10 live days · Your work, in practice
Direct a Factory for a coherent content series.
Choose MasterCourse for all ten days and the Capstone that connects editorial, production and release-review proactive AI agent teams.
Your audience needs a reason to watch and a reason to trust you. Learn to write focused prompts for individual pieces, delegate recurring preparation to bounded proactive agents, and direct a Factory of proactive AI agent teams that supports a content series without replacing your voice.
Choose useful topics, distinguish verified information from personal experience, and keep scripts, visual choices and publishing decisions aligned. Protect audience trust while managing repeated production work.
What you learn
Learn to connect creator prompts and proactive production agents into a Factory of supervised proactive AI agent teams, with source-linked handoffs and creator approval before publication.
Build a Factory of proactive AI agent teams for content preparation. Use a Dot to coordinate continuing work across their handoffs and return source-linked drafts, changed claims and choices for the creator. Test changing inputs, blocked work and a later restart. The creator approves claims, disclosures, publication and audience communication.
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 Editorial Desk. Provide the audience question, approved sources, voice, sponsor rules, formats and review standard. Connect only the permitted research and production records; keep accepted sources and script decisions with the assignment.
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 drafts, changed claims and choices for the creator 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 creator approves claims, disclosures, publication and audience communication.
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 public or specifically permitted source material and cleared media. Keep private messages, audience identifiers and information about minors out of unapproved cloud assignments. The creator checks claims, sponsorship disclosures and permissions before publication; preparation does not authorize posting or messaging followers.
Publishing accounts, editing tools and audience data each need their own permissions. The Dot should prepare work in approved locations and return it for review rather than assuming access to every channel.
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 Creators, educators, influencers and personal-brand teams responsible for useful content, audience trust and a consistent production practice. 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.
Audience questions · Script purpose
Turn an audience need into a useful script.
- 1.1Define the audience question
- 1.2Compare honest hooks
- 1.3Draft the short script
Visual treatment · Short-video review
Make the first edit serve the message.
- 2.1Plan the shots and visuals
- 2.2Build the short edit
- 2.3Check the audience’s reading
Ideas · Recurring topic intake
Build a useful idea queue.
- 3.1Sort incoming topic ideas
- 3.2Handle duplicates and stale ideas
Research · Claims and corrections
Keep the evidence behind each piece current.
- 4.1Prepare a bounded research packet
- 4.2Recheck changed evidence
Scripts · Voice and series planning
Prepare scripts that belong in the same series.
- 5.1Draft the next script batch
- 5.2Apply review without flattening the voice
Production · Captions and adaptations
Keep edits and adaptations tied to the script.
- 6.1Prepare the edit requests
- 6.2Track returned edits and fixes
Publishing review · Learning loop
Prepare a release queue you can approve.
- 7.1Assemble the approval packet
- 7.2Use feedback to plan the next run
Factory · Series proactive AI agent teams
Give a content series a shared operating plan.
- 8.1Assign the series proactive AI agent teams
- 8.2Define the acceptance checks
Factory · Corrections across a series
Keep the proactive AI agent teams aligned when a claim changes.
- 9.1Run the series handoffs
- 9.2Propagate a factual correction
Factory · Approval and continued work
Approve the process for the next series.
- 10.1Refine the proactive AI agent team instructions
- 10.2Run a second sample batch
- 10.3Record the creator’s decision
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 01Turn an audience need into a useful script.
Begin with a supplied topic, audience questions and a small source packet. Use prompts to make one piece useful before planning a larger series.
- 1.1
Define the audience question
Sort the supplied questions into one clear viewer need. Write a brief describing what the piece should explain and what falls outside its scope.
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 focused audience and content brief.
- 1.2
Compare honest hooks
Prompt a few opening lines that match the actual value of the piece. Reject exaggeration, invented experience and promises the content cannot fulfill.
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 reviewed hook set with one selected opening.
- 1.3
Draft the short script
Write a short script from approved facts and clearly identified personal observations. Keep source references beside claims that require checking.
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 concise script with a claim-check list.
By the end of the day
A creator prompt set and a short script with a clear purpose.
Review checkpoint
Check that the opening earns attention through relevance and that every factual claim can be supported.
Day 02Make the first edit serve the message.
Use the script to explore a small visual treatment and short edit. Review the actual video for meaning, pacing and trust.
- 2.1
Plan the shots and visuals
Turn the script into a short shot outline. Explore a permitted Higgsfield visual treatment and distinguish illustrative generated material from records of real events.
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 shot outline and labeled visual reference set.
- 2.2
Build the short edit
Use approved assets to assemble a small CapCut example. Review the opening, transitions and captions against the script rather than letting effects drive the story.
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 short edited study with reviewed captions.
- 2.3
Check the audience’s reading
Watch the piece without relying on production notes. Check claims, caption errors, potentially misleading visuals and any sponsorship or permissions questions needing 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 corrected video study and publishing-review checklist.
By the end of the day
A reviewed short-video example and a checklist for the next piece.
Review checkpoint
The viewer should understand what is factual, personal or illustrative. Leave unresolved permissions and disclosure questions for the appropriate human review.
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 03Build a useful idea queue.
Create a proactive agent that checks approved audience-question exports or a submitted idea inbox on a schedule. Keep collection bounded and avoid gathering unnecessary personal data.
- 3.1
Sort incoming topic ideas
Have the proactive agent group supplied questions by audience need, relevance and connection to existing content. Keep a source link and avoid ranking by unsupported predictions of reach.
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 source-linked idea queue.
- 3.2
Handle duplicates and stale ideas
Run a second batch containing repeats and an outdated topic. Preserve prior decisions, flag stale evidence and stop unsupported suggestions for review.
Proactive agent practice. Create and test the content preparation proactive agent on one sample run. Name the role Editorial Desk and hand supported work to a Dot using approved research sources, selected scripts and a production review queue. 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
- An intake history with repeat handling and a review queue.
By the end of the day
A recurring topic-intake proactive agent that keeps useful ideas separate from unresolved suggestions.
Review checkpoint
Check that the queue reflects the audience brief rather than automatically rewarding provocative wording.
Day 04Keep the evidence behind each piece current.
Use a proactive research agent to prepare source notes for approved topics. It should retain evidence and surface conflicts, not treat a generated answer as verification.
- 4.1
Prepare a bounded research packet
Have the proactive agent summarize an approved source set for a chosen topic. Retain links, dates and the exact claims each source supports; separate unknowns.
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 claim-to-source research packet.
- 4.2
Recheck changed evidence
Introduce a newer source that contradicts an earlier statement. Run the check again, mark affected scripts and pause their progress until the creator resolves the claim.
Proactive agent practice. Connect the permitted research sources and confirm when the proactive role checks them. Introduce a changed fact; return the source date and affected claims before an old statement reaches the next script.
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 correction queue with affected content identifiers.
By the end of the day
A proactive research agent that carries sources and corrections into later work.
Review checkpoint
Inspect the original sources. A citation next to a claim does not establish that the source supports it.
Day 05Prepare scripts that belong in the same series.
Give a scripting proactive agent a small approved topic batch, your voice guide and the accepted research packets. Let it prepare drafts while preserving editorial control.
- 5.1
Draft the next script batch
Have the proactive agent prepare a bounded set of scripts with a specific viewer question, source-backed points and a suitable action. Link each draft to its research packet.
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 small script batch with source references.
- 5.2
Apply review without flattening the voice
Feed creator notes into a revision run. Preserve accepted passages, limit attempts and flag contradictory feedback rather than averaging it into generic copy.
Proactive agent practice. Keep a proactive scripting role available for the approved series. Prepare a small batch from accepted research and voice instructions, bring choices to the creator and wait before dependent edit work.
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 script revision log with accepted and open decisions.
By the end of the day
A recurring scripting proactive agent with an inspectable history of voice and factual decisions.
Review checkpoint
Read the scripts aloud and check that they reflect your actual perspective and experience.
Day 06Keep edits and adaptations tied to the script.
Build a production coordinator proactive agent around CapCut editing and permitted Higgsfield assets. It should prepare and track the work without assuming universal control of either tool.
- 6.1
Prepare the edit requests
Have the proactive agent assemble accepted scripts, visual references, caption drafts and format instructions into a small production queue. Mark manual export and editing steps explicitly.
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 edit queue with source references.
- 6.2
Track returned edits and fixes
Register supplied exports and human review notes. Carry caption, factual and visual corrections into the next run, limiting retries and preserving the approved script version.
Proactive agent practice. Follow accepted scripts through the permitted production queue on an agreed schedule. Return captions, format adaptations and requested fixes against the right version, with publication still awaiting approval.
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 edit-review log and a current asset manifest.
By the end of the day
A production workflow that connects scripts, captions, visuals and returned versions.
Review checkpoint
Watch the actual exports. Check that adapting a piece has not removed a qualifier or changed its meaning.
Day 07Prepare a release queue you can approve.
Connect the proactive agents into a recurring content workflow. Use a small supplied performance report to practice learning from published work without promising growth or inventing causal explanations.
- 7.1
Assemble the approval packet
Have a proactive agent combine the current script, sources, exports and unresolved permissions or sponsorship questions. Mark each item ready for review, returned or held.
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 publishing-review queue with evidence links.
- 7.2
Use feedback to plan the next run
Give the proactive agent a supplied results snapshot and audience notes. Separate observed results from hypotheses, propose a small next test and pause any item with unresolved claims.
Proactive agent practice. Let Editorial 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 bounded follow-up plan and repeat-run record.
By the end of the day
A tested content workflow with a human release gate and a measured learning loop.
Review checkpoint
Confirm that the system neither publishes on its own nor claims that one metric proves why a piece performed as it did.
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 a content series a shared operating plan.
Organize multiple supervised proactive AI agent teams around a small series sample. Set a common audience promise, evidence standard and record of decisions.
- 8.1
Assign the series proactive AI agent teams
Define Research and Editorial, Production, and Release and Learning proactive AI agent teams with multiple proactive agent roles. Give each a deliverable and a clear limit on its authority.
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 series record.
- 8.2
Define the acceptance checks
Specify what makes a research packet usable, a script ready to edit and a video ready for human review. Name the return route for a failed check.
Proactive agent practice. Brief the Dot on Research and Editorial, Production and Release and Learning proactive AI agent teams. Test which work can run in parallel and which must wait for an editorial choice. 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 proactive AI agent team handoff table with acceptance criteria.
By the end of the day
A content Factory plan with distinct proactive AI agent team outputs and creator decision points.
Review checkpoint
Check that every proactive AI agent team can reject incomplete inputs and that no proactive AI agent team can invent the creator’s personal experience.
Day 09Keep the proactive AI agent teams aligned when a claim changes.
Run a small series packet through the proactive AI agent teams using prepared assets and accelerated handoffs. Test the expensive mistake: a corrected fact that has already reached scripts and edits.
- 9.1
Run the series handoffs
Pass accepted topic and research packets to Production, then send the returned edits to Release and Learning. Log accepted versions, returns and outstanding decisions.
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 series handoff log.
- 9.2
Propagate a factual correction
Change a supported claim after an edit is prepared. Locate affected scripts, captions and exports, stop their release and route the correction through each proactive AI agent team.
Proactive agent practice. Correct a fact after production has begun. Have the Dot identify affected scripts, edits and captions, coordinate the changes and return an account of what was rechecked. 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 correction run and revised content manifest.
By the end of the day
A tested correction path across multiple proactive AI agent teams and content versions.
Review checkpoint
Inspect every affected export for the old claim; a corrected script does not automatically correct a video.
Day 10Approve the process for the next series.
Refine the Factory and test a second small content batch. The Capstone tests a reusable production process rather than promising a finished campaign, audience growth or viral reach.
- 10.1
Refine the proactive AI agent team instructions
Use the first run’s failures to tighten source requirements, voice guidance, retry limits and escalation owners.
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 series operating guide.
- 10.2
Run a second sample batch
Process a prepared topic batch through all proactive AI agent teams. Compare the accepted sources, scripts, exports and unresolved decisions with the expected result.
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 creator’s decision
Review each sample piece for accuracy, voice, visual meaning and open questions. Approve, return or hold it and document who may publish.
Proactive agent practice. Run a second sample series and inspect sources, voice, disclosures and approval status together. Confirm that the creator decides what is published and that unused schedules are canceled. 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 creator approval record and next-series checklist.
By the end of the day
A tested Factory of creator-support proactive AI agent teams with source-linked work and human publishing control.
Review checkpoint
Another operator should be able to see what is approved, what remains held and why a piece cannot yet be released.
Days 8–10 · MasterCourse - Capstone
A Factory with clear handoffs.
Prepare a small, coherent content series and demonstrate how a correction moves through research, scripts, edits and final review.
Proactive AI agent team 1
Research and Editorial
- Proactive agent roles
- Topic, Source-check, Script
- Deliverable
- Accepted audience briefs, source-linked claims and reviewed scripts.
- Handoff
- Pass the editorial packet to Production; return unresolved factual or voice decisions to the creator.
- Acceptance check
- Claims have inspectable sources, uncertainty is retained and personal experience is not invented.
Proactive AI agent team 2
Production
- Proactive agent roles
- Edit-brief, Visual coordinator, Caption-review
- Deliverable
- Versioned video studies, caption records and an export manifest.
- Handoff
- Pass the returned assets and unresolved issues to Release and Learning; send meaning changes back to Editorial.
- Acceptance check
- Exports use the accepted script, captions have human review and illustrative visuals do not misrepresent evidence.
Proactive AI agent team 3
Release and Learning
- Proactive agent roles
- Manifest, Approval coordinator, Feedback
- Deliverable
- A human publishing queue and a bounded next-test plan.
- Handoff
- Return failures to their owning proactive AI agent teams and send accepted pieces to the creator for release.
- Acceptance check
- Source and asset versions agree; open claims, permissions and sponsorship questions remain blocked; observed results are separate from hypotheses.
Proactive AI agent teams share content identifiers, source versions and a creator decision log. Approved topic batches trigger work; scheduled checks handle updates and outstanding reviews. Retry limits and explicit handoffs control long-running work without assuming automatic editing or publication.
The creator retains responsibility for accuracy, personal claims, audience trust, permissions and publication. Proactive Agents prepare options and records; they do not publish or invent endorsements.
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 Research and Editorial, Production and Release and Learning as teams of proactive AI agents. The Dot carries the accepted script and source record through ongoing batches. Research and preparation may run in parallel; factual corrections return to affected outputs before creator approval.
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 short script, check its claims and review captions and visual choices through a video exercise.
Choose Intro for focused tasks such as audience questions, hooks, scripts and short-video planning.
Intensive
Learn to build and supervise proactive agents that maintain an idea queue, prepare source-backed scripts and coordinate edits, captions and approved format adaptations.
Choose Intensive when you can already brief a useful task and want recurring proactive agents to manage content preparation.
Create and test proactive AI agents for content preparation. Name a role such as Editorial Desk, then hand suitable work to OpenAI Dots to follow chosen topics and keep research, scripts and edit preparation moving between reviews. 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 creator prompts and proactive production agents into a Factory of supervised proactive AI agent teams, with source-linked handoffs and creator approval before publication.
Choose MasterCourse for all ten days and the Capstone that connects editorial, production and release-review proactive AI agent teams.
Build a Factory of proactive AI agent teams for content preparation. Use a Dot to coordinate continuing work across their handoffs and return source-linked drafts, changed claims and choices for the creator. Test changing inputs, blocked work and a later restart. The creator approves claims, disclosures, publication and audience communication.
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.
CapCut
Edit short videos, captions and selected audio/visual improvements.
Plan and access
CapCut Pro $19.99/month or $179.99/year in the official comparison guide.Region, app platform and promotions affect prices. Check rights for assets and output specifications before release.
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.
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 CapCut for a short edit and Higgsfield for a permitted visual study. Compare the opening, pacing, captions and relationship between the visuals and the factual script.
Intensive · Proactive Agents
Coordinate CapCut editing and Higgsfield visual preparation through approved assets, supported connections and explicit file handoffs. Proactive Agents retain source, script and export versions while people review the finished pieces.
MasterCourse - Capstone · Factory
Connect Research and Editorial, Production, and Release and Learning proactive AI agent teams. Trace a factual correction through scripts, captions and exports before the creator makes the publishing decision.
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.
Publishing accounts, editing tools and audience data each need their own permissions. The Dot should prepare work in approved locations and return it for review rather than assuming access to every channel.
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 focused tasks such as audience questions, hooks, scripts and short-video planning. Choose Intensive when you can already brief a useful task and want recurring proactive agents to manage content preparation. Choose MasterCourse for all ten days and the Capstone that connects editorial, production and release-review proactive AI agent teams.
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 public or specifically permitted source material and cleared media. Keep private messages, audience identifiers and information about minors out of unapproved cloud assignments. The creator checks claims, sponsorship disclosures and permissions before publication; preparation does not authorize posting or messaging followers.