Guide
Technology Assisted Review For UK Lawyers
17 pages · 22 min read
Technology-Assisted Review (TAR) amplifies human judgement by ranking documents.
- Search terms and technology assisted review
§ Guide
Technology Assisted Review For UK Lawyers
This guide explains how Technology-Assisted Review works, its two generations, and how to defend the machine's judgement in UK legal contexts.
Ref · E-D · 2026 · §LIBClass · ConfidentialJuris · England & WalesStatus · Active
Guide · 17 pages · 22 min read · Published 2026-08-30
Managing massive document volumes in electronic disclosure requires UK legal practitioners to accurately teach machine models what relevant evidence looks like while maintaining defensibility before the English courts. Written for solicitors, litigation teams, and e-Discovery specialists, this practical guidance details how machine-assisted document review operates across predictive coding and Continuous Active Learning frameworks. It examines the human training layer, seed selection, and reviewer consistency, alongside statistical validation metrics such as recall, precision, elusion, and the stopping decision. Beyond algorithmic mechanics, it explains protocol negotiation, Disclosure Review Document drafting, keyword integration, email threading, privilege management, and wider source architecture across text and non-text routes. Real-world worked examples illustrate common pitfalls including premature budget-driven stopping decisions and scope gaps. To assist in negotiations and court proceedings, it provides structured interrogatories for clients, opponents, and service providers, a red flag checklist, and guidance on when to instruct digital forensic specialists to produce CPR Part 35 expert reports supported by full chain-of-custody documentation.
Share
Read this guide on your phone, open the PDF reader with the full text, browse guides by topic or go back to the full PDF library.
§ Credit and source
Published by Computer Forensics Lab on 2026-08-30. Original material of the practice, free to read, cite and download. The authority behind this subject is Practice Direction 57AD, Appendix 2, use of technology in disclosure, which you should read alongside this guide. See every guide's author and source.
§ Read Technology Assisted Review For UK Lawyers
Download the PDFPrefer a PDF that matches this page exactly? Download the current text as a PDF, generated from the current wording of the guide, including any later corrections.
Page 1
TECHNOLOGY - ASSISTED REVIEW · A GUIDE FOR UK LAWYERS Technology-Assisted Review for UK Lawyers Predictive Coding, Continuous Active Learning and Defending the Machine's Judgement COMPUTER FORENSICS LAB
§ ABOUT THE AUTHOR PREPARED BY COMPUTER FORENSICS LAB E-DISCOVERY TEAM VALIDATION STATISTICS CPR PART 35 EXPERT REPORT S FULL CHAIN-OF-CUSTODY DOCUMENTATION
§ CONTENTS In this guide 01 Executive summary 02 The problem in plain English: teaching a machine what relevant looks like 03 How TAR works: models, training and the two generations 04 The human layer: seeds, subject-matter reviewers and consistency 05 Validation: recall, precision and the stopping decision 06 TAR in the protocol: disclosure, negotiation and the courts 07 TAR in the tool chain: keywords, threading and privilege 08 Source architecture: where else the evidence lives 09 Worked examples 10 Common mistakes and technical limitations 11 Questions to ask · Suggested wording 12 Checklist and red flags · When to involve a digital forensic expert 13 Frequently asked questions 14 Glossary · References · Disclaimer · How a specialist laboratory can assist
§ 01 · ORIENTATION Executive summary THE HEADLINE POINT: TARISHUMANJUDGEMENTAMPLIFIEDBYRANKING: ITS DEFENSIBILITYISTHETRAININGRECORDPLUSTHEVALIDATIONSTATISTICS, ANDBOTH AREBUILT, NOTASSUMED
§ 02 · FIRST PRINCIPLES The problem in plain English: teaching a machine what relevant looks like
§ 03 · THEMACHINERY How TAR works: models, training and the two generations
Page 2
§ 04 · THETEACHERS The human layer: seeds, subject-matter reviewers and consistency
§ 05 · THELICENCETOSTOP Validation: recall, precision and the stopping decision
§ 06 · THE PAPER WORK AND THE COURT S TAR in the protocol: disclosure, negotiation and the courts
§ 07 · THETOOLCHAINSEAT TAR in the tool chain: keywords, threading and privilege
§ 08 · THEWIDERMAP Source architecture: where else the evidence lives QUESTION QUALIT Y TRAINING VALIDATION PROTOCOL & PLATFORM N ON-TEXT RECORD FILE CORRESPONDENCE LOGS ROUTES TEXT- LAYER
§ 09 · IN THE WILD Worked examples EXAMPLE1 · THE1. 8MILLIONDOCUMENTSREVIEWEDBY140, EXAMPLE2 · THESTOPPINGDECISIONTHATWASABUDGETINCOSTUME EXAMPLE3 · THEELUSIONFINDTHATWASASCOPEHOLE
Page 3
§ 10 · WHEREITGOESWRONG Common mistakes and technical limitations Common mistakes Technical limitations
§ 11 · INTERROGATORIES & DRAFTING AIDS Questions to ask · Suggested wording Ask your client Ask your opponent Ask your e Discovery / forensic provider SUGGESTED WORDING · TA R PA R AG RAPHFORTHEDRD / PROTOCOL
§ 12 · QUICK CONTROL Checklist and red flags · When to involve a digital forensic expert The TAR checklist Red flags When to involve a digital forensic expert
§ 13 · COMMON QUESTIONS Frequently asked questions Is predictive coding actually approved by the English courts? How big does a matter need to be before TAR makes sense? Can the model miss the smoking gun? Do we have to tell the other side we are using TAR? What recall target should we agree? Is TAR the same as using generative AI for review?
§ 14 · REFERENCE Glossary CAL Sources and authoritative references DISCLAIMER
§ HOW A SPECIALIST LABORATORY CAN ASSIST Working with Computer Forensics Lab Speak to a forensic examiner, not a salesperson. INSTRUCTTHELAB NEWENQUIRIESEMAILE - DISCOVERY
§ Related documents
Guide
How To Design Defensible Keyword Searches
17 pages · 21 min read
Learn to design effective and defensible keyword searches for e-discovery.
- Search terms and technology assisted review
- Chain of custody and defensibility
Guide
Why Lawyers Should Test Search Terms Before Agreeing Them
17 pages · 20 min read
Lawyers must test search terms to avoid signing a list they have not run, transforming search negotiation from adjectives into arithmetic.
- Search terms and technology assisted review
Instruct the practice
Bring us in early.
Defensibility is built, not retrofitted.
Whether you are responding to a regulator, preparing for disclosure, or scoping an internal investigation, start the chain of custody with a short, confidential conversation.