Legal Intake, Triage & Assignment
A production intake pipeline that screens, enriches, triages, estimates, recommends, reviews, and assigns legal enquiries end-to-end.
Enquiry to assignment, in one pipeline.
Every enquiry flows through screening, ML classification, forecasting, retrieval, ranking, and a human-in-the-loop review before being assigned to a fee-earner.
- stage 01autoInbound enquiryemail · form · portal
- stage 02autoRelevance filterML classifier
- stage 03autoCase classificationdepartment + case type
- stage 04autoCost & time forecastregression models
- stage 05autoLegal retrievalUK laws · case law
- stage 06autoFee-earner recommendationranking model
- stage 07HITLDepartment head reviewhuman-in-the-loop
- stage 08autoAssignment + client updatestructured record
Measured outcomes.
From inbox to fee-earner.
Anonymised summary of the system's stages and design choices.
Problem
Inbound enquiries queue up across email and portals. Manual triage takes days, blocks fee-earner assignment, and leaks revenue on missed matters.
Screening & classification
Custom ML filters relevant emails and classifies case type and department, reducing reliance on open-ended LLM reasoning and hallucination risk.
Forecasting
Regression models estimate cost and time-to-resolution per matter, feeding downstream ranking and department planning.
Retrieval
Relevant UK laws and court cases are retrieved at assignment time to give the fee-earner immediate context on the matter.
Recommendation & HITL
A ranking model recommends fee-earners; department heads review and approve assignments in a lightweight human-in-the-loop step.
Assignment & records
Structured case records, department alerts, and client updates are generated automatically - minutes instead of days.