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: Establish the Foundation — Ingestion, Search, Retrieval
Module 1: The Legal Engineer’s Landscape
- Learning objectives — understand the role, where AI integrates into legal work, and the two critical risks that pervade all operations.
- Topics
-
- The legal engineer role and current market demand.
- AI applications in eDiscovery, review, contracts, research, and investigations; plain-language explanation of the EDRM model.
- Build vs. buy considerations.
- The two universal risks: confidentiality/privilege and defensibility.
Module 2: Legal Data Complexity — Ingestion and Extraction
- Learning objectives — handle the reality of managing legal data at scale.
- Topics
- Handling 1,400+ file types, emails, PST files, scanned documents, load files (.dat/.opt); and critical embedded metadata.
- Techniques for text extraction (Tika), OCR, and deduplication strategies.
- Lab: FreeEed Ingestion — construct an ingestion pipeline over a deliberately messy document set (including emails/PSTs, scans, and load files).
Module 3: Search and Retrieval — The Core Foundation
- Learning objectives — build the essential eDiscovery primitive: finding any information within any dataset.
- Topics — full-text search and indexing (Solr/Lucene); relevance scoring, metadata/date filtering; searching across OCR-processed content.
- Lab: eDiscovery Search — index a corpus and perform real eDiscovery-style searches, including within OCR’d scans.
Module 4: RAG for Legal Documents — with Citations
- Learning objectives — implement RAG over legal documents that includes source citations.
- Topics
- Why retrieval, not fine-tuning, is preferred for sensitive material — ensuring the model never ingests raw documents.
- Chunking, embeddings, and critically, 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 provides answers backed by source citations.
Day 2: Ensure Privacy, Defensibility, and Deployment Readiness
Module 5: Privacy, Privilege, and Local Serving — Avoiding the Privilege Trap
- Learning objectives — keep legal data local and demonstrate certification capability.
- Topics
- Data flow analysis when interacting with cloud AI services.
- Privilege waiver implications, duty of competence, and the spectrum of "private" (contractual vs. physical separation).
- Case study: Morgan v. V2X and why local hosting is court-defensible.
- Serving local models (via Ollama/vLLM) and monitoring outbound traffic.
- Lab: Local Model + Egress Proof — run a local model end-to-end and use monitoring tools to prove no data egressed.
Module 6: Defensible AI Review
- Learning objectives — measure and document an AI review process to ensure legal validity.
- Topics
- Court-admissible metrics: recall, elusion, precision, ground-truth validation; TAR/active learning.
- Transparency (justifying classification decisions) and reproducibility — pinning the model version, fixing settings, and comprehensive logging.
- Creating a "defensible case snapshot" that allows a review to be re-run a year later with identical results.
- Lab: Defensible Review — evaluate an AI review against blind ground truth data and produce a reproducibility package.
Module 7: Deployment — Workflow, Private Hosting, and Governance
- Learning objectives — assemble components into a workflow, deploy privately, and evaluate performance.
- Topics
- Multistep legal workflows (ingest → search → summarize → review → produce) with human-in-the-loop processes.
- Essentials of private/on-premises deployment (containerization; keeping data in-house).
- AI governance for legal teams and scoring the system using SAIS-100 (the Elephant Scale Secure AI Score).
- Lab: Score and Package — wire a multistep workflow, evaluate 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 with citations using a local model, measure review defensibility, and package for private deployment.
- Participants depart with a portfolio-ready project that mirrors real-world legal engineer responsibilities.
Optional Day 3 / Advanced Modules (delivered as a 3rd day or modular series)
- Investigations: Entities, Relationships, and Timelines — extract people/organizations/dates, reconstruct email threads, build chronologies, map near-duplicates, and trace document lineage. Lab: build a timeline and entity/relationship view.
- Agentic and Multistep Legal Workflows (Deep Dive) — advanced orchestration, contract analysis, multi-document synthesis, tool use, and guardrails as design principles. Lab: construct a multistep workflow with a human checkpoint.
- Scale Deployment — on-premises and appliance deployment, distributed processing for large volumes, regulated environments (CJIS, government, higher education), and hardware sizing. Lab: containerize and scale a processing job across multiple workers.
- Governance and Compliance Deep Dive — the AI regulatory landscape (100+ US state AI laws, EU AI Act), audit requirements, and comprehensive SAIS-100 governance audits. Lab: audit a legal-AI system against a governance/defensibility checklist.
Requirements
- Proficiency in Python and familiarity with basic APIs.
- Helpful: User-level understanding of Large Language Models (LLMs) — no machine learning background is required, as we build the foundational mental model.
- No legal background required — essential legal concepts are taught within their practical context.
Audience
- Software or AI engineers transitioning into the legal technology sector.
- Engineers at legal-tech firms who need deeper domain knowledge in law.
- Technically adept legal, eDiscovery, or information-governance professionals who prefer building solutions rather than just purchasing them.
- Any professional aiming for a "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
