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 — comprehend the role of the legal engineer, how AI integrates into legal work, and the two critical risks that permeate all activities.
- Topics
-
- The legal-engineer role and current market demand.
- AI integration points: eDiscovery, review, contracts, research, and investigations; explained in plain terms via the EDRM model.
- Build versus buy decisions.
- 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/PST formats, scanned paper, load files (.dat/.opt), and critical embedded metadata.
- Text extraction (Tika), OCR, and de-duplication strategies.
- Lab: FreeEed Ingestion — construct an ingestion pipeline using a deliberately messy document set (emails/PSTs, scans, load files).
Module 3: Search and Retrieval — the Foundation
- Learning objectives — build the core eDiscovery primitive: finding any information within any dataset.
- Topics — full-text search and indexing (Solr/Lucene); relevance scoring, metadata filtering, date range constraints; searching across OCR-processed content.
- Lab: eDiscovery Search — index a corpus and execute real-world eDiscovery-style searches, including within OCR’d scans.
Module 4: RAG for Legal Documents — with Citations
- Learning objectives — implement RAG over legal documents that explicitly cites its sources.
- Topics
- Why retrieval, not fine-tuning, is preferred for sensitive material—the model never ingests the full document corpus.
- Chunking strategies, embeddings, and above all, citations / provenance.
- Multi-document and thread summarization techniques.
- Lab: Legal RAG with Citations — build a RAG-based 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 location.
- Topics
- Data flow when interacting with cloud-based AI services.
- Privilege waiver risks, duty of competence, and the 'private' spectrum (contractual vs. physical isolation).
- Morgan v. V2X precedent 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 tools, that no data left the environment.
Module 6: Defensible AI Review
- Learning objectives — measure and document an AI review process to ensure it holds up in legal scrutiny.
- Topics
- Court-admissible metrics: recall, elusion, precision, ground-truth validation; TAR (Technology-Assisted Review) / active learning.
- Transparency (explaining coding decisions) and reproducibility — pinning the model version, fixing settings, and logging all actions.
- The 'defensible case snapshot' enabling a reviewer to re-run the process a year later and achieve 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 components into a workflow, deploy it privately, and evaluate its quality.
- Topics
- Multi-step legal workflows (ingest → search → summarize → review → produce) with human-in-the-loop controls.
- Private/on-premises deployment essentials (containerization; keeping data within the organization).
- AI governance for legal contexts 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)
- Construct a private, defensible legal-AI application end-to-end — ingest a messy corpus, search it, answer questions using citations via a local model, measure the defensibility of the review, and package it for private deployment.
- Participants depart 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/organizations/dates, reconstruct email threads, build chronologies, map near-duplicates and document lineage. Lab: construct a timeline and entity/relationship view.
- Agentic and Multi-Step Legal Workflows (deep dive) — advanced orchestration, contract analysis, multi-document synthesis, tool use, and guardrails as design principles. 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 multiple 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 LLMs (no ML background required—we develop the necessary mental model).
- No legal background required—essential legal concepts are taught within context.
Audience
- Software/AI engineers transitioning into legal technology.
- Engineers at legal-tech companies needing deeper domain-specific legal knowledge.
- Technically-minded legal, eDiscovery, or information-governance professionals who prefer building solutions over purchasing them.
- Anyone targeting the 'legal engineer' or 'AI legal engineer' role.
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
