Orient
Confirm the active matter and identify the precise issue that needs attention.
LegalRAG Pro user training
These films show where AI enters the practitioner workflow: bounded Ask questions, Case Operator investigations, evidence and chronology analysis, proposed work, drafts and reports — all kept inside a source-linked matter with professional control.
Training uses the fictional Eleanor Morgan v Alderwick Systems Ltd synthetic matter. No client information is shown. Professional legal judgement remains with the lawyer.
Choose your route
New users should normally start with the quick start, then use the full practitioner film as the detailed reference.
See the complete practitioner journey at a glance before choosing a focused workflow.
Start here →8:10 · complete workflowFollow one substantial matter through evidence, issues, investigation, supervised work and professional decision.
Open full training →1:07 · leadership viewA concise operating-model briefing for partners, senior management and legal innovation leaders.
Watch orientation →Start here
A concise route through the connected working method: matter context, source-linked evidence, bounded investigation, supervised work and professional decision.
Complete practitioner training
The complete connected-matter film: orientation, issues, chronology, evidence, source inspection, Ask, Case Operator, tasks, drafts, reports and professional review.
For partners and legal leaders
Use this short film when a senior stakeholder needs the operating model and professional-control principle before deciding whether to examine the practitioner workflow in detail.
Working method
Confirm the active matter and identify the precise issue that needs attention.
Use chronology, evidence and source documents to establish what the record actually says.
Use Ask for bounded questions or Case Operator for governed matter work where appropriate.
Review tasks, drafts and report state before approving, relying on or circulating work.
Finance training
The 64-second practitioner film uses synthetic data to show historical financials, comparables, deterministic calculations, evidence, limitations, traceability, export and the Finance AI boundary.