mean remembering it. The live demo, not a mockup. Narrated — captions available.

fileferret.local · A matter, assembled

A matter, assembled. The files an engagement depends on, the notes staff left on them, and an export of the whole thing whenever it is wanted. The live demo, not a mockup. Narrated — captions available.

fileferret.local · Ask a question of your own files

Ask a question of your own files. A question put to chosen collections, answered only from the firm’s own documents. The live demo, not a mockup. Narrated — captions available.

fileferret.local · What client information you hold, and where

What client information you hold, and where. Every indexed collection checked for personal information, privileged content and CUI markings — located down to the file, with the values themselves masked. The live demo, not a mockup. Narrated — captions available.

Semantic search

Find by meaning, not just keywords.

Ask in plain language and get back the documents that actually match the idea — ranked by similarity, across every file you have indexed, with keyword and wildcard filters when you need precision.

Meaning-based ranking with a tunable similarity threshold
Combine with wildcard filters like *.pdf, *invoice*, or ai_topic_tag:tax*
One ranked list across documents, images, audio, and video — group by source collection when you want it
Save searches you run often and re-run them in one click

Ask & analyze, with citations

Answers you can trace back to the source.

Pose a question over a matter and get a written answer assembled from your own files — every claim linked to the exact document and passage it came from, so nothing is taken on faith.

Plain-language questions across a whole client collection
Every answer cites the source file and the passage used
Answers stream back as they are generated
An incognito mode that leaves no history when you need it

Indexes everything

Documents, images, audio, and video — searchable.

FileFerret reads far more than text. Scanned pages are run through OCR, recordings and video are transcribed, and images are described — so a phrase buried in a voicemail or a scanned exhibit is just as findable as one in a Word file.

OCR for scanned documents and image-only PDFs
Transcription for audio and video, searchable by spoken word
Object and text detection inside images
Reads from the file shares and storage you already use

Investigation projects

Gather, tag, and export your findings.

Turn a search into a case file. Group results into named projects, flag the files that matter with an interest score and a note, and export the tagged set as a clean spreadsheet for review or discovery.

Organize findings into named investigation projects
Tag files with a 1–5 interest score and free-text notes
Bulk-tag and filter large result sets quickly
Export tagged evidence to CSV with your filters applied

A wall between clients

Per-client collections, access you control.

Each client’s material lives in its own collection. Administrators decide exactly which staff can reach which client, so a search never crosses a boundary it should not.

Separate, per-client document collections
Per-user access control over which collections are searchable
Roles for everyday users and administrators
Clear separation that mirrors your ethical walls

Accountable by default

A complete record of who did what.

Every login, search, file open, and admin action is written to an activity log you can review — the kind of accountability your clients, insurers, and regulators expect of a firm holding their most sensitive material.

Full activity log: logins, searches, file access, admin changes
Review and disable accounts from one place
Scheduled re-indexing keeps results current automatically
Runs on a private appliance we ship, install, and support — on your premises

See FileFerret on your own files.

We’ll scope your firm’s needs, ship and install a private FileFerret appliance, train your team, and support you for years to come. No client data leaves your office — ever.

Request a demo Get in touch