Skip to main content

Smartbox.ai Gen 2 is in beta. General availability January 2027. Join the beta

Smartbox.ai

01 · Control your data

Know what you hold, and what’s in it.

Collect it properly, route it to the right case, and understand it before anyone reads a page — whatever the format, however long the file.

Join the Gen 2 beta
Document thumbnails across a case, with AI analysis progressing through the collection.

Collect

Forensic collection, from where the data lives.

Collect from a wide set of sources with forensic integrity. Each item’s source, custodian and fingerprint are recorded as it arrives, so the chain of custody starts at collection, not at review.

  • Microsoft 365
  • Google Workspace
  • SharePoint
  • OneDrive
  • Google Drive
  • Box
  • Dropbox
  • Clinical systems
  • Dictation systems
  • Forensic images

Route

Every email in the right case. Every case with its own inbox.

Requests and material that arrive by email are routed to the right case, and the case’s workflow starts. Every communication about a case is recorded with it, not lost in someone’s mailbox.

How workflows work
  1. Inbound

    Your request mailbox

  2. Routing

    Matched to a case or a new one

  3. Case inbox

    Workflow starts

Understand

The case, as a map.

Unsupervised machine learning groups every document into themes and topics, so you can scope, prioritise and cull before review begins.

Explore the topic map
The topic map inside a subject access case, with Workbench, Topics, Cull, Problem files and Bin views, and a topic timeline beneath.

See your own data on the map.

Every format

Video, audio, spreadsheets and the longest files.

Nothing goes out to a specialist tool, and nothing gets split to fit.

Body-worn video with faces covered and separate sound and picture lanes.

Video and audio

Transcribe and redact video, body-worn video and CCTV. Redact sound and picture separately, and follow a moving subject.

Better spreadsheet support

Workbooks reviewed and redacted as reliably as documents.

OCR for embedded images

Text inside images embedded in documents and emails is read, searched and redacted like any other text.

Unlimited pages per document

No limit on pages, however long the file. A bundle stays one document.

Document comparison

Put two documents side by side and see every difference, so versions are reviewed once.

File types: documents (PDF, Word, Excel, PowerPoint, email — .msg, .eml), images (JPEG, PNG, TIFF, HEIC), audio (MP3, WAV, M4A, and the audio track of video files), video (MP4, MOV), forensic extracts (.pst, .ost, EnCase, forensic image formats), scans and handwritten notes. Collection and integrations

Beta open now · General availability January 2027

Take control of your next case.

Join the Gen 2 beta, or see it working on your kind of material in a 60-minute demo.

We use cookies to measure how the site is used, and — if you agree — to measure our advertising. You can accept one without the other, and declining is one click. See our cookie policy.