10 live days · Your work, in practice
Direct a Factory of proactive legal AI agent teams.
Choose MasterCourse for all ten days, including the exclusive three-day Capstone. Build and test the full pathway on a bounded sample matter.
Turn a scattered matter file into work an attorney can inspect. Build useful first drafts, proactive agents that keep the matter record current, and a Factory of proactive AI agent teams that prepares a coordinated work product for attorney approval.
Legal work carries obligations to the client, the record and the decision-maker. The exercises preserve source references, jurisdiction, access boundaries and unanswered questions so that faster preparation does not conceal a weak premise.
What you learn
Learn to move from individual legal prompts to proactive matter agents and a Factory of coordinated proactive AI agent teams, with evidence handoffs, shared records and attorney approval before release.
Build a Factory of proactive AI agent teams for matter preparation. Use a Dot to coordinate continuing work across their handoffs and return source-linked changes, draft preparation and unresolved evidence questions. Test changing inputs, blocked work and a later restart. The attorney verifies authority and approves advice, communications and filings.
Proactive Agents · OpenAI Dots
Create it. Name it. Put it to work.
Create and test a proactive AI agent, give its role a stable name, and define what it may do. Then hand supported work to OpenAI Dots for one run or a continuing responsibility. Your Dot can keep working between conversations, using approved context and connected tools, and return results or ask for a decision without a fresh prompt for every step.
Give the role a name and a brief
Name the sample role Matter Watch. Give it the matter identifier, jurisdiction, approved source index and attorney review rules. Connect only the permitted sample folder or hand over a reviewed export; preserve the accepted version in its working record.
Choose a run or an ongoing responsibility
A Dot has its own cloud computer and browser. When the assignment, files and tools are available there, it can work while your phone or computer is off. Always-on means available to continue the responsibility; it may wait for a schedule, input or approval and remains subject to access and usage limits. Work using local files or applications still needs that connected computer online with the ChatGPT app open.
Set the return and the review rhythm
Return source-linked changes, draft preparation and unresolved evidence questions under the same named responsibility, with source versions and completed, waiting and blocked work clearly separated. Agree whether you need a scheduled report, an update on a material change, or a decision request. The attorney verifies authority and approves advice, communications and filings.
Agree when results are due, which changes deserve an alert and where to review them. Confirm recurring schedules, time zones and end dates; connecting an app alone does not enable monitoring. Test a changed input and a blocked step. Before retiring the responsibility, stop its delegated work and cancel its schedules separately. Keep the reviewed instructions so you can recheck access and resume when needed.
Connect only what the role needs
Practice with fictional or specifically approved, minimized matter material. Do not move privileged, confidential or identifying client information into a cloud workspace unless the firm has approved that use, access and retention. The attorney verifies authority, decides the legal position and approves client communications and filings.
Research databases and matter systems may require separate access. A Dot does not inherit permission to every client file or gain authority to file, advise or communicate for the attorney.
This practice is part of the existing proactive agent assignments and review time. It does not add class days or extend the hours shown in your booking.
The learning map
Work units by day
10 days of practical work for Attorneys, paralegals and in-house legal teams. Every unit below has an output and a review point.
Your learning plan: these are the tasks you will practice. The time suggested for each task is a guide; your booking shows the confirmed class dates and start and end times.
Matter intake · Facts and gaps
Make sense of the matter
- 1.1Define the matter and jurisdiction
- 1.2Separate facts from open questions
- 1.3Write the first-pass matter brief
Research · Client communication
Explain the issue clearly
- 2.1Frame the research question
- 2.2Draft a client explanation
- 2.3Refine your legal prompts
Proactive Intake agent · Access and state
Keep incoming documents organized
- 3.1Define the proactive intake agent’s job
- 3.2Process a second document batch
Chronology proactive agent · Source changes
Maintain a source-linked chronology
- 4.1Update events from new evidence
- 4.2Handle gaps and conflicting accounts
Proactive Drafting agent · Verification queue
Prepare drafts when the record is ready
- 5.1Build the proactive drafting agent
- 5.2Route uncertain claims for review
Evidence proactive agent · Discovery preparation
Keep evidence questions in view
- 6.1Organize questions and evidence
- 6.2Prioritize gaps for attorney review
Matter workflow · Recovery tests
Test the recurring matter work
- 7.1Run the proactive agents over several updates
- 7.2Challenge the stop and restart rules
Factory design · proactive AI agent team roles
Give the Factory clear responsibilities
- 8.1Assign roles across the proactive AI agent teams
- 8.2Define the shared matter record
Factory handoffs · Contradictions
Connect the proactive AI agent teams through review
- 9.1Pass work between the proactive AI agent teams
- 9.2Reconcile conflicting outputs
Factory operation · Attorney release
Approve a reusable matter system
- 10.1Refine proactive AI agent team instructions
- 10.2Set attorney approval gates
- 10.3Run and review the Factory
The work behind the map
Daily detail
Follow the work from its starting material to a result you can inspect. Each checkpoint gives you a reason to approve, revise or stop.
Intro
Days 1–2 · Tasks
Frame a useful first pass.
Direct one important task at a time. Give the prompt enough context, inspect the result and improve it before reuse.
Day 01Make sense of the matter
Use a supplied matter packet to produce one useful first-pass brief. Establish what the record supports before asking AI to interpret it.
- 1.1
Define the matter and jurisdiction
Identify the sample matter’s purpose, jurisdiction, audience and permitted sources. Write a scope note that makes the requested task and exclusions explicit.
Suggested time for this task: 1 hour in Full Course; 30 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A matter scope note with a defined question and source boundaries.
- 1.2
Separate facts from open questions
Prompt a facts list from the packet. Mark allegations, inferences and missing information separately, and attach the passage supporting each factual entry.
Suggested time for this task: 1 hour 20 minutes in Full Course; 40 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A source-linked facts list with allegations and open questions marked.
- 1.3
Write the first-pass matter brief
Combine the scope, facts and review standard in one reusable prompt. Check the resulting brief against the packet and correct unsupported statements.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A reviewed matter brief and the prompt that produced it.
By the end of the day
A matter brief that distinguishes the known record from the work still to do.
Review checkpoint
Trace material statements to supplied sources and check that the brief does not turn an allegation into an established fact.
Day 02Explain the issue clearly
Practice two individual assignments: prepare a research plan and draft an explanation a client can follow. Keep unresolved legal questions visible.
- 2.1
Frame the research question
Write a research prompt with the issue, jurisdiction and relevant facts. Identify authority to check in an appropriate legal research source rather than accepting generated citations at face value.
Suggested time for this task: 1 hour in Full Course; 30 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A research plan and an authority-verification checklist.
- 2.2
Draft a client explanation
Use the reviewed matter brief to draft a plain-language explanation. Distinguish what is known, what needs verification and what the attorney must decide.
Suggested time for this task: 1 hour 20 minutes in Full Course; 40 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A client explanation with review questions and source references.
- 2.3
Refine your legal prompts
Compare the draft and its citations with the underlying sources. Revise the instructions to address missing context, unsupported claims and language that overstates certainty.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- Practice refining a legal prompt and correcting a client explanation against its sources.
By the end of the day
Practice using prompts for intake, research and client explanations, then checking the results against the sources.
Review checkpoint
Confirm source accuracy, jurisdiction and audience fit. The exercise prepares drafts for attorney review, not legal advice for a live client.
Intensive
Days 3–7 · Proactive Agents
Keep recurring work moving.
Build proactive agents that run defined tasks over time. Give each one a trigger, working record and limits, then review its exceptions and results.
Build the proactive agent and test one complete run. Name its role, approve its inputs and connections, then hand suitable work to a Dot. Choose a single assignment or a continuing responsibility with clear reports, review points and a way to stop.
Day 03Keep incoming documents organized
Build a bounded proactive intake agent around the sample matter. A new permitted document should produce an inventory update or a clear exception without restarting the entire task.
- 3.1
Define the proactive intake agent’s job
Specify its prompt, input location, document-arrival trigger, permitted actions and saved matter index. Give it a duplicate check and a stop rule for restricted or unreadable files.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- A proactive intake agent specification and a permission-aware matter inventory.
- 3.2
Process a second document batch
Run a seeded batch, then a later batch containing a duplicate and an unreadable file. Preserve completed work, allow one safe retry and route the unresolved file to a reviewer.
Proactive agent practice. Create and test the matter preparation proactive agent on one sample run. Name the role Matter Watch and hand supported work to a Dot using an approved sample matter folder and source index. Define permitted actions and the return you expect; inspect the first result before giving it an ongoing responsibility.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- A tested proactive intake agent with a run log and exception queue.
By the end of the day
A repeatable document-intake proactive agent that records what arrived, what changed and what needs review.
Review checkpoint
Check that restricted inputs are not processed, duplicates do not create new matter facts and an unsuccessful retry remains visible.
Day 04Maintain a source-linked chronology
Make a chronology proactive agent respond to accepted inventory changes. Preserve both the current account and the evidence of why an entry changed.
- 4.1
Update events from new evidence
Define a trigger for newly accepted documents. Have the proactive agent extract dated events with passage references, retaining stable event identifiers and the last processed document version.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- A chronology proactive agent and a versioned event record.
- 4.2
Handle gaps and conflicting accounts
Introduce a document with a missing date and another with a conflicting account. The proactive agent should queue the conflicts for review and avoid silently replacing a supported entry.
Proactive agent practice. Connect the approved document source or supply a reviewed export. On a confirmed check, identify new events, changed dates and source versions. Preserve the accepted chronology; return conflicting evidence to the attorney.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- An annotated chronology and an evidence-conflict queue.
By the end of the day
A chronology that updates as permitted evidence arrives and preserves unresolved differences.
Review checkpoint
Sample events against the original passages; a newer document must not automatically outrank a better-supported source.
Day 05Prepare drafts when the record is ready
Connect an approved drafting request to the current matter record. The proactive agent may prepare and revise a draft; an attorney remains responsible for its use.
- 5.1
Build the proactive drafting agent
Define the approved-request trigger, required matter snapshot, drafting prompt and output structure. Save the source version used and stop when essential context is missing.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- A proactive drafting agent with a source-linked first draft and run record.
- 5.2
Route uncertain claims for review
Add a checking pass that flags unsupported propositions, authority needing verification and source changes affecting the draft. Allow a bounded revision, then escalate unresolved issues.
Proactive agent practice. Let the proactive drafting role prepare another pass when an approved record change makes one necessary. Require source references and uncertain propositions with the draft; polished language is not verified authority.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- A draft verification queue and a tested revision path.
By the end of the day
A drafting process that identifies its evidence and asks for review where the record is insufficient.
Review checkpoint
Verify authority in the appropriate source and inspect whether each flagged issue points to the affected passage.
Day 06Keep evidence questions in view
Use a recurring evidence-review proactive agent to prepare a bounded discovery packet. Each question should connect to an issue and the material that prompted it.
- 6.1
Organize questions and evidence
Configure a scheduled review of the accepted sample inventory and issue list. Produce source-linked evidence extracts, candidate discovery questions and a record of newly reviewed material.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- An evidence-review proactive agent and a draft discovery-preparation packet.
- 6.2
Prioritize gaps for attorney review
Introduce an omitted attachment and an ambiguous reference. Have the proactive agent rank the missing inputs by their effect on the assignment, stop unsupported conclusions and request attorney direction.
Proactive agent practice. Set the evidence-review cadence and the changes that deserve an alert. Test one missing document and one material change. Return evidence gaps to the attorney without contacting witnesses or seeking private records.
Suggested time for this task: 2 hours in Full Course; 1 hour in Crash Course. Part of your class day, not extra time.- Practice result
- A prioritized evidence-gap list with reasons and review owners.
By the end of the day
A recurring evidence packet that distinguishes useful extracts from unanswered questions.
Review checkpoint
Review relevance and source context. Do not let the proactive agent send requests, make privilege determinations or treat an omission as proof.
Day 07Test the recurring matter work
Run the proactive agents through several simulated update cycles. Test how they resume after interruption and how an attorney’s answer changes the next run.
- 7.1
Run the proactive agents over several updates
Connect proactive agents for intake, chronology, drafting and evidence through accepted records. Simulate successive document batches and inspect each run’s saved state, output and pending review.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A tested matter workflow with a shared index and run history.
- 7.2
Challenge the stop and restart rules
Withhold a required source, change permissions and interrupt a run. Test bounded retries, duplicate prevention, attorney escalation and resumption from the last accepted step.
Proactive agent practice. Let Matter Watch continue a cloud-capable assignment while you leave the chat. Inspect the result, block one input and test recovery. Then retire the responsibility: stop active delegates, cancel future schedules and retain the reviewed instructions. Recheck access and inputs before calling it back into service.
Suggested time for this task: 2 hours 20 minutes in Full Course; 1 hour 10 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A failure-test log, corrected instructions and a matter-proactive agent operating guide.
By the end of the day
A matter workflow that can continue between reviews without hiding uncertainty or losing completed work.
Review checkpoint
Every test should show who owns the exception, which work may continue and what must wait for attorney direction.
MasterCourse - Capstone
Days 8–10 · MasterCourse only · Factory
Direct a Factory of proactive AI agent teams.
Coordinate multiple supervised proactive AI agent teams around a larger outcome. Define what each proactive AI agent team delivers, how work changes hands and where you approve the result.
Build a Factory of proactive AI agent teams around a shared outcome. Give each team accepted inputs, a named responsibility and a clear handoff. A Dot can coordinate continuing work and delegate bounded runs; each role does not need a separate personal Dot.
Day 08Give the Factory clear responsibilities
Scale the sample matter into a coordinated preparation assignment. Build separate Matter Intelligence, Work Product and proactive Review AI agent teams, each containing proactive agents with defined jobs.
- 8.1
Assign roles across the proactive AI agent teams
Map proactive agents for intake, chronology and evidence to Matter Intelligence; proactive agents for research, drafting and synthesis to Work Product; and source-checking and release-checking proactive agents to Review. Define each proactive AI agent team’s output.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A Factory plan with proactive AI agent team roles, deliverables and attorney decision rights.
- 8.2
Define the shared matter record
Specify the records proactive AI agent teams may read or change, the approved source snapshot and the form of a review request. Add completion and acceptance criteria before a proactive AI agent team may pass work onward.
Proactive agent practice. Give the Dot a coordination brief for the three proactive AI agent teams: accepted inputs, required source references, destinations and attorney decision points. Test one handoff before allowing dependent work to continue. Give each role a stable name and decide which responsibilities continue between cycles.
Suggested time for this task: 2 hours 20 minutes in Full Course; 1 hour 10 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A shared-record plan and explicit proactive AI agent team handoff contracts.
By the end of the day
A Factory plan for multiple supervised proactive AI agent teams working toward one matter deliverable.
Review checkpoint
Check that every output has a receiving proactive AI agent team, a source version and an acceptance condition; no proactive agent may expand its access or release authority.
Day 09Connect the proactive AI agent teams through review
Run the proactive AI agent teams on a bounded sample assignment and introduce a late piece of evidence. Test how a change reaches every affected deliverable.
- 9.1
Pass work between the proactive AI agent teams
Send an accepted evidence bundle from Matter Intelligence to Work Product, then route the draft and source map to Review. Preserve a shared assignment ID and return rejected work to its owner.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A tested handoff plan between proactive AI agent teams, with acceptance and revision records.
- 9.2
Reconcile conflicting outputs
Seed a contradiction between a chronology entry and a draft claim. Trace it to the sources, pause affected work and request an attorney’s resolution before the proactive AI agent teams revise their outputs.
Proactive agent practice. Introduce late evidence after a draft has moved to review. Have the Dot identify affected outputs, return the change to the responsible proactive AI agent team and collect a reconciled version without erasing the earlier record. Check that waiting work resumes only after the required input or decision is accepted.
Suggested time for this task: 2 hours 20 minutes in Full Course; 1 hour 10 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A conflict log for the proactive AI agent teams and a corrected matter packet.
By the end of the day
A connected Factory that returns incomplete work and carries corrections across proactive AI agent team boundaries.
Review checkpoint
Check that a source correction reaches the chronology, research notes and draft, rather than being fixed in only one document.
Day 10Approve a reusable matter system
Practice running the complete Factory through short update cycles. Test its operating rules, review its results and identify what needs further evaluation before use on a real matter.
- 10.1
Refine proactive AI agent team instructions
Use the handoff tests to tighten each proactive AI agent team’s instructions, permitted actions, saved state and escalation rules. Record the limits of the classroom build.
Suggested time for this task: 1 hour in Full Course; 30 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- Reusable proactive AI agent team instructions and a limitations register.
- 10.2
Set attorney approval gates
Define who may approve sources, resolve conflicting evidence and release a work product. Make rejected work return to its owner with a reason and revision request.
Suggested time for this task: 1 hour 20 minutes in Full Course; 40 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- An attorney approval plan with explicit release conditions.
- 10.3
Run and review the Factory
Simulate a new document batch and a returned draft. Run the proactive AI agent teams through acceptance, revision and final human review. Check how the prompts, proactive agent instructions and shared records support each handoff.
Proactive agent practice. Run a second sample matter cycle and inspect the complete return: accepted sources, draft, unresolved questions and approval status. Confirm that no communication or filing occurred and stop remaining delegated work and schedules. Retire the Factory’s active work and schedules, then rehearse a restart from its reviewed roles and a fresh approved input.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A demonstrated legal Factory, reviewed sample packet and operating guide.
By the end of the day
Practice running a legal Factory from source intake to attorney review, and identify what needs more testing before use in practice.
Review checkpoint
Confirm source traceability and human release controls. The classroom demonstration does not establish suitability for a live matter or replace attorney judgment.
Days 8–10 · MasterCourse - Capstone
A Factory with clear handoffs.
Prepare a source-linked matter work product as the evidence changes, coordinating several proactive AI agent teams while an attorney controls scope and release.
Proactive AI agent team 1
Matter Intelligence
- Proactive agent roles
- Intake, Chronology, Evidence
- Deliverable
- A versioned facts, chronology and evidence bundle.
- Handoff
- Pass the accepted bundle and unresolved questions to Work Product; send material conflicts to the attorney.
- Acceptance check
- Each material entry has a source reference, a matter identifier and a clear status; missing evidence is explicit.
Proactive AI agent team 2
Work Product
- Proactive agent roles
- Research-planning, Drafting, Synthesis
- Deliverable
- A draft explanation or matter brief with its research and source map.
- Handoff
- Send the draft and supporting record to Review; return missing-input requests to Matter Intelligence.
- Acceptance check
- The draft matches the approved scope, identifies its source snapshot and marks propositions awaiting verification.
Proactive AI agent team 3
Review
- Proactive agent roles
- Source-checking, Consistency, Release-checking
- Deliverable
- A checked matter packet and prioritized attorney review queue.
- Handoff
- Return defects to the responsible proactive AI agent team; send release-ready work to the attorney for decision.
- Acceptance check
- Cross-document conflicts are resolved or clearly escalated, and no release occurs without attorney approval.
Simulate successive document arrivals, a changed source and a returned draft. Preserve accepted records between runs; bound retries and pause only the work affected by an unresolved exception.
The attorney approves scope, resolves legal and evidentiary questions and authorizes any external use. Classroom work uses supplied or permitted sample material.
The Capstone builds and tests a supervised prototype with sample cycles, revisions and exceptions. Longer projects continue beyond class; three days do not imply completion of a full production program.
A Factory that can carry work forward
Coordinate Matter Intelligence, Work Product and Review as teams of proactive AI agents. The Dot follows one approved matter record across their handoffs, returns conflicting evidence to the responsible team and holds dependent work for attorney review. Keep the Factory available for later evidence updates, with the matter’s access and retention limits still in force.
Keep the approved brief, source versions and decisions in the shared handoff record. Notes help preserve context; they do not replace a checked record. Test a second cycle, a blocked handoff and recovery. Retire the Factory by stopping active delegates and future schedules; retain the reviewed roles for a later restart.
Your time commitment
How long is each class day?
You attend 10 live classes, one on each scheduled day. Choose Full Course or Crash Course for all 10 days. The times below include breaks.
Full Course
6 hours per day
More time to practice, ask questions and review your work.
Suggested plan for one day
- Lessons and hands-on practice
- 4 hours
- Review and questions
- 30 minutes
- Lunch break
- 1 hour
- Two short breaks
- 15 minutes each
10 class days × 6 hours = 60 hours totalIncludes all scheduled breaks.
Crash Course
2 hours 30 minutes per day
The same topics in shorter classes, with prepared examples and less practice time.
Suggested plan for one day
- Lessons and hands-on practice
- 2 hours
- Review and questions
- 20 minutes
- One short break
- 10 minutes
10 class days × 2 hours 30 minutes = 25 hours totalIncludes all scheduled breaks.
Lunch, breaks and review time are already included in each day. The task times in Daily detail fit inside the practice time above. Your trainer may adjust the plan; the start and end times shown with your selected dates are the ones to follow.
Choose your starting point
One progression. Three choices.
Intro teaches individually directed prompts. Intensive puts recurring work into proactive agents. MasterCourse connects the whole pathway and adds the Factory Capstone.
Intro
Learn to write legal prompts, prepare a source-linked matter brief and check a client explanation against the evidence.
Choose Intro to practice individual research, analysis and drafting tasks. You direct each prompt and check each result; no technical background is required.
Intensive
Learn to build and supervise proactive agents for intake, chronology, drafting and evidence that process new inputs, preserve the matter record and bring exceptions to an attorney.
Choose Intensive when you can already frame a task and want proactive agents to carry out recurring work within defined limits. It covers five days, curriculum days 3–7.
Create and test proactive AI agents for matter preparation. Name a role such as Matter Watch, then hand suitable work to OpenAI Dots to keep the document inventory and chronology current as approved evidence arrives. Choose one run or a continuing responsibility, with approved connections, agreed reports and a clear way to pause or retire the work.
MasterCourse
Learn to move from individual legal prompts to proactive matter agents and a Factory of coordinated proactive AI agent teams, with evidence handoffs, shared records and attorney approval before release.
Choose MasterCourse for all ten days, including the exclusive three-day Capstone. Build and test the full pathway on a bounded sample matter.
Build a Factory of proactive AI agent teams for matter preparation. Use a Dot to coordinate continuing work across their handoffs and return source-linked changes, draft preparation and unresolved evidence questions. Test changing inputs, blocked work and a later restart. The attorney verifies authority and approves advice, communications and filings.
Intensive is a five-day purchase, not a seven-day bundle. The three-day Capstone is available only inside the ten-day MasterCourse.
Live guidance · Continued reference
Come prepared. Keep what you learn.
Bring a computer, a reliable connection and a work example you are authorized to use. Sample or sanitized material lets you practice without introducing confidential source files.
Practice with guidance
Work through the assignments live, compare results and use trainer feedback to refine your prompts, proactive agent instructions and review standards.
Revisit your classes
Students have access to recordings of their classes in the members portal.
Specialist tools · Separate subscriptions
Tools serve the assignment.
Two specialist tools chosen for practical fit and an established learning ecosystem. Claude, OpenAI, Gemini and Open Source options support the prompt and proactive agent work. Specialist examples connect it to your field.
CoCounsel Legal
Legal research, document comparison and drafting. Essentials does not include the full Legal plan’s Westlaw research features.
Plan and access
Published in-house starting prices: CoCounsel Legal $1,694.90/month; Essentials $340.85/month.Confirm the correct legal-content package and organization authorization; these are in-house starting examples, not a universal per-seat quote.
Gemini Notebook (formerly NotebookLM)
Source-linked organization and summaries of supplied files. Current vendor naming is Gemini Notebook.
Plan and access
Free access available; Google AI Pro $19.99/month.Confirm organization permissions, source limits and applicable plan. A source notebook is not a legal citator.
Do I need my own software access?
Yes. Arrange full access to the required features before class, including suitable paid plans, usage credits and organization permissions. Software costs are separate from tuition. Free access may not cover every exercise.
How these tools support your course
Intro · Tasks
Use CoCounsel Legal and Gemini Notebook examples to prepare a matter brief and a client explanation. Check authority in an appropriate legal research source; Gemini Notebook organizes supplied sources and does not replace that verification.
Intensive · Proactive Agents
Use permitted CoCounsel Legal and Gemini Notebook exports or sample documents as proactive agent inputs. Test recurring matter tasks through supported automation or a controlled simulation where direct integration is unavailable.
MasterCourse - Capstone · Factory
Coordinate Matter Intelligence, Work Product and proactive Review AI agent teams around permitted CoCounsel Legal and Gemini Notebook outputs. Test source changes, rejected handoffs and attorney release without assuming unrestricted autonomous access.
Vendor information checked September 29, 2026. Plans and limits can change. Proactive Agents use supported connections or approved exported inputs; specialist subscriptions do not imply universal proactive agent integration. Human approval remains part of publishing, releasing work and professional decisions.
OpenAI Dots · Proactive agents at work
Hands-on proactive agent and Dots work starts in Intensive. Check Dots availability, supported connections and your organization’s permissions before class. You authorize each app or browser session; Dots does not inherit all your logins. Subscriptions and usage charges are separate from tuition. Some specialist work needs a reviewed export or an online local application.
Research databases and matter systems may require separate access. A Dot does not inherit permission to every client file or gain authority to file, advise or communicate for the attorney.
Before you choose
FAQ
Clear scope makes it easier to choose a course and arrive ready to work.
Which level should I choose?
Choose Intro to practice individual research, analysis and drafting tasks. You direct each prompt and check each result; no technical background is required. Choose Intensive when you can already frame a task and want proactive agents to carry out recurring work within defined limits. It covers five days, curriculum days 3–7. Choose MasterCourse for all ten days, including the exclusive three-day Capstone. Build and test the full pathway on a bounded sample matter.
What does Factory mean?
A Factory coordinates supervised teams of proactive AI agents around a shared outcome. Each AI agent team has a defined responsibility, a deliverable and an acceptance check for the next handoff. You control permissions, review exceptions and approve release. The MasterCourse-only Capstone tests continuing cycles as well as individual runs.
Are recordings available?
Yes. Students can access recordings of their classes in the members portal.
How long is each class, and how many days do I attend?
This MasterCourse has 10 class days. Full Course lasts 6 hours each day, including lunch and two short breaks. Crash Course lasts 2 hours 30 minutes each day, including one short break. Choose one format for the whole course. Both cover the same topics; Full Course gives you more practice time. Check your selected dates for the exact start and end times in your time zone.
Which time zone will I see?
The class chooser detects your time zone automatically. Use Change time zone to select another location; the dates and hours update together.
Can Intro or Intensive tuition count toward MasterCourse?
The amount actually paid for Intro and/or Intensive can be credited once toward one MasterCourse enrollment within twelve months of each purchase. Intro and Intensive do not credit each other. No credit toward other programs, software or cash. Credit requests are reviewed against purchase records and eligibility; they are not an automatic checkout discount.
Full refund, transfer and credit policyWhat happens if I miss a day?
A missed day has a guaranteed place on the same curriculum day in a later cohort, free of charge, within twelve months of the original cohort's last scheduled day. After this window, new enrollment uses the then-published fee; day credits have no cash value and cannot buy a different curriculum day. An attended day may be repeated without charge within the same twelve-month window, subject to space. One free transfer of the whole seat or its unused days to a later cohort, in either published format, without a reason or a price increase, within twelve months of the original cohort’s last scheduled day. A day already consumed on one format is consumed on both; unused curriculum days are portable across dates and formats.
Full refund, transfer and credit policyWhat should I know before enrolling?
Full refund for a cancelled live program before its first scheduled session begins, including individual and group purchases and an approved MasterMind season. No refund after the purchased program starts, including dissatisfaction or absence, except for a session the provider fails to deliver. Statutory rights are unaffected. Partial attendance consumes the day under the published attendance rules. Read the full terms before choosing your class.
Full refund, transfer and credit policyWhen do I start using Dots?
Intro teaches individual tasks, clear prompts and review. Intensive teaches you to create proactive agents, test their work and hand supported responsibilities to OpenAI Dots. MasterCourse adds a Factory of proactive AI agent teams with shared records and coordinated handoffs.
Can the work continue after I close my phone or computer?
A Dot has its own cloud computer and browser. When the assignment, files and tools are available there, it can work while your phone or computer is off. Always-on means available to continue the responsibility; it may wait for a schedule, input or approval and remains subject to access and usage limits. Work using local files or applications still needs that connected computer online with the ChatGPT app open.
How do I stay in control over time?
Give the Dot and its assignments recognizable names, keep approved context current, and agree what deserves a report. It can surface missing input, access or decisions. To pause or retire work, check active delegates and saved schedules separately; pausing the main conversation does not stop them all. Review access and inputs before resuming.
What material can I use for the cloud exercises?
Practice with fictional or specifically approved, minimized matter material. Do not move privileged, confidential or identifying client information into a cloud workspace unless the firm has approved that use, access and retention. The attorney verifies authority, decides the legal position and approves client communications and filings.