Two years on from its launch, Relativity's aiR for Review has shifted from a novelty to a tool that review teams are using on real matters. It is worth taking stock of where it works, where the cost-benefit makes sense, and where it still needs careful handling.
What aiR for Review actually does
aiR for Review uses a large language model, integrated into Relativity, to make relevance and issue-coding predictions against a defined set of review criteria. Unlike classic Active Learning, it does not require thousands of human-coded documents to begin producing useful output: a well-written set of instructions and a small validation sample is often enough to get a meaningful first pass. Each prediction comes with a rationale the reviewer can read.
Where it earns its place
Three use cases have become reasonably well established:
- Early case assessment. Running aiR against the corpus very early, on a draft of the relevance criteria, surfaces likely hot documents and gives the legal team something concrete to refine scope and strategy against.
- Issue tagging at scale. Multi-issue matters, where each document might touch several themes, are where the rationale-per-issue output is most valuable. Reviewers spend their time confirming or rejecting structured suggestions rather than starting from a blank tagging panel.
- QC and prioritisation. Even where humans do first-pass review, aiR is being used to flag documents whose human coding looks inconsistent with the surrounding pattern.
Where it still needs careful handling
It is not magic. A few practical points come up repeatedly:
- Instructions are the work. The quality of aiR's output is largely a function of how clearly relevance and issues are written. Vague criteria produce vague predictions, just as they do for human reviewers.
- Validation is non-negotiable. Defensibility still depends on measuring recall and precision against a human-coded sample, and being able to explain the methodology if challenged.
- Privilege remains sensitive. Most teams continue to apply traditional searches and human review for privilege, with aiR as an additional safety net rather than a replacement.
Wider context
aiR is not the only player. Reveal, DISCO and others have shipped comparable generative-AI features, and the EDRM has published practical guidance on validation in its EDRM model updates. The UK courts have not, to date, treated AI-assisted review as inherently more suspect than other technology-assisted review approaches, provided the methodology can be explained.
Bottom line
Generative-AI review tools earn their place where they let smaller review teams handle larger, more complex matters without sacrificing defensibility. They do not remove the need for a properly scoped collection, clear relevance criteria or human judgement on privilege and key documents - and matters where any of those are weak are not the matters to try them on first.
§ From the guide, latest version
CFL Benefits Of Early Case Assessment In EDiscoveryCOMPUTER FORENSICS LAB · E-DISCOVERY TEAM CFLELECTRONICEVIDENCESERIES · EARLY CASE ASSESSMENT Benefits of Early Case Assessment in e Discovery A Practical Guide to Understanding Evidence, Controlling Disclosure Costs and Developing Case Strategy Earlier Understand the evidence before the evidence controls the case. ALIGNEDPRACTICE · CFLAB. UK · E-DISCOVERY. UK § ABOUT THE AUTHOR PREPARED BY COMPUTER FORENSICS LAB E-DISCOVERY TEAM HOWTOREADTHISGUIDE § CONTENTS In this guide 01 Executive summary and the ECA Principle 02 ECA and EDA: two related disciplines, one central proposition 03 The traditional problem: collect everything and review later 04 ECA and the disclosure framework in England and Wales 05 The strategic benefits of ECA (twelve benefits) 06 What modern e Discovery technology adds to ECA 07 The modern ECA workflow: twelve stages in a feedback loop 08 The evidence universe 09 ECA can reveal what is missing: source architecture and alternative evidence paths 10 Case study: Pyrrho Investments v MWB Property (2016) 11 Case study: Triumph Controls v Primus International (2018) 12 Worked case study: Halden Systems v a departing sales director (hypothetical) 13 Cost illustration and the e Discovery cost funnel 14 Questions ECA should answer (lawyer's checklist of 54 questions) 15 ECA deliverables and sample templates 16 ECA dashboard concept (illustrative data only) 17 ECA and privilege 18 ECA and UK data protection 19 Fifteen ECA mistakes that can become expensive later 20 When digital forensics should enter the ECA process 21 Practical implementation plan: first 24 hours to the DRD 22 Question banks: client, opponent and provider 23 Model instruction wording 24 Red flags 25 Glossary 26 Conclusion: early knowledge changes the economics of disclosure; specialist support 27 References and bibliography 28 Disclaimer and jurisdiction a l notes § 01 · EXECUTIVE SUMMARY Executive summary THEECAPRINCIPLE "Do not begin by asking how quickly every potentially relevant byte can be collected. Begin by asking what the legal team needs to know, which evidence could answer those questions, where that evidence is likely to exist, and what proportionate method should be used to preserve, assess and collect it." Early Case Assessment (ECA) is the structured, early analysis of a dispute: its facts, legal issues, risks, likely liability, key witnesses, evidence requirements, probable cost and possible strategy. Early Data Assessment (EDA) is the early analysis of the electronically stored information itself: custodians, sources, volumes, dates, file types, communications, duplication, concepts, keywords and collection requirements. The EDRM Identification Standards treat the two as the twin components of identification. This guide argues that the principal value of ECA is not a smaller review population. It is knowledge, obtained early enough that strategy, scope, budget and preservation decisions can still be changed. QUESTION SHORT ANSWER FIVEPOINTSTOTAKEAWAY § 02 · FIRST PRINCIPLES ECA and EDA: two related disciplines, one central proposition The central proposition of this guide is simple. The principal benefit of Early Case Assessment is not merely reducing the number of documents lawyers must review. Its greater value is allowing legal teams to understand the evidence, risks, relationships, likely disclosure burden and potential strengths and weaknesses of a matter sufficiently early to make better strategic decisions. The problem explained in plain English Important terminology TERM MEANING IN THIS GUIDE 01 · EXECUTIVE SUMMARY How modern e Discovery combines the two L AW YER ' SQUESTION Is ECA just a vendor label for a processing platform? 02 · ECAANDEDA § 03 · THE PROBLEM The traditional problem: collect everything and review later Consider a hypothetical commercial dispute over a terminated supply agreement. The client identifies custodians. Their data sits in Microsoft 365 mailboxes, Teams, Share Point and One Drive, on several laptops and applications. The first instruction is: "collect everything for all twenty, back to 2019, so we are covered." What "collect everything" actually produces CONSEQUENCE WHY IT HAPPENS § 04 · WHYITMATTERSLEGALLY ECA and the disclosure framework in England and Wales proportionality, cooperation, preservation, informed identification of custodians and sources, and a considered approach to technology. ECA is the practical work that makes those obligations achievable and the party's positions credible. The Business and Property Courts: PD 57AD TRADITIONAL · " COLLECTFIRST " MODERNDATA - INFORMEDECA " UNDERSTANDFIRST " UNDERSTANDING ARRIVES LAST FIRST 03 · THETRADITIONALPROBLEM CPR Part 31 and PD 31B ECA findings and their possible disclosure consequences ECA FINDING POSSIBLE DISCLOSURE CONSEQUENCE 04 · ECAANDTHEDISCLOSUREFRAMEWORK JURISDICTION A L NOTES § 05 · STRATEGICBENEFITS The strategic benefits of ECA 5.1 Understanding the factual story earlier 5.2 Identifying the important custodians EARLY CASE ASSESSMENT CASE MERITS KEY PEOPLE MISSING EVIDENCE EVIDENCE SOURCES PRESERVATION RISK S DATE RANGE S PRIVILEGE COMMUNICATION PATTERNS DISCLOSURE COSTS HOT DOCUMENTS DATA VOLUMES ADVERSE EVIDENCE STRATEGY 5.3 Finding important documents earlier 5.4 Discovering adverse documents early 5.5 Improving case valuation and risk analysis HYPOTHETICALCOMMUNICATIONNETWORK · ILLUSTRATIVEONLY SALES DIRECTOR 05 · THESTR AT EGICBENEFITSOFECA 5.6 Targeting collection 5.7 Reducing unnecessary review 5.8 Better budgeting 5.9 Better settlement decisions 5.10 Better disclosure negotiations 5.11 Better preservation decisions 5.12 Better data-protection outcomes § 06 · TECHNOLOGY What modern e Discovery technology adds to Early Case Assessment can go wrong. Human validation remains necessary in every case, because each tool answers a narrow question well and a broad question badly. TOOL WHAT IT DOES WHAT QUESTION IT ANSWERS KEY LIMITATION Generative AI in ECA: emerging uses and necessary safeguards BEFOREGENERATIVEAITOUCHESASSESSMENTDATA, CONFIRM 06 · WH AT MODERNEDISCOVERYTECHNOLOGYADDS Are predictive coding, TAR, CAL, semantic search and generative AI the same thing? § 07 · PRACTICALWORKFLOW The modern ECA workflow: twelve stages in a feedback loop SOURCES DATA COMMUNI CAT IONS LEGAL ISSUES DATA SOURCES REFINED SCOPE PRESERVATION LEGAL ASSESSMENT EARLY COLLECTION FINDING S ANALYTICS ITERATE COLLECTION AND REVIEW § 08 · EVIDENCE - SOURCE MAP The evidence universe ECA should identify not merely "documents" but the systems and relationships capable of producing evidence. of them. COMMERCIAL DISPUTE PEOPLE DEVICES THIRD PARTIES COMMUNICATIONS BACKUP S / HISTORICAL CLOUD SYSTEMS NETWORK SYSTEMS BUSINESS APPLICATION S 07 · THEMODERNECAWORKFLOW REGION WHAT TO ENUMERATE IN ECA T YPICAL SURPRISES § 09 · EVIDENCEGAPS ECA can reveal what is missing Absence is evidence of something. An abrupt silence, a referenced attachment that is not there, a name that source and one or more alternative evidence paths. WHAT ECA NOTICES PRIMARY EVIDENCE SOURCE ALTERNATIVE EVIDENCE PATH 08 · THEEVIDENCEUNIVERSE Source architecture: where else the evidence lives EVIDENCE CLOUD BACKUP LOGS LOCAL COUNTERPART DELETED / DEVICE DEVICE RECOVERABLE MISSING LAPTOP 09 · ECACANREVEALWH AT ISMISSING § 10 · CASESTUDY Case study: Pyrrho Investments Ltd v MWB Property Ltd [2016] EWHC 256 (Ch) HISTORICALNOTE The facts Why the court approved predictive coding ECA lessons LESSONSFORTODAY ' SLAWYER § 11 · CASESTUDY Case study: Triumph Controls UK Ltd v Primus International Holding Co [2018] EWHC 176 (TCC) 31B and the TeCSA/TECBAR e Disclosure Protocol. The judgment demonstrates that technology does not make an e Discovery methodology automatically defensible. What happened 17.6m+ c. 3.1m HISTORICALCASEDECIDEDUNDERCPR31 / PD31B · PRE - DATESPD57AD FIGURESFROMTHEJUDGMENTAT [ 5 ] AND [ 33 ] 10 · CASESTUDY: PYRRHOINVESTMENTS ( 2016 ) Why the sampling and review approach was found inadequate THEJUDGMENTDOESNOTSAY TECHNOLOGY SAMPLING VALIDATION LEGAL OVERSIGHT DOCUMENTED METHODOLOGY DEFENSIBLE APPROACH TECHNOLOGY WITHOUT ADEQUATE VALIDATION AUTOMATICALLY DEFENSIBLE 11 · CASESTUDY: TRIUMPHCONTROLS ( 2018 ) 4.2 and 5.2; PD 57AD para 9.6). § 12 · WORKED EXAMPLE Worked case study: Halden Systems Ltd and a departing sales director HYPOTHETICAL Halden Systems, a UK software company, alleges that its former sales director, Mr Voss, diverted major customers to a competitor before resigning. It seeks injunctive relief and damages for breach of contract and fiduciary duty and threatens proceedings in the Business and Property Courts. Potential evidence includes Exchange Online, Teams, One Drive, the company laptop, an iPhone, Whats App, Salesforce, VPN logs, USB activity and indicators of a personal cloud-storage account. Initial position INITIAL ASSUMPTION ECA FINDING STRATEGIC CONSEQUENCE Preservation versus collection, and collection versus review If we only collect three custodians, are we exposed to the criticism made in Triumph Controls? § 13 · COSTILLUSTRATION Cost illustration and the e Discovery cost funnel The figures below are hypothetical and formula-based. They are not market prices, averages or benchmarks. Their purpose is to show how apparently modest decisions taken early propagate through the funnel and multiply at the review stage. STAGE PATH B: ECA-INFORMED (HYPOTHETICAL) PATH A: COLLECT EVERY THING (HYPOTHETICAL) 12 · WORKEDCASESTUDY ( HYPOTHETICAL ) POTENTIAL EVIDENCE UNIVERSE PRESERVED DATA COLLECTED DATA PROCESSED DATA DE-DUPLICATE D DATA POTENTIALLY RELEVANT REVIEW POPULATION PRODUCED 13 · COSTILLUSTR AT IONANDTHECOSTFUNNEL § 14 · LAWYER ' SCHECKLIST Questions ECA should answer work; if it can answer only by assumption, it has identified a risk. Case Data custodian? Disclosure Technology Risk Cost Privilege Data protection § 15 · OUTPUTS ECA deliverables and sample templates A professional ECA exercise produces documents, not impressions. The templates below are skeletons; each is populated with measured figures and the date on which they were measured. EVIDENCE - SOURCEMAPDUPLI CAT I ON REPORT CUS TO DIANM AT RIXTIMELINE DATA-VOLUME REPORT FILE -TYPEANA LY SIS DAT EDISTRIBUTION COMMUNI CAT IONMAP DOMAINANA LY SIS KEY- CONCEPTREPORTDISC LO SURE - COSTESTIM AT E KEY WO RD -TEST REPORT REVIEW STRATEGY H OT- DOCUMENT LIST A DV ERSE - DOCUMENTES CA L AT ION DATA- GA PREPORT PRESE RVAT ION - RISKREGISTER COLLECTIONRECOMMEN DAT ION 14 · QUESTIONSECASHOULDANSWER TECHNI CA L- RISKREGISTER § 16 · DASHBOARDCONCEPT ECA dashboard concept A mock dashboard showing the kind of intelligence a good ECA platform surfaces. Every value is fictional and illustrative; none is drawn from a real matter or from any benchmark. 18 31 24 CUSTODIANS POTENTIAL SOURCES SOURCES ASSESSED PRESERVATION RISKS OPEN 412 GB 1.62m 0.94m 2021-03 to SOURCE VOLUME PROCESSED DOCUMENTS AFTER DEDUPLICATION (GLOBAL) 2026-06 DATE RANGE · PEAK MOST ACTIVE CUSTODIANS DOCS EXTERNAL ISSUES COUNT STATUS TOP EXTERNAL DOMAINS MSGS CATEGORY COST ESTIMATES (ILLUSTRATIVE) VALUE BASIS § 17 · PRIVILEGE AND CONFIDENTIAL IT Y ECA and privilege Early assessment identifies where privileged material concentrates before a wide review team sees it. Domain analysis lists the law firms, in-house legal addresses and legal department groups in the data; name lists identify 15 · ECADELIVERABLESANDTEMPL AT ES lawyers and paralegals; family analysis shows the email chains and attachments that travelled with legal advice; date analysis shows the period after litigation was contemplated, when litigation privilege may attach. Why privilege search in g is not infallible Safeguards before substantive material is exposed too widely Does running analytics on the client's data risk waiving privilege? § 18 · DATAPROTECTION ECA and UK data protection the Data (Use and Access) Act 2025, govern its collection, hosting, analysis, transfer and retention. The framework does not prevent disclosure; it disciplines how disclosure is prepared. CONSIDERATION POSITION (ENGLAND AND WALES, AS AT SEPTEMBER 2026) 17 · ECAANDPRIVILEGE TWOTHINGSECADOESNOTPERMIT 18 · ECAANDUKD ATA PROTECTION § 19 · COMMON MISTAKES Fifteen Early Case Assessment mistakes that can become expensive later 1. Starting too late 2. Confusing preservation with collection 3. Collecting before understanding systems 4. Choosing custodians solely from an or g an is at i on chart 5. Ignoring former employees 6. Relying only on interviews 7. Assuming email contains everything 8. Ignoring Teams, Slack and Whats App 9. Using untested keywords 10. Ignoring metadata 11. Treating deduplication as merely deletion 12. Failing to validate samples 13. Overlooking privileged material 14. Ignoring cloud retention and deletion 19 · FIFTEENECAMIS TA KES 15. Failing to document decisions § 20 · WHENTOINVOLVEADIGITALFORENSICEXPERT When digital forensics should enter the ECA process Ordinary e Discovery collection copies what exists, in a defensible way, for review. Forensic investigation asks what notice, early, which one the facts require. CIRCUMSTANCE WHY FORENSIC EXPERT IS E IS NEEDED EARLY § 21 · IMPLEMENTATIONPLAN Practical implementation plan WINDOW LEGAL TEAM CLIENT IT EDISCOVERY TEAM DIGITAL FORENSIC TEAM § 22 · QUESTIONBANKS Question banks Questions to ask the client 21 · PRACTICALIMPLEMEN TAT IONPLAN Questions to ask the opponent Questions to ask a forensic or e Disclosure provider § 23 · SUGGESTED WORDING Model instruction wording A · INSTRUCTIONTOANEDISCLOSUREPROVIDERFORANECAEXERCISE B · PRESERVATION INSTRUCTION TO THE CLIENT 22 · QUESTIONBANKS C · LETTERTOTHEOPPONENTONECA - INFORMEDSCOPE D · INSTRUCTIONTOADIGITALFORENSICEXAMINERWITHINECA § 24 · REDFLAGS Red flags search order. § 25 · GLOSSARY Glossary 23 · MODEL INSTRUCTION WORDING 25 · GLOSSARY § 26 · CONCLUSION Early knowledge changes the economics and strategy of disclosure Well-designed ECA moves a legal team from assumptions about a dataset to measurable information about people, evidence sources, data volumes, relationships, important events, relevant documents, adverse evidence, missing evidence, costs and technical risks. It does not guarantee lower costs, and it does not guarantee better outcomes. What it provides is evidence-based intelligence at the one point in a case when legal and disclosure strategies can still be changed at modest cost. When specialist e Discovery and digital forensic support may help BEFOREECA · " WETHINK " AFTERECA · " THEAVAILABLEEVIDENCEINDICATES " HYPOTHETICALEXAMPLESONLY § 27 · REFERENCESANDBIBLIOGRAPHY References and bibliography 26 · CONCLUSION § 28 · DISCLAIMER Disclaimer and jurisdiction a l notes 1 September 2026. It is not legal advice, does not create a solicitor-client or expert-client relationship, and FORUM THIS GUIDE 27 · REFERENCESANDBIBLIOGRAPHY § APPENDIX · DETACHABLECHECKLIST Early Case Assessment Checklist for Litigation Lawyers Issues Communications Custodians Systems Preservation Data volumes Date ranges Search terms Adverse documents Missing evidence 28 · DISCLAIMER AND JURISDICTION A L NOTES Alternative evidence sources Review strategy Collection strategy Disclosure strategy Documentation APPENDIX · ECACHECKLIST INSTRUCTTHELAB Speak to a forensic examiner, not a salesperson. NEWENQUIRIESEMAILE - DISCOVERY +44 (0)20 7164 6971 info@cflab.uk e-discovery.uk CFLELECTRONICEVIDENCESERIES · BENEFITSOFEARLYCASEASSESSMENTINEDISCOVERY · © COMPUTER FORENSICS LAB LT D