10 live days · Your work, in practice
Direct a Factory across story, production and post.
Choose MasterCourse for the full ten-day progression and the Capstone that tests coordination across departments.
A script change travels through shots, schedules and the edit. Learn to produce useful first passes, delegate recurring planning work to bounded proactive agents, and direct a Factory of proactive AI agent teams that keeps a sample sequence coherent from scene to review.
Protect the creative intent while keeping departments working from the same script, references and decisions. Know which changes affect the plan and which need a director, producer or department lead to decide.
What you learn
Learn to connect film prompts and planning proactive agents into a Factory of supervised proactive AI agent teams, with version control, clear handoffs and production approvals.
Build a Factory of proactive AI agent teams for sequence preparation. Use a Dot to coordinate continuing work across their handoffs and return revision-linked impacts, department questions and outstanding post decisions. Test changing inputs, blocked work and a later restart. Department owners retain scheduling, resource and release decisions.
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 role Sequence Desk. Give it the approved script revision, scene identifiers, permitted references and department checks. Connect only the cleared script or planning workspace; retain the accepted revision and decisions between runs.
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 revision-linked impacts, department questions and outstanding post decisions 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. Department owners retain scheduling, resource and release decisions.
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
Use approved scripts, licensed references and cleared sample footage. Protect unreleased story material, performer information and private crew records. A Dot does not grant likeness or voice permissions, approve production commitments or release footage on behalf of the production.
Cloud coordination can work with approved script and planning exports. Editing, rendering or media stored only on a local workstation still requires that workstation and the necessary application access.
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 Filmmakers, producers, editors and production teams coordinating a story across development, planning and post-production. 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.
Script reading · Scene evidence
Build a scene breakdown you can trust.
- 1.1Draft concise coverage
- 1.2Extract scene requirements
- 1.3Write the shot brief
Shot exploration · Continuity
Compare shots against the story.
- 2.1Prepare reference-led shot prompts
- 2.2Review the visual tests
- 2.3Write the editorial handoff
Script revisions · Change history
Track what a script revision changes.
- 3.1Compare approved script versions
- 3.2Preserve the approved baseline
Breakdowns · Department dependencies
Turn changes into department questions.
- 4.1Update the affected breakdowns
- 4.2Route planning conflicts
Shot development · Review queues
Keep shot tests tied to their scene.
- 5.1Prepare the next shot requests
- 5.2Track returned tests and revisions
Post-production · Versioned handoffs
Prepare an edit handoff that survives revisions.
- 6.1Assemble the post packet
- 6.2Close the feedback loop
Continuity · Readiness checks
Test the sequence workflow under change.
- 7.1Run the sequence checks
- 7.2Pause and resume the workflow
Factory · Department proactive AI agent teams
Connect story, production and post proactive AI agent teams.
- 8.1Define the three proactive AI agent teams
- 8.2Define the department handoffs
Factory · Changes across proactive AI agent teams
Carry one revision through every proactive AI agent team.
- 9.1Run the proactive AI agent team handoffs
- 9.2Resolve a contradictory revision
Factory · Review and reuse
Approve the process for the next sequence.
- 10.1Refine the proactive AI agent team instructions
- 10.2Run a second scene packet
- 10.3Record the department decisions
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 01Build a scene breakdown you can trust.
Work with a short supplied script. Use prompts to prepare coverage and a breakdown, then inspect both against the actual scene.
- 1.1
Draft concise coverage
Prompt a synopsis, dramatic question and development notes from the supplied script. Keep observation separate from interpretation and cite scene references.
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 coverage draft with scene references.
- 1.2
Extract scene requirements
List characters, locations, props and visible action from one scene. Mark implied requirements separately from explicit script facts.
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 scene breakdown.
- 1.3
Write the shot brief
Turn the director’s supplied intent into a short shot brief covering story purpose, framing and movement. Leave technical and production choices open for 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 shot brief tied to the scene’s dramatic purpose.
By the end of the day
A checked script first pass and a practical brief for one short scene.
Review checkpoint
Check every required element against the script. Do not let plausible additions become production requirements.
Day 02Compare shots against the story.
Explore a few possible shots using Higgsfield and Runway examples. Judge them as planning material, with continuity and editability in view.
- 2.1
Prepare reference-led shot prompts
Use the approved scene brief to write prompts for a small shot comparison. Record character, location and camera references without assuming the models will preserve them.
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 prompt and reference sheet for the shot tests.
- 2.2
Review the visual tests
Compare permitted outputs for framing, movement, spatial logic and character continuity. Record where a visually appealing shot fails the intended scene.
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 shot comparison with accepted and rejected choices.
- 2.3
Write the editorial handoff
Draft a short handoff listing selected versions, intended sequence order and known continuity problems. Separate generated planning material from captured production footage.
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 versioned shot-selection and edit note.
By the end of the day
A reviewed shot plan with references and a clear handoff to an editor.
Review checkpoint
A person checks screen direction, performance intent and continuity; the prompt is not proof the shot meets the brief.
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 03Track what a script revision changes.
Build a revision proactive agent that checks approved script versions on an event or schedule. It should explain the difference without silently replacing the planning baseline.
- 3.1
Compare approved script versions
Give the proactive agent two supplied revisions and a scene identifier scheme. Have it produce a change report linked to the affected scenes and source passages.
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 scene-level revision report.
- 3.2
Preserve the approved baseline
Rerun the comparison with an unchanged file and a missing revision. Keep prior decisions, suppress duplicate reports and pause when the version sequence is unclear.
Proactive agent practice. Create and test the sequence preparation proactive agent on one sample run. Name the role Sequence Desk and hand supported work to a Dot using approved script revisions, breakdowns and post handoff records. 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 revision proactive agent with a baseline and exception log.
By the end of the day
A revision proactive agent that separates new script changes from already reviewed work.
Review checkpoint
Verify that a proactive agent cannot treat an unapproved draft as the production baseline.
Day 04Turn changes into department questions.
Use a breakdown proactive agent to update affected scene records after an accepted script change. Give it clear limits around scheduling, staffing and safety decisions.
- 4.1
Update the affected breakdowns
Have the proactive agent compare accepted revision notes with current character, location and prop records. Update only affected entries and keep the source of each proposed change.
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 revised scene-requirements register.
- 4.2
Route planning conflicts
Introduce an unavailable location and a changed prop requirement. Have the proactive agent prepare department questions, stop dependent tasks and revisit them after a recorded decision.
Proactive agent practice. Connect the approved planning record and set when the proactive role checks script impacts. Return changed breakdowns and department questions while preserving the baseline; scheduling and resource commitments remain with production.
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 dependency queue with department owners and blocked items.
By the end of the day
A breakdown workflow that reveals who needs to resolve each planning conflict.
Review checkpoint
Check that the proactive agent flags feasibility questions instead of inventing availability, costs or safe operating instructions.
Day 05Keep shot tests tied to their scene.
Build a proactive agent that prepares shot requests and tracks returned visual tests. Run creative tools through their supported interfaces; use reviewed exports when a direct connection is unavailable.
- 5.1
Prepare the next shot requests
Have the proactive agent turn accepted scene requirements and references into a small queue of shot prompts. Link every request to the current scene and review standard.
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 versioned shot-test queue.
- 5.2
Track returned tests and revisions
Register supplied Higgsfield or Runway outputs and reviewer notes. Limit resubmission attempts, retain rejected versions and pause when references conflict.
Proactive agent practice. Keep shot-request preparation attached to the accepted scene and reference record. Let the proactive role return new tests and revision requests at agreed checkpoints, with scene versions and decisions clearly linked.
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 shot-history record with bounded revision requests.
By the end of the day
A repeatable shot-development queue that preserves why each version was accepted or rejected.
Review checkpoint
Check visual continuity yourself. A proactive agent can coordinate the records without being able to judge every frame reliably.
Day 06Prepare an edit handoff that survives revisions.
Give an editorial coordinator proactive agent a supplied media manifest and review notes. Its task is to prepare consistent handoffs as approved shot versions change.
- 6.1
Assemble the post packet
Have the proactive agent collect accepted shot references, sequence order and outstanding notes into a post-production manifest. Flag missing media rather than substituting another 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 post packet with shot identifiers and current versions.
- 6.2
Close the feedback loop
Add time-referenced editorial notes to the sample packet. Route each note to its owner, carry unresolved notes forward and stop retries when the source media is unavailable.
Proactive agent practice. Maintain the post handoff as an ongoing coordination role. Check the permitted record on the confirmed schedule and return linked edit notes, media references and unresolved feedback; native editing and rendering require verified application access.
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 editorial issue log linked to the relevant shot versions.
By the end of the day
An editorial coordination proactive agent that maintains one inspectable history of media and notes.
Review checkpoint
Confirm that old notes do not attach to a different cut or a replacement shot without review.
Day 07Test the sequence workflow under change.
Connect the recurring proactive agents around a small sequence. Examine how they respond to a new script revision, a missing shot and a delayed review.
- 7.1
Run the sequence checks
Have a checking proactive agent compare script, breakdown, shot and post manifests. Produce a readiness report showing mismatched versions, missing decisions and unresolved continuity notes.
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 sequence-readiness report with evidence links.
- 7.2
Pause and resume the workflow
Withhold one approval, then supply a corrected packet. Verify that proactive agents retain state, update affected work and request human review before the sequence is marked ready.
Proactive agent practice. Let Sequence Desk 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 tested planning workflow and recovery record.
By the end of the day
A recurring scene-to-post workflow with visible stop conditions and a human review queue.
Review checkpoint
Inspect whether the workflow remains blocked when an apparently complete sequence uses the wrong script revision.
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 08Connect story, production and post proactive AI agent teams.
Design a Factory of multiple supervised proactive AI agent teams for one short sequence. Give each proactive AI agent team a real deliverable, then make its acceptance conditions explicit.
- 8.1
Define the three proactive AI agent teams
Assign Story and Continuity, Production Planning, and Post Coordination proactive AI agent teams with multiple proactive agent roles. Set scope, shared scene identifiers and the decisions reserved for department leads.
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 proactive AI agent team map and shared sequence record.
- 8.2
Define the department handoffs
Set acceptance checks for scene facts, planning dependencies and media manifests. Name the receiving proactive AI agent team and human owner for every returned item.
Proactive agent practice. Brief the Dot on Story and Continuity, Production Planning and Post Coordination proactive AI agent teams. Check the scene and revision identifiers at every handoff. 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 department handoff table with acceptance criteria.
By the end of the day
A film-support Factory plan connecting three proactive AI agent teams around one controlled sequence.
Review checkpoint
Every handoff must identify the script version and accepted inputs. Creative and production authority stays with people.
Day 09Carry one revision through every proactive AI agent team.
Run a small sequence packet through the Factory. Use accelerated checks to examine work that would ordinarily wait on departments over several days.
- 9.1
Run the proactive AI agent team handoffs
Have Story and Continuity issue an accepted breakdown, Production Planning return dependency decisions, and Post Coordination prepare the media and review packet. Record each acceptance.
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 complete sample sequence handoff log.
- 9.2
Resolve a contradictory revision
Change a scene requirement after shot selection. Trace the effect through production and post, stop incompatible work and reconcile conflicting notes before resuming.
Proactive agent practice. Introduce a contradictory script change after planning has begun. Have the Dot return the affected outputs and department questions for reconciliation before work advances. 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 coordinated revision run with explicit returns and reapprovals.
By the end of the day
A tested revision route across story, production and post proactive AI agent teams.
Review checkpoint
Check that every affected proactive AI agent team receives the change and that accepted work is not silently overwritten.
Day 10Approve the process for the next sequence.
Refine the Factory and run a second small scene packet. The Capstone tests production coordination; it does not promise a finished film or a production-ready schedule.
- 10.1
Refine the proactive AI agent team instructions
Use handoff failures to tighten source requirements, role boundaries, retry limits and escalation rules.
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 revised sequence operating guide.
- 10.2
Run a second scene packet
Process a prepared scene change through all proactive AI agent teams and compare the resulting manifests, exceptions and review requests with the expected outcome.
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 second-run evidence packet.
- 10.3
Record the department decisions
Review the packet as director, producer or department lead. Record what is approved, returned or held and who may authorize further production work.
Proactive agent practice. Run a second scene packet and inspect the full return against the approved revision. Record department decisions and verify that unfinished delegated work is stopped when the exercise closes. 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 signed-off sample decision record and next-sequence checklist.
By the end of the day
A tested Factory of film-support proactive AI agent teams with versioned handoffs and named human approvals.
Review checkpoint
Another operator should be able to identify the current script, selected shots, open issues and next required decision.
Days 8–10 · MasterCourse - Capstone
A Factory with clear handoffs.
Keep one short sequence coherent as approved script changes pass through planning, shot development and post-production preparation.
Proactive AI agent team 1
Story and Continuity
- Proactive agent roles
- Script-change, Breakdown, Continuity
- Deliverable
- A source-linked scene packet and continuity questions.
- Handoff
- Send the accepted scene packet to Production Planning; return unresolved creative choices to the director.
- Acceptance check
- The packet names the approved script version, distinguishes facts from suggestions and preserves continuity questions.
Proactive AI agent team 2
Production Planning
- Proactive agent roles
- Dependency, Shot-request, Asset coordinator
- Deliverable
- A checked dependency record and versioned shot requests.
- Handoff
- Pass accepted shot references and known constraints to Post Coordination; send missing decisions to department leads.
- Acceptance check
- Locations, props and shot references match the current scene; unresolved feasibility decisions are explicitly blocked.
Proactive AI agent team 3
Post Coordination
- Proactive agent roles
- Media-manifest, Editorial-note, Version-check
- Deliverable
- A sequence manifest and consolidated editorial review queue.
- Handoff
- Return media discrepancies to Production Planning and send the reviewed packet to the editor and director.
- Acceptance check
- Every selected shot has a current version and source; notes reference the correct cut; missing media remains visible.
Proactive AI agent teams share scene identifiers, an approved script baseline and a decision log. Revision events trigger affected work; bounded retries and named escalations control stalled handoffs. The class uses prepared scenes and accelerated runs, with manual media exports where required.
The director, producer and relevant department leads retain creative, feasibility, safety and production decisions. Proactive Agents prepare records and requests; they do not authorize a shoot or release.
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 Story and Continuity, Production Planning and Post Coordination as teams of proactive AI agents. The Dot follows the accepted revision through recurring preparation, identifies affected scenes and routes department questions before dependent work advances. Native editing or rendering still needs the verified production setup.
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 prompt for a scene breakdown, trace it to the script and review a shot brief through a short-scene exercise.
Choose Intro for individually directed script, scene and shot-planning tasks.
Intensive
Learn to build and supervise proactive agents that monitor approved revisions, update planning records and prepare continuity and post-production handoffs for review.
Choose Intensive when you can frame a useful prompt and want recurring proactive agents to coordinate the preparation around a sequence.
Create and test proactive AI agents for sequence preparation. Name a role such as Sequence Desk, then hand suitable work to OpenAI Dots to follow script changes and keep story, planning and post preparation in step. 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 connect film prompts and planning proactive agents into a Factory of supervised proactive AI agent teams, with version control, clear handoffs and production approvals.
Choose MasterCourse for the full ten-day progression and the Capstone that tests coordination across departments.
Build a Factory of proactive AI agent teams for sequence preparation. Use a Dot to coordinate continuing work across their handoffs and return revision-linked impacts, department questions and outstanding post decisions. Test changing inputs, blocked work and a later restart. Department owners retain scheduling, resource and release decisions.
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.
Higgsfield
Image and video generation for motion concepts, shot tests and creative alternatives.
Plan and access
Starter $19/month, billed annually, on the inspected pricing view.Starter includes selected models. Credits, model access and concurrency vary. Vendor excludes MCP/CLI, Canvas and Supercomputer from the website-only unlimited/free-generation benefits.
Runway
Generate and compare visual or motion studies, with paid credits and export features.
Plan and access
Free plan; Standard $15/month or $12/month billed annually.Generation length, resolution and model affect credit use. API/MCP availability is plan-specific; use reviewed exports if unsupported.
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 Higgsfield and Runway to explore a few shots from an approved scene brief. Compare framing, movement and continuity, then retain the prompts, references and selected versions.
Intensive · Proactive Agents
Feed permitted Higgsfield and Runway exports into a versioned shot and post workflow. Proactive Agents prepare requests and track review decisions through supported connections or manual media handoffs.
MasterCourse - Capstone · Factory
Have Story and Continuity, Production Planning and Post Coordination proactive AI agent teams reconcile a changed scene and its visual tests. Require department acceptance before the final human sequence review.
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.
Cloud coordination can work with approved script and planning exports. Editing, rendering or media stored only on a local workstation still requires that workstation and the necessary application access.
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 for individually directed script, scene and shot-planning tasks. Choose Intensive when you can frame a useful prompt and want recurring proactive agents to coordinate the preparation around a sequence. Choose MasterCourse for the full ten-day progression and the Capstone that tests coordination across departments.
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?
Use approved scripts, licensed references and cleared sample footage. Protect unreleased story material, performer information and private crew records. A Dot does not grant likeness or voice permissions, approve production commitments or release footage on behalf of the production.