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.
Duration 14 hours
Course Outline
Day 1: Establishing the Foundation — Ingest, Search, and Retrieve
Module 1: The Legal Engineer’s Landscape
- Learning objectives—Comprehend the role, the integration of AI in legal work, and the two overarching risks present in all scenarios.
- Topics
-
- The role of the legal engineer and the current demand for these skills.
- AI applications: eDiscovery, review, contracts, research, and investigations; understanding the EDRM model in simple terms.
- The build vs. buy decision framework.
- The two critical risks: confidentiality/privilege and defensibility.
Module 2: Handling Messy Legal Data — Ingestion and Extraction
- Learning objectives—Manage the complexities of legal data at scale.
- Topics
- Support for 1,400+ file types, including email/PST, scanned documents, and load files (.dat/.opt); the importance of embedded metadata.
- Text extraction (Tika), OCR, and deduplication strategies.
- Lab: FreeEed Ingestion — Construct an ingestion pipeline using a deliberately messy document set (including email/PST, scans, and load files).
Module 3: Search and Retrieval — The Core
- Learning objectives—Develop the fundamental eDiscovery capability: locating specific content within a vast corpus.
- Topics—Full-text search and indexing (Solr/Lucene); relevance ranking, metadata and date filtering; searching within OCR-processed content.
- Lab: eDiscovery Search — Index a document corpus and execute real eDiscovery-style searches, including within OCR-processed scans.
Module 4: RAG for Legal Documents — With Citations
- Learning objectives—Build a RAG system for legal documents that provides source citations.
- Topics
- Why retrieval is preferred over fine-tuning for sensitive materials—ensuring the model does not memorize the documents.
- Chunking, embeddings, and the critical role of citations/provenance.
- Summarization across multiple documents and threads.
- Lab: Legal RAG with Citations — Create a RAG Q&A system over a document set that answers queries with source citations.
Day 2: Ensuring Privacy, Defensibility, and Deployability
Module 5: Privacy, Privilege, and Local Serving — The Privilege Trap
- Learning objectives—Keep legal data local and capable of certification.
- Topics
- Understanding data flow when interacting with cloud AI services.
- Privilege waiver, duty of competence, and the “private” spectrum (contractual vs. physical isolation).
- Morgan v. V2X and the defensibility of local processing in court.
- Serving local models (Ollama / vLLM) and monitoring outbound traffic.
- Lab: Local Model + Egress Proof — Run a local model end-to-end and use monitoring tools to prove that no data left the environment.
Module 6: Defensible AI Review
- Learning objectives—Measure and document AI reviews to ensure they are legally robust.
- Topics
- Court-accepted metrics: recall, elusion, precision, ground-truth validation; TAR / active learning.
- Transparency (explaining document coding) and reproducibility—pinning the model, fixing settings, and logging all actions.
- Creating a “defensible case snapshot” that allows a review to be re-executed later with identical results.
- Lab: Defensible Review — Evaluate an AI review against blind ground truth and generate a reproducibility bundle.
Module 7: Deployment — Workflow, Private Infrastructure, and Governance
- Learning objectives—Assemble components into a workflow, deploy privately, and assess the system.
- Topics
- Designing multi-step legal workflows (ingest → search → summarize → review → produce) with human-in-the-loop oversight.
- Essentials of private/on-prem deployment (containerization; keeping data within the organization).
- Brief overview of AI governance for legal contexts, and scoring the system using SAIS-100 (the Elephant Scale Secure AI Score).
- Lab: Score and Package — Configure a multi-step workflow, evaluate it with SAIS-100, and prepare it for private deployment.
Capstone (Integrated across Day 2)
- Develop a private, defensible legal-AI application end-to-end—ingest a messy corpus, enable search, answer questions with citations using a local model, measure a defensible review, and package the solution for private deployment.
- Participants will leave with a portfolio project that mirrors the responsibilities of a legal engineer.
Optional Day 3 / Advanced Modules (available as a third day or modular series)
- Investigations: Entities, Relationships, and Timelines — Extract people/organizations/dates, reconstruct email threads, build chronologies, and map near-duplicates and document lineage. Lab: Construct a timeline and entity/relationship view.
- Agentic and Multi-Step Legal Workflows (Advanced) — Advanced orchestration, contract analysis, multi-document synthesis, and tool usage with guardrails as design principles. Lab: Build a multi-step workflow with human checkpoints.
- Deployment at Scale — On-prem and appliance deployment, distributed processing for high volumes, and regulated environments (CJIS, government, higher education), including hardware sizing. Lab: Containerize and scale processing jobs across workers.
- Governance and Compliance Deep-Dive — Overview of 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 basic API concepts.
- Recommended: User-level familiarity with LLMs (no machine learning background is required, as the necessary mental models will be built during the course).
- No legal background is necessary—essential legal concepts will be taught in context.
Audience
- Software and AI engineers entering the legal tech sector.
- Engineers at legal-tech companies who require deeper domain-specific knowledge.
- Technically proficient legal, eDiscovery, or information-governance professionals who aim to build solutions rather than solely procure them.
- Individuals targeting the “legal engineer” or “AI legal engineer” role.
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
