10 live days · Your work, in practice
Direct a Factory for creative asset production.
Choose MasterCourse for all ten days, including the Capstone that connects briefing, production and quality review across proactive AI agent teams.
A strong image must survive the brief, the edit and the handoff. Learn to direct individual generative tasks, delegate recurring production coordination to bounded proactive agents, and run a Factory of proactive AI agent teams that prepares a controlled asset set for creative approval.
Translate a visual intention into editable, reviewable files while controlling references, revisions and delivery specifications. Preserve the craft decisions that cannot be settled by a filename or an automated check.
What you learn
Learn to connect creative prompts and proactive production agents into a Factory of supervised proactive AI agent teams, with versioned asset handoffs and human approval before release.
Build a Factory of proactive AI agent teams for asset preparation. Use a Dot to coordinate continuing work across their handoffs and return traceable asset versions, precise edit requests and outstanding defects. Test changing inputs, blocked work and a later restart. The creative owner approves image decisions and final delivery.
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 Production Desk. Provide the visual brief, licensed references, source versions, edit requirements and delivery specifications. Connect only permitted cloud records or hand over reviewed previews; identify native Adobe steps that still need a connected workstation.
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 traceable asset versions, precise edit requests and outstanding defects 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 creative owner approves image decisions and final delivery.
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 source images and references with appropriate rights and consent. Keep confidential client assets and identifying imagery out of unapproved cloud contexts. The class does not treat generated imagery as automatic rights clearance or permit release without creative approval.
A Dot does not automatically run every Adobe desktop application in its cloud computer. Cloud preparation can use approved references and exports; work that needs local Adobe software still depends on an available, connected computer.
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 Designers, photographers, editors and creative producers using Adobe tools to develop, refine and deliver visual assets. 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.
References · Concept choices
Turn a visual brief into a deliberate direction.
- 1.1Write the visual brief
- 1.2Compare concept prompts
- 1.3Choose the production direction
Layered edits · Output checks
Keep control of the edited image.
- 2.1Make a controlled edit
- 2.2Inspect the difficult details
- 2.3Prepare a checked export
Asset intake · Source records
Keep incoming production work organized.
- 3.1Build the asset request queue
- 3.2Handle incomplete or repeated inputs
Concept requests · Reference control
Keep exploration tied to the approved brief.
- 4.1Prepare the concept queue
- 4.2Track concept selection
Photoshop production · Revision notes
Give each edit a precise instruction.
- 5.1Prepare the edit packet
- 5.2Track revisions without losing the source
Variants · Delivery specifications
Prepare variants without losing the image.
- 6.1Build the variant instructions
- 6.2Check the returned variants
Quality review · Delivery readiness
Assemble a delivery packet you can inspect.
- 7.1Compile the delivery review
- 7.2Test a rejected asset
Factory · proactive Production AI agent teams
Connect the proactive AI agent teams around one asset brief.
- 8.1Assign the proactive production AI agent teams
- 8.2Set the handoff requirements
Factory · Revision coordination
Carry a creative change through the asset set.
- 9.1Run the production handoffs
- 9.2Reconcile a changed reference
Factory · Approval and repeat production
Approve the process for the next brief.
- 10.1Refine the proactive AI agent team instructions
- 10.2Process a second sample brief
- 10.3Record creative release
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 a visual brief into a deliberate direction.
Work from a supplied image brief and permitted references. Use Firefly to explore a small set of concepts, then make the choice explicit.
- 1.1
Write the visual brief
Describe composition, subject, lighting, intended use and constraints from the supplied assignment. Separate required reference qualities from optional stylistic choices.
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 visual brief and annotated reference sheet.
- 1.2
Compare concept prompts
Prepare a few Firefly prompts that vary one meaningful choice at a time. Record the reference inputs and prompt alongside each permitted output.
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 small concept comparison with a prompt record.
- 1.3
Choose the production direction
Inspect the concepts against the brief. Write a selection note that identifies what to retain, correct or reject before production.
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 selected concept and image-specific correction plan.
By the end of the day
A creative prompt set, reference sheet and justified visual direction.
Review checkpoint
Check the actual composition and artifacts. A convincing overall impression can conceal details that need correction.
Day 02Keep control of the edited image.
Carry one selected concept into Photoshop. Practice a bounded edit and inspect the working file as carefully as the exported image.
- 2.1
Make a controlled edit
Use a supplied image and a specific edit instruction in Photoshop. Preserve the original and organize the edit so the important choices remain reviewable.
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 layered working image with the original preserved.
- 2.2
Inspect the difficult details
Review edges, lighting, repeated textures and subject consistency at useful viewing scales. Prompt a correction checklist from your observations, then make the necessary adjustments.
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 image-specific review checklist and revised working file.
- 2.3
Prepare a checked export
Use the supplied delivery specification to prepare a sample export. Record size, format, version and source location; flag permissions questions for a person to resolve.
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 checked sample export and source-file record.
By the end of the day
A reviewed working image, export and reusable edit-review checklist.
Review checkpoint
Compare the export with the working file and brief. Keep visual acceptance and permissions separate from technical completeness.
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 production work organized.
Build a proactive intake agent that processes approved asset requests on arrival or on a schedule. Use a supplied manifest so it can identify sources without assuming access to private production systems.
- 3.1
Build the asset request queue
Have the proactive agent extract brief, references, required outputs and source locations. Associate every request with an asset identifier and recorded permission status.
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 structured asset queue with source references.
- 3.2
Handle incomplete or repeated inputs
Run a second batch with a missing reference and a duplicate request. Preserve prior status, pause incomplete work and set a limit on follow-up attempts.
Proactive agent practice. Create and test the asset preparation proactive agent on one sample run. Name the role Production Desk and hand supported work to a Dot using approved visual briefs, licensed references and a versioned review folder. 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 stopped exceptions and owners.
By the end of the day
A recurring proactive intake agent that keeps missing material visible.
Review checkpoint
Check that the proactive agent has not guessed a source, replaced a missing reference or treated unknown permissions as approval.
Day 04Keep exploration tied to the approved brief.
Use a concept coordinator proactive agent to prepare controlled Firefly requests and maintain their results. It should expose reference drift before more production work depends on it.
- 4.1
Prepare the concept queue
Have the proactive agent turn accepted briefs into a bounded set of prompt and reference requests. Record the intended variation and review criterion for each.
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 concept-request queue.
- 4.2
Track concept selection
Register returned concept files and human selection notes. Have the proactive agent stop rejected routes, preserve the decision history and request clarification when feedback conflicts.
Proactive agent practice. Give the proactive concept role the accepted brief and reference set. Confirm where it can obtain updates and when to report. Return distinct options for creative selection before further editing.
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 concept register with accepted routes and unresolved decisions.
By the end of the day
A concept coordinator that keeps exploration finite and decisions traceable.
Review checkpoint
Check selected images against the references yourself; the proactive agent’s record is not a substitute for art direction.
Day 05Give each edit a precise instruction.
Have an editing coordinator proactive agent prepare the work around Photoshop refinement. Supported connections may move records; image editing remains an explicit step when direct automation is unavailable.
- 5.1
Prepare the edit packet
Turn accepted concepts and reviewer notes into specific edit requests with source versions, areas to change and details to preserve.
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 Photoshop edit packet with acceptance checks.
- 5.2
Track revisions without losing the source
Register returned working files and previews. Have the proactive agent match them to the requested version, carry unresolved notes forward and stop repeated unsuccessful correction cycles.
Proactive agent practice. Keep edit instructions and production status current against named source versions. Use approved connections or reviewed exports; local Adobe work still needs its connected computer online. Ask for missing access instead of claiming the edit ran.
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 revision history linking source files, previews and decisions.
By the end of the day
An edit-coordination workflow that preserves the relationship between a request and its returned file.
Review checkpoint
Inspect layer organization and the actual visual change. Reject a polished preview if it hides an unreviewable source.
Day 06Prepare variants without losing the image.
Coordinate a small batch of derived assets with a proactive agent that reads the approved delivery matrix. Keep cropping and visual quality subject to human review.
- 6.1
Build the variant instructions
Have the proactive agent map one approved image to a supplied set of sizes and uses. Prepare crop, format and naming instructions while flagging requirements that conflict.
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 variant production matrix.
- 6.2
Check the returned variants
Compare exported-file records with the matrix and collect human crop and image-quality notes. Rerun after corrections, updating only affected items.
Proactive agent practice. Confirm when the proactive variant role checks for returned previews. Compare versions with the source image and delivery standard, tie defects to the right file and bring rejected work back into the revision queue.
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 variant-check report with a current export manifest.
By the end of the day
A repeatable variant workflow with technical checks and visual review kept distinct.
Review checkpoint
Check that an export matching the required dimensions still preserves the intended composition.
Day 07Assemble a delivery packet you can inspect.
Connect proactive agents for intake, concept, edit and variant around a small production batch. Make blocked files and incomplete decisions clear before any client delivery.
- 7.1
Compile the delivery review
Have a checking proactive agent join the brief, accepted references, current working files, exports and review notes. Identify stale versions and missing sign-offs.
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 delivery-readiness packet with source and export links.
- 7.2
Test a rejected asset
Introduce a technically valid export with a visual defect and a missing source file. Keep the item blocked until the correct evidence and human review are supplied.
Proactive agent practice. Let Production 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 production workflow and rejection-recovery log.
By the end of the day
A recurring production workflow with a clear queue for creative and delivery approval.
Review checkpoint
Verify that passing technical checks never bypasses a failed visual review or a missing source.
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 the proactive AI agent teams around one asset brief.
Design multiple supervised proactive AI agent teams for a small visual-production assignment. Define the records that must travel from briefing through production to delivery review.
- 8.1
Assign the proactive production AI agent teams
Define Brief and References, Image Production, and Quality and Delivery proactive AI agent teams with multiple proactive agent roles. Set their scope, shared asset identifiers and human owners.
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 production record.
- 8.2
Set the handoff requirements
Specify what each proactive AI agent team sends and what its recipient may reject. Include accepted references, source-file versions, review notes and export requirements.
Proactive agent practice. Give the Dot the three production proactive AI agent teams’ responsibilities, required inputs and acceptance checks. Separate cloud preparation from native editing steps that need a connected computer. 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 production handoff table with acceptance criteria.
By the end of the day
A creative-production Factory plan with distinct proactive AI agent team responsibilities.
Review checkpoint
A receiving proactive AI agent team must be able to reject a packet that is attractive but incomplete or based on the wrong brief.
Day 09Carry a creative change through the asset set.
Run a scoped image batch through the proactive AI agent teams using prepared files and accelerated reviews. Examine the effects of a changed reference after variants have been prepared.
- 9.1
Run the production handoffs
Pass an accepted brief from Brief and References to Image Production, then send the source and export packet to Quality and Delivery. Log acceptance and return 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
- An end-to-end production handoff log.
- 9.2
Reconcile a changed reference
Change a required visual detail and introduce a stale variant. Route corrections across the proactive AI agent teams, preserve the earlier record and block incompatible exports.
Proactive agent practice. Change an approved visual reference and have the Dot trace the affected assets and proactive AI agent teams. Review the returned revisions against both the new direction and the preserved source files. 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 asset manifest.
By the end of the day
A tested correction route across the proactive AI agent teams and their source and export files.
Review checkpoint
Inspect the images as well as the records; all affected variants must reflect the accepted decision.
Day 10Approve the process for the next brief.
Refine the Factory and test another small asset batch. The Capstone demonstrates a controlled production process, not a guarantee of a finished client campaign.
- 10.1
Refine the proactive AI agent team instructions
Use failed checks to tighten reference requirements, revision 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 production operating guide.
- 10.2
Process a second sample brief
Run a prepared brief through all proactive AI agent teams and compare the returned sources, exports and exceptions with the required delivery matrix.
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 results packet.
- 10.3
Record creative release
Review the sample asset set as the creative owner. Approve, return or hold each item and identify who may authorize actual delivery.
Proactive agent practice. Run a second sample brief through the Factory. Inspect the versions, visual checks and release status; confirm that a creative owner approves the final delivery. 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 human release record and next-brief checklist.
By the end of the day
A tested Factory of production-support proactive AI agent teams with reviewable working files and controlled delivery handoffs.
Review checkpoint
Another operator should be able to locate the current brief, accepted source, final variants and any decision that still blocks delivery.
Days 8–10 · MasterCourse - Capstone
A Factory with clear handoffs.
Coordinate one small visual-production batch from approved brief and references through editable working files to a reviewed export set.
Proactive AI agent team 1
Brief and References
- Proactive agent roles
- Brief, Reference coordinator, Source-record
- Deliverable
- An accepted visual brief, reference packet and delivery matrix.
- Handoff
- Send the accepted packet to Image Production; route missing sources and permissions questions to the owner.
- Acceptance check
- Required visual choices and output specifications are explicit; references have source records; unresolved questions are visible.
Proactive AI agent team 2
Image Production
- Proactive agent roles
- Concept coordinator, Edit-packet, Variant coordinator
- Deliverable
- A versioned working-file and preview packet with recorded creative decisions.
- Handoff
- Send current sources and exports to Quality and Delivery; return contradictory direction to Brief and References.
- Acceptance check
- The files match the accepted brief; revisions are traceable; source and export versions agree.
Proactive AI agent team 3
Quality and Delivery
- Proactive agent roles
- Manifest, Review-note, Approval coordinator
- Deliverable
- A delivery-readiness manifest and a human decision queue.
- Handoff
- Return defects to Image Production and send the reviewed packet to the creative owner.
- Acceptance check
- Required files are present; human visual reviews are recorded; rejected and unresolved assets remain blocked.
Proactive AI agent teams share asset identifiers, an approved reference version and a decision record. Changes reopen only affected requests. Bounded retries and named owners control stalled work, using supported connections or explicit handoffs of files and review notes.
The creative owner makes visual, permissions and delivery decisions. Proactive Agents coordinate the work and expose discrepancies; they do not replace pixel-level review or authorize client delivery.
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 Brief and References, Image Production and Quality and Delivery as teams of proactive AI agents. The Dot maintains a shared version record across ongoing requests, routes rejected variants to the right production step and waits for creative approval before delivery. Separate cloud preparation from native editing that needs an online workstation.
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 creative prompts, compare visual references and review a layered image while keeping track of your edits.
Choose Intro for focused image prompts, concept comparisons and controllable edits.
Intensive
Learn to build and supervise proactive agents that organize asset requests, prepare editing instructions and track versions, review notes and delivery checks.
Choose Intensive when you can frame a creative task and want recurring proactive agents to coordinate repeat production work.
Create and test proactive AI agents for asset preparation. Name a role such as Production Desk, then hand suitable work to OpenAI Dots to follow production requests and keep edit instructions, previews and revisions connected. 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 creative prompts and proactive production agents into a Factory of supervised proactive AI agent teams, with versioned asset handoffs and human approval before release.
Choose MasterCourse for all ten days, including the Capstone that connects briefing, production and quality review across proactive AI agent teams.
Build a Factory of proactive AI agent teams for asset preparation. Use a Dot to coordinate continuing work across their handoffs and return traceable asset versions, precise edit requests and outstanding defects. Test changing inputs, blocked work and a later restart. The creative owner approves image decisions and final delivery.
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.
Adobe Firefly
Generate and refine visual alternatives; premium image/video capabilities consume plan-specific credits.
Plan and access
Firefly Pro $19.99/month on the US annual plan, billed monthly.This plan includes Photoshop web/mobile, not a promise of desktop Photoshop. Required tools and credits must be checked separately.
Adobe Photoshop
Edit layered images and inspect generated additions for usable production assets.
Plan and access
Photoshop $22.99/month on the US annual plan, billed monthly.A subscription and sufficient generative access are separate from course tuition. Preserve editable source files and review visual defects.
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 Adobe Firefly for a small concept comparison and Photoshop for a controlled edit. Inspect references, edge quality, composition and the ability to revise the working image.
Intensive · Proactive Agents
Move permitted Firefly outputs into Photoshop production through supported downloads and handoffs. Proactive Agents track requests, source versions and review notes; manual editing remains explicit where required.
MasterCourse - Capstone · Factory
Coordinate Brief and References, Image Production, and Quality and Delivery proactive AI agent teams. Test a changed reference, a stale variant and a failed visual check before the creative owner releases the sample set.
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.
A Dot does not automatically run every Adobe desktop application in its cloud computer. Cloud preparation can use approved references and exports; work that needs local Adobe software still depends on an available, connected computer.
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 image prompts, concept comparisons and controllable edits. Choose Intensive when you can frame a creative task and want recurring proactive agents to coordinate repeat production work. Choose MasterCourse for all ten days, including the Capstone that connects briefing, production and quality review across 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 approved source images and references with appropriate rights and consent. Keep confidential client assets and identifying imagery out of unapproved cloud contexts. The class does not treat generated imagery as automatic rights clearance or permit release without creative approval.