Wirewalk Instituteof AI
pro-210 Intermediate AvailableFlagship

Building and Deploying AI in Legal Practice

For KM, litigation, contracts, conflicts and legal operations leads: build a versioned evidence recommendation across one synthetic firm case.

Level
Intermediate
Study time
25 hours
Lessons
21 in 6 modules
Exam
20 questions

About this course

Alder Ridge LLP, a fictional 300-lawyer US firm, has fourteen days and a $60,000 optional evidence envelope. Its Tillman litigation, Northfield commercial work and Pellston diligence expose fabricated citations, incomplete evaluations, custodian misses, changed amendments, permission leaks and manipulated intake. Preserve and revise eight artifacts into a continue, narrow, hold or next-cycle recommendation. Learn from authored outputs and isolated worked calculations; no client information, account, subscription or live dispatch is needed for the core route.

US-first primary sources are refreshed within the November 14, 2026 source record. Operative federal rules, adopted jurisdictional rules, ABA interpretive guidance, historical court decisions, proposals, vendor descriptions and local case policy have different force. The current judiciary Evidence Rules compilation contains neither proposed 707 nor draft 901(c); proposal history is bounded to the retrieved October agenda and November suggestions records. Vendor claims do not prove local performance, confidentiality or privilege.

Plan about 25 hours for reading,21 twenty-minute case tasks, six 12-minute module labs, a 32-minute capstone, dossier assembly/revision, fallible AI practice feedback, retrieval and the 40-minute exam. This is an author estimate for supplied-output work, not observed learner timing. Optional expanded legal research, code and live-tenant work add time. Practice feedback is optional and can be wrong. Completion follows lessons, listed labs played to any ending and the exam; practice feedback is not a certificate gate. The certificate records course completion, not workplace competence, CLE credit, a professional license, specialty accreditation, legal compliance or vendor endorsement. Educational, not legal advice.

What you will be able to do

  • Analyze a draft brief and design a version-bound citation and proposition-support workflow with a responsible signer and correction route
  • Evaluate legal AI task fit using predeclared gold/error criteria, blind product mapping, observed grading limits and changed-version retest needs
  • Analyze positive/null-set validation, joint recall uncertainty, custodian weighting and scope changes; draft ESI language that reports evidence without unsupported guarantees
  • Evaluate privilege/log quality and exhibit authentication plans, distinguishing waiver orders, provenance, operative evidence rules and pending proposals
  • Evaluate clause tiers, document type, amendment precedence and diligence sampling; preserve confidentiality when designing a precedent bank
  • Analyze and test matter access across direct retrieval, derived objects, shared spaces and stale permission feeds without treating technical isolation as a conflict-law decision
  • Evaluate vendor data flows, client restrictions and specific-consent needs; distinguish historical privilege/work-product holdings from a blanket enterprise safe harbor
  • Design an observable supervision, reasonable-fee and bounded-intake recommendation with a feasible budget, exception owners and changed-evidence revision

Syllabus

6 modules · 21 lessons · about 25 hours

Module 1: The KM Attorney's Citation-Verification Gate Before Every Court Filing

Analyze source and proposition defects, then commission a logged local filing workflow without converting it into a universal statutory checklist.
3 lessons
  1. ABA Formal Opinion 512, FRCP 11 and Rule 3.3 as Design Requirements for a Filing Workflow
  2. Designing the Gate: Citation Extraction, Citator Checks, Proposition Support and a Sign-Off Log
  3. Lab: Running the Gate on a Synthetic Motion Brief With Five Planted Citation Defects
  • Decision Lab · 12 minThe amended paragraph at 5 p.m.Commission a specific evidence strategy, absorb a changed record and choose a defensible bounded recommendation with persistent resource consequences.

Module 2: The Legal Innovation Lead's Blinded Evaluation Set for Choosing a Platform

Replace demo-driven buying with matter-realistic tasks, gold answers, blinded grading and retesting after vendor model changes.
3 lessons
  1. What Is Being Compared: Research Platforms, Firm-Wide Platforms and Enterprise Assistants as of November 2026
  2. Gold Answers, a Fatal-Error Severity Rubric and Blinded Grading Under Rules 1.1 and 5.3
  3. Lab: Building a 12-Task Evaluation Set and Grading Two Anonymized Tools
  • Decision Lab · 12 minThe model version changes after gradingCommission a specific evidence strategy, absorb a changed record and choose a defensible bounded recommendation with persistent resource consequences.

Module 3: The Litigation-Support Manager's Defensible Generative Review

Interpret both validation samples and concentrated misses; preserve privilege/log and exhibit-foundation limits when review criteria change.
4 lessons
  1. Generative First-Pass Review: Criteria Prompts, Version Records and a Develop-Validate-Apply Workflow
  2. Lab: Recall, Elusion and a Biased Custodian in 2,000 Synthetic Emails, Then the ESI Protocol Paragraphs
  3. AI Privilege Screening and Privilege-Log Entries Under FRCP 26(b)(5)(A) and FRE 502(b) and (d)
  4. A Suspected AI-Altered Exhibit: An Authentication Plan Under FRE 901 and the Status of Proposed Rule 707
  • Decision Lab · 12 minThe insurer request changes the frameCommission a specific evidence strategy, absorb a changed record and choose a defensible bounded recommendation with persistent resource consequences.

Module 4: In-House Counsel's Contract Playbook and the M&A Associate's Diligence Grid

Make negotiating positions machine-usable for AI review in Word, and QC bulk data-room extraction before anything is marked no issue.
4 lessons
  1. Turning Negotiating Positions Into a Clause-Level NDA and MSA Playbook With Escalation Tiers
  2. Lab: Grading AI Redlines on Synthetic NDAs With a Residuals Clause, One-Way Confidentiality and an Uncapped Indemnity
  3. Data-Room Diligence Grids: Column Questions, OCR Failures, Amendments and Sampling QC
  4. Scoping a Precedent-Bank Drafting Assistant Without Leaking Other Clients' Terms Under Rules 1.6, 1.8(b) and 1.9(c)
  • Decision Lab · 12 minThe last amendment changes the gridCommission a specific evidence strategy, absorb a changed record and choose a defensible bounded recommendation with persistent resource consequences.

Module 5: The Conflicts Lead and Firm Counsel: Ethical Walls, Vendor Diligence and Privilege Exposure

Keep walled matters out of AI retrieval, approve or reject AI vendors on their actual terms, and manage privilege risk from client and lawyer AI use.
4 lessons
  1. Permission-Aware Retrieval: Enforcing Ethical Walls and Lateral Screens in a Firm AI Platform
  2. Lab: Red-Teaming Matter Permissions for Six Users and Eight Matters
  3. AI Vendor Diligence: Retention, Training Use, Outside Counsel Guidelines and Specific Client Consent
  4. Privilege and Work Product After United States v. Heppner and Warner v. Gilbarco
  • Decision Lab · 12 minThe retention terms change after the demoCommission a specific evidence strategy, absorb a changed record and choose a defensible bounded recommendation with persistent resource consequences.

Module 6: The Practice-Group Leader, Billing Partner and Legal Ops Manager: Supervision, Fees and Intake

Connect supervision records, actual-time billing and bounded intake controls; defend and revise the selected committee evidence commission.
3 lessons
  1. From Policy to Supervision: A Risk-Tier Table Under Rules 5.1 and 5.3 and the Lesson of Johnson v. Dunn
  2. Billing AI-Assisted Work: Time Entries, Tool Costs and Flat Fees Under Rule 1.5, ABA 512 and State Opinions
  3. A Least-Privilege Intake Agent: Routing Requests Into CLM Without Misrouting a Subpoena or Obeying an Injected Instruction
  • Decision Lab · 12 minThe attachment has no readable textCommission a specific evidence strategy, absorb a changed record and choose a defensible bounded recommendation with persistent resource consequences.
  • Capstone simulation · 32 minThe Tillman committee packet after two changesCarry A1–A8 through a model change and a terms/access change, price selected evidence commissions, and defend an explicit continue, narrow, hold or next-cycle recommendation.

Exam and certificate

The exam unlocks once you have completed every lesson and played each Decision Lab to an ending. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Thomson Reuters, LexisNexis, Harvey, Legora, Relativity, Everlaw, Litera, Spellbook, Intapp, Ironclad, Icertis, Microsoft, OpenAI, or Anthropic. Product and company names are trademarks of their respective owners.

More in AI in Professional Services

All 19 courses in this track
pro-001 Free intro Available

AI in Professional Services: The One-Hour Briefing

A free, task-by-task hour on AI in law, accounting, tax, audit, recruiting and consulting. Each lesson follows one named role through one real job, such as verifying citations in a research memo, testing journal entries or checking a recruiting shortlist for adverse impact, and ends with a short exercise on synthetic data.

1 h · 9 lessons Free intro
pro-120 Basic Waitlist

AI for Accounting, Tax and Audit Professionals

AI for Accounting, Tax and Audit Professionals: a basic course in the AI in Professional Services track. Syllabus in preparation.

h · 0 lessons Join the waitlist