Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Day 1: Build the Foundation — Ingest, Search, Retrieve
Module 1: The Legal Engineer’s Landscape
- Learning objectives — understand the role, where AI fits within legal work, and the two critical risks that permeate the field.
- Topics
-
- The legal-engineer role and its current market demand.
- Where AI fits: eDiscovery, review, contracts, research, investigations; the EDRM model explained simply.
- Build vs. buy considerations.
- The two pervasive risks: confidentiality/privilege and defensibility.
Module 2: Legal Data Is Messy — Ingestion and Extraction
- Learning objectives — handle the reality of legal data at scale.
- Topics
- Handling 1,400+ file types, email and PST files, scanned paper, load files (.dat/.opt); understanding crucial embedded metadata.
- Text extraction (Tika), OCR, and de-duplication strategies.
- Lab: FreeEed Ingestion — build an ingestion pipeline over a deliberately messy document set (email/PST, scans, load files).
Module 3: Search and Retrieval — the Foundation
- Learning objectives — build the core eDiscovery primitive: finding anything within everything.
- Topics — full-text search and indexing (Solr/Lucene); relevance, metadata and date filtering; searching across OCR'd content.
- Lab: eDiscovery Search — index a corpus and run real eDiscovery-style searches, including within OCR'd scans.
Module 4: RAG for Legal Documents — with Citations
- Learning objectives — build RAG over legal documents that cites its sources accurately.
- Topics
- Why retrieval, not fine-tuning, is preferred for sensitive material — the model never ingests the raw documents directly.
- Chunking, embeddings, and crucially citations/provenance.
- Multi-document and thread summarization techniques.
- Lab: Legal RAG with Citations — build a RAG Q&A system over a document set that answers questions with source citations.
Day 2: Make It Private, Defensible, and Shippable
Module 5: Privacy, Privilege, and Local Serving — the Privilege Trap
- Learning objectives — keep legal data local and provide certification for its security.
- Topics
- Data flow when interacting with cloud AI services.
- Privilege waiver, duty of competence, and the 'private' spectrum (contractual vs. physical).
- The significance of Morgan v. V2X and why local deployment is court-defensible.
- Serving local models (Ollama/vLLM) and monitoring outbound traffic.
- Lab: Local Model + Egress Proof — run a local model end-to-end and prove, via monitoring, that no data has left the environment.
Module 6: Defensible AI Review
- Learning objectives — measure and document an AI review process so it withstands legal scrutiny.
- Topics
- Critical metrics for court: recall, elusion, precision, ground-truth validation; TAR/active learning principles.
- Transparency (why did the system code this document?) and reproducibility — pinning the model version, fixing settings, and logging every step.
- The 'defensible case snapshot' allowing someone to re-run your review a year later with identical results.
- Lab: Defensible Review — measure an AI review against a blind ground truth and produce a reproducibility bundle.
Module 7: Ship It — Workflow, Private Deployment, and Governance
- Learning objectives — assemble the components into a workflow, deploy privately, and score performance.
- Topics
- A multi-step legal workflow (ingest → search → summarize → review → produce) incorporating human-in-the-loop processes.
- Essentials of private/on-premises deployment (containerization; keeping data within the building).
- AI governance for legal in brief, and scoring the system using SAIS-100 (the Elephant Scale Secure AI Score).
- Lab: Score and Package — wire a multi-step workflow, score it with SAIS-100, and package it for private deployment.
Capstone (integrated across Day 2)
- Build a private, defensible legal-AI application end-to-end — ingest a messy corpus, search it, answer questions with citations using a local model, measure a defensible review, and package it for private deployment.
- Participants leave with a portfolio project that mirrors the actual work of a legal engineer.
Optional Day 3 / Advanced Modules (deliverable as a 3rd day or a modular series)
- Investigations: Entities, Relationships, and Timelines — extract people/orgs/dates, reconstruct email threads, build chronologies, map near-duplicates and document lineage. Lab: build a timeline and entity/relationship view.
- Agentic and Multi-Step Legal Workflows (deep) — richer orchestration, contract analysis, multi-doc synthesis, tool use and guardrails as a design principle. Lab: build a multi-step workflow with a human checkpoint.
- Deployment at Scale — on-premises and appliance deployment, distributed processing for large volumes, regulated environments (CJIS, government, higher-ed), hardware sizing. Lab: containerize and scale a processing job across workers.
- Governance and Compliance Deep-Dive — the AI-regulation landscape (100+ US state AI laws, the EU AI Act), audit requirements, and a full SAIS-100 governance audit. Lab: audit a legal-AI system against a governance/defensibility checklist.
Requirements
- Proficiency in Python and familiarity with basic APIs.
- Helpful: user-level familiarity with Large Language Models (LLMs) — no machine learning background required, as we build the conceptual model from scratch.
- No prior legal background needed — essential legal concepts are taught within context.
Audience
- Software and AI engineers transitioning into legal tech.
- Legal-tech company engineers requiring deeper domain expertise in law.
- Technically minded legal, eDiscovery, or information-governance professionals who wish to build solutions rather than merely purchase them.
- Anyone aspiring to the role of 'legal engineer' or 'AI legal engineer'.
14 Hours
Testimonials (1)
That i gained a knowledge regarding streamlit library from python and for sure i'll try to use it to improve applications in my team which are made in R shiny
