Legal document review · Production

The 36 Group saves four weeks and £50,000 in trial preparation using Luminance AI

The problem

The 36 Group faced a tight court deadline requiring review of over 10,000 documents spanning decades of evidence, while their existing CCDCS system could not support real-time collaboration or efficient search, and the 20-person team had to work remotely during COVID-19.

First attempt

The existing CCDCS platform could not support real-time collaboration or efficient search, and manual keyword searches through police files with cryptic filenames meant critical information was often missed.

Workflow diagram · grounded in source
1
Document upload to platform
Trigger
The team uploaded the full dataset in minutes and gained immediate access via a secure, cloud-based platform.
source quote
“The team uploaded the full dataset in minutes and gained immediate access to the documents via a secure, cloud-based platform”
2
AI document analysis
Ai action
Luminance's AI rapidly analyzed and understood the document set, surfacing key information via intuitive 3D visualizations.
source quote
“Luminance's AI rapidly analyzed and understood the document set, surfacing key information via intuitive 3D visualizations. The legal team could instantly spot patterns, trends, or anomalies in the evidence”
3
Conceptual search across documents
Ai action
Luminance enabled conceptual search so a query for 'black shoes' surfaced all references across testimonies, and searching for 'mother' also returned conceptually similar terms like 'mum'.
source quote
“A search for 'black shoes' (a key piece of physical evidence) surfaced all references, allowing the team to confirm continuity across multiple testimonies. Searching for "mother" also returned conceptually similar terms like "mum"”
4
Adaptive review pattern learning
Ai action
Luminance's AI adapted to lawyers' review patterns, surfacing related material without requiring manual tagging or metadata.
source quote
“Luminance's AI adapted to their review patterns – surfacing related material without requiring manual tagging or metadata”
5
Cross-examination bundle compilation
Output
Cross-examination bundles were compiled in minutes because Luminance had already surfaced the right material.
source quote
“When it came time to compile cross-examination bundles, Luminance had already surfaced the right material – reducing what is usually a time-consuming task to just minutes”
Reported outcome

The defense team saved four working weeks and £50,000 during the review and disclosure phase, and cross-examination bundles were compiled in minutes instead of a time-consuming manual task.

Reported metrics
Working weeks savedfour working weeks
Cost saved in review and disclosure£50,000
Documents reviewed10,000+
Cross-examination bundle compilation timejust minutes
Reported stack
LuminanceCCDCS
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://www.luminance.com/customers/the-36-group/
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

The defense team saved four working weeks and £50,000 during the review and disclosure phase, and cross-examination bundles were compiled in minutes instead of a time-consuming manual task.

What tools did this team use?

Luminance, CCDCS.

What results were reported?

Working weeks saved: four working weeks; Cost saved in review and disclosure: £50,000; Documents reviewed: 10,000+; Cross-examination bundle compilation time: just minutes (source-reported, not independently verified).

What failed first in this deployment?

The existing CCDCS platform could not support real-time collaboration or efficient search, and manual keyword searches through police files with cryptic filenames meant critical information was often missed.

How is this legal document review AI workflow structured?

Document upload to platform → AI document analysis → Conceptual search across documents → Adaptive review pattern learning → Cross-examination bundle compilation.

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.