What is this course about?
Conflicts checking is fundamentally an entity resolution problem, and firms miss conflicts because name variants and corporate families defeat string matching. This course covers resolution across corporate structures, searching unstructured matter history, prospective client confidentiality under Rule 1.18, and recording the clearance decision defensibly.
Who is this course for?
- Conflicts and new business intake staff
- General counsel of the firm and risk partners
- Law firm administrators
- Practice group leaders
What do I need before starting?
- Familiarity with your firm's conflicts process
- No technical background required
What will I be able to do afterwards?
- Frame conflicts checking as an entity resolution problem
- Resolve name variants, corporate families, and beneficial ownership
- Search unstructured matter history effectively
- Apply Rule 1.18 to prospective client information
- Record the clearance decision so it is defensible later
What does each module cover?
Why is conflicts checking an entity resolution problem?
35 minThe reframe that explains why string matching misses conflicts firms later regret.
Objectives
- Frame conflicts as entity resolution
- Identify why string matching fails
- Analyze how past misses actually occurred
Topics
Activity. Analyze a past conflicts miss and identify the resolution failure behind it.
How do you resolve corporate families?
50 minParents, subsidiaries, affiliates, and the beneficial ownership that connects apparently unrelated parties.
Objectives
- Resolve corporate family structures
- Trace beneficial ownership where required
- Handle structures that obscure relationships
Topics
Activity. Resolve a complex corporate family for a real prospective client.
How do you handle name variants?
45 minTransliteration, abbreviation, and the many ways the same party appears differently.
Objectives
- Handle transliteration and spelling variation
- Manage abbreviations and trade names
- Set match confidence thresholds
Topics
Activity. Test variant handling against a set of deliberately varied party names.
How do you search unstructured matter history?
50 minFinding conflicts in documents and correspondence, not just in the conflicts database.
Objectives
- Search unstructured matter content for parties
- Surface relationships the database does not record
- Balance recall against reviewer burden
Topics
Activity. Search unstructured matter files for parties absent from the conflicts database.
How do you make intake adaptive?
40 minIntake questionnaires that adapt to matter type and surface what conflicts checking needs.
Objectives
- Design intake that adapts to matter type
- Elicit the party information conflicts requires
- Reduce intake burden on the client
Topics
Activity. Design an adaptive intake flow for two different matter types.
What does Rule 1.18 require of prospective client data?
40 minConfidentiality obligations that attach before anyone is a client.
Objectives
- State Rule 1.18 obligations
- Handle prospective client information appropriately
- Avoid disqualification through intake
Topics
Activity. Review your intake process for Rule 1.18 exposure.
How do you handle imputation and screening?
40 minImputed conflicts and ethical screens, and what an AI system needs to know about them.
Objectives
- Apply imputation rules
- Implement ethical screens technically
- Verify screens are actually effective
Topics
Activity. Implement and test an ethical screen in the firm's systems.
Building the conflicts agent
50 minThe lab module: an agent that surfaces candidates for human clearance rather than clearing them.
Objectives
- Build an agent that surfaces rather than decides
- Record the human clearance decision
- Validate against known past conflicts
Topics
Activity. Validate the agent against ten known past conflicts and count what it would have caught.
What is the capstone project?
Conflicts agent validated against known past conflicts
Build a conflicts checking workflow with corporate family resolution, variant handling, unstructured matter search, adaptive intake, Rule 1.18 compliant handling, and ethical screening — validated against known past conflicts including missed ones.
Deliverable: A working conflicts agent with validation against historical conflicts and misses.
How are learners assessed?
- Agent must catch the past conflicts the firm missed
- Rule 1.18 review of the intake process with gaps remediated
- Ethical screen tested for actual effectiveness
What ships with the course?
Facilitator guide
Session-by-session running order, discussion prompts, and the questions that reliably derail a room.
Learner workbook
Exercises, checklists, and the templates each module's activity produces.
Hands-on lab environment
A sandboxed ibl.ai deployment so exercises run against real agents, not screenshots.
Assessment bank
Scenario questions and rubric criteria mapped to each stated learning outcome.
Source bibliography
Every primary regulation and standard cited on this page, linked and dated.
Which AI agents does this course use?
The hands-on modules run against agents already deployable on the ibl.ai platform for legal.
Where does the course material come from?
Every module is grounded in primary sources — the regulation, standard, or research itself, not a summary of it. Each was resolved at authoring time.
- Model Rules of Professional Conduct
American Bar Association
Rules 1.7, 1.9, 1.10 and 1.18 governing conflicts and prospective clients.
- CourtListener
Free Law Project
Disqualification case law researched in the imputation module.
- FinCEN
U.S. Treasury
Beneficial ownership reporting relevant to corporate family resolution.
- AI Risk Management Framework
NIST
Validation methodology for the historical conflicts testing.
Delivery notes
Binding guidance for anyone preparing and delivering this course.
- Module 8's validation against known misses is the assessment that matters. A conflicts agent that catches only the conflicts already caught adds nothing.
- The agent must surface candidates, never clear them. Make this structural — an automated clearance is a malpractice exposure no efficiency gain justifies.
- Module 6 is frequently overlooked and creates real disqualification risk. Intake processes that collect too much prospective client detail have disqualified firms.
- Use synthetic client and matter data. Real conflicts data cannot be used in a workshop even within the firm, because participants span practice groups.
- Module 7's screen verification should test technically, not review policy. Screens that exist on paper and not in the access control system are common.
Why run AI training on a platform you own?
You own the course, not a licence to it
Course content, learner data, and the platform run inside your perimeter — you own all the code and the data.
Model-agnostic delivery
Run the course's AI components on any LLM — Claude, GPT, Llama, Gemini, Command — and switch anytime.
No per-seat training licences
Usage-based or self-hosted, so cost tracks actual use rather than headcount.
Deploy anywhere
Cloud, private VPC, on-premise, or fully air-gapped — including for cohorts that cannot use public AI tools.
Frequently asked questions
What does the Client Intake and Conflicts Checking with AI course cover?
Conflicts checking is fundamentally an entity resolution problem, and firms miss conflicts because name variants and corporate families defeat string matching. This course covers resolution across corporate structures, searching unstructured matter history, prospective client confidentiality under Rule 1.18, and recording the clearance decision defensibly. It runs 4.5 hours across 8 modules across 8 modules, at intermediate level, and closes with a capstone: Conflicts agent validated against known past conflicts.
Who should take Client Intake and Conflicts Checking with AI?
It is written for Conflicts and new business intake staff, General counsel of the firm and risk partners, Law firm administrators, Practice group leaders. Prerequisites: Familiarity with your firm's conflicts process; No technical background required.
Can we run this course on our own infrastructure?
Yes. ibl.ai is model-agnostic and deploy-anywhere — cloud, private VPC, on-premise, or fully air-gapped — and you own all the code and the data. Cohort data, submissions, and any material learners upload stay inside your perimeter, which matters for legal teams that cannot send work to a public AI tool.
How do we get access to Client Intake and Conflicts Checking with AI?
Request access and we will set it up for your cohort — hosted by ibl.ai, or running against your own deployment. Tell us the group size and timing you need, and whether it should run inside your own perimeter.
How much does AI training for legal cost on ibl.ai?
There is no per-seat pricing — you pay for usage or self-host and pay only for the infrastructure, so a 5,000-person rollout does not cost 5,000 licences. 1.6M+ users across 400+ organizations run the platform this way, including NVIDIA, MIT, and Syracuse University.