10 live days · Your work, in practice
Direct a Factory for financial reporting.
Choose MasterCourse for the full ten-day pathway and exclusive three-day Capstone. Build a bounded management-reporting system with simulated reporting cycles.
Make the numbers easier to trace and the decisions easier to prepare. Build from a checked variance explanation to proactive agents that maintain a reporting cycle, then coordinate a Factory of proactive finance AI agent teams around a management pack.
Finance must explain what changed, what the evidence supports and which assumptions drive the next decision. The course connects source data, calculations and commentary so that a polished report never outruns its numbers.
What you learn
Learn to connect financial prompts, proactive reporting agents and a Factory of proactive AI agent teams for data, planning and management reporting, with finance approval before release.
Build a Factory of proactive AI agent teams for reporting preparation. Use a Dot to coordinate continuing work across their handoffs and return reconciliations, variance explanations and unresolved differences. Test changing inputs, blocked work and a later restart. Finance approves assumptions and release; preparation does not authorize payments, postings or trades.
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 Reporting Watch. Define the reporting period, approved extracts, calculation rules, reconciliation tolerance and finance approver. Connect only the approved data source; keep the accepted version and exceptions 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 reconciliations, variance explanations and unresolved differences 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. Finance approves assumptions and release; preparation does not authorize payments, postings or trades.
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 synthetic or organization-approved financial extracts with only the fields the exercise needs. Keep customer identifiers, account credentials and nonpublic reporting information out of unapproved cloud contexts. The exercise does not authorize payments, trades, ledger postings, filings or decisions about a person’s access to credit.
Access to a spreadsheet does not grant access to the accounting system behind it. Production connections and data residency must follow the organization’s approved setup; finance retains release authority.
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 CFOs, controllers, FP&A teams, accountants and finance operations professionals. 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.
Variance analysis · Source checks
Explain what changed
- 1.1Frame the financial question
- 1.2Calculate and explain a variance
- 1.3Prepare a reviewer’s brief
Scenario planning · Assumptions
Compare the choices behind a forecast
- 2.1Define the scenario drivers
- 2.2Compare the financial effects
- 2.3Write a decision-ready explanation
Data proactive agent · Period controls
Keep the reporting inputs current
- 3.1Define the data proactive intake agent
- 3.2Process a second reporting batch
Reconciliation proactive agent · Exception review
Catch differences before reporting
- 4.1Reconcile an accepted dataset
- 4.2Resolve or escalate exceptions
Variance proactive agent · Evidence requests
Keep commentary tied to the numbers
- 5.1Generate the recurring variance review
- 5.2Request support for explanations
Forecast proactive agent · Driver changes
Refresh scenarios within clear limits
- 6.1Build a driver-update proactive agent
- 6.2Test missing and extreme inputs
Proactive Reporting agent · Recurring cycles
Run the reporting cycle end to end
- 7.1Assemble the recurring management pack
- 7.2Test late data and recovery
Factory design · proactive Finance AI agent teams
Organize the reporting Factory
- 8.1Assign proactive AI agent team responsibilities
- 8.2Define the reporting handoffs
Factory coordination · Late changes
Carry changes across the proactive AI agent teams
- 9.1Connect the three proactive finance AI agent teams
- 9.2Reconcile a late-period correction
Factory operation · Finance approval
Release a pack you can defend
- 10.1Refine the operating rules
- 10.2Set the finance release checks
- 10.3Run the full reporting simulation
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 01Explain what changed
Use a sample profit-and-loss statement and budget to prepare one useful variance explanation. Keep the reporting period, units and calculation method visible.
- 1.1
Frame the financial question
Specify the reporting period, currency, units and decision the analysis should support. Identify the source tables and define what counts as a material variance for this exercise.
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 financial task brief with source and materiality assumptions.
- 1.2
Calculate and explain a variance
Prompt an analysis of the selected lines, then independently check the arithmetic in the workbook. Separate a measured variance from a possible explanation that still needs evidence.
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 reconciled variance table and draft commentary.
- 1.3
Prepare a reviewer’s brief
Write a concise summary of the main changes, their supported causes and outstanding questions. Attach source references and save the prompt for a comparable period.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A reviewed variance brief and reusable finance prompt.
By the end of the day
A financial explanation that a reviewer can trace back to the sample numbers.
Review checkpoint
Recompute material totals and percentage changes. Check period, currency and units before reviewing the narrative.
Day 02Compare the choices behind a forecast
Build one bounded scenario comparison. Show which assumptions change the result and which decisions the figures cannot make for you.
- 2.1
Define the scenario drivers
Choose a small set of sample revenue, cost or cash drivers. Record the base values, source and reason for changing each driver in the exercise.
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 scenario brief and assumptions register.
- 2.2
Compare the financial effects
Prompt a comparison of the base case and two alternatives. Check the formulas and avoid presenting illustrative assumptions as a prediction.
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 checked scenario table with driver sensitivities.
- 2.3
Write a decision-ready explanation
Explain the main tradeoffs, the evidence still needed and the limits of the comparison. Refine the prompt so the assumptions travel with the answer.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- Practice explaining a scenario and refining the prompts used to analyze it.
By the end of the day
Practice analyzing variances, comparing scenarios and explaining the results clearly to management.
Review checkpoint
Check that each scenario is internally consistent and that commentary distinguishes a calculation from a forecast assumption.
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 the reporting inputs current
Build a proactive agent that handles arriving sample data files. The output must be a consistent dataset, not an unexplained collection of spreadsheets.
- 3.1
Define the data proactive intake agent
Set a file-arrival trigger, accepted formats, account mapping and saved processing record. Require period, entity and currency fields before a file enters the reporting dataset.
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 data proactive intake agent specification and mapping table.
- 3.2
Process a second reporting batch
Run successive sample batches with a duplicate, changed column and missing period. Preserve processed-file state, retry a temporary failure once and stop malformed data for review.
Proactive agent practice. Create and test the reporting preparation proactive agent on one sample run. Name the role Reporting Watch and hand supported work to a Dot using an approved reporting extract and calculation definitions. 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 versioned reporting dataset, run log and intake exceptions.
By the end of the day
A data proactive intake agent that records what it accepted, rejected and changed.
Review checkpoint
Check that rejected files cannot silently enter totals and that a duplicate does not double-count a period.
Day 04Catch differences before reporting
Give a reconciliation proactive agent responsibility for checking each accepted data version. Its job is to identify differences and preserve evidence, not to make unexplained adjustments.
- 4.1
Reconcile an accepted dataset
Trigger checks when intake accepts a new version. Compare row counts, source totals and agreed control balances; retain the inputs and results for each run.
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 reconciliation proactive agent with a documented control report.
- 4.2
Resolve or escalate exceptions
Seed a missing account, rounding difference and unexplained balance. Apply approved tolerances, queue material exceptions and resume only after the reviewer records a disposition.
Proactive agent practice. Use the permitted connection or reviewed extract to revisit reconciliations on an agreed schedule. Return differences with source rows and version labels. Block affected reports until finance resolves unexplained differences.
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 reconciliation queue with decisions and rerun evidence.
By the end of the day
A repeatable reconciliation step that prevents unresolved differences from passing unnoticed.
Review checkpoint
Inspect the sample exceptions and confirm that the proactive agent does not invent a correcting entry or silently change source data.
Day 05Keep commentary tied to the numbers
Build a proactive agent that prepares a fresh variance review when reconciled results change. Require evidence before turning a possible cause into management commentary.
- 5.1
Generate the recurring variance review
Define the accepted-data trigger, comparison period, thresholds and commentary prompt. Preserve the baseline and flag changes from the previous accepted report.
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 variance proactive agent and a versioned commentary draft.
- 5.2
Request support for explanations
Introduce an unexplained movement and conflicting business notes. Queue a question for the responsible owner, mark provisional explanations and limit automatic revision attempts.
Proactive agent practice. Make variance commentary a continuing preparation role. When checked figures change, refresh affected explanations and separate calculations from causes that still need evidence. Bring the draft back for finance review.
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 variance evidence queue and revised draft commentary.
By the end of the day
Updated variance commentary with its supporting figures and open questions attached.
Review checkpoint
Check that narrative changes follow data changes and that unsupported causes remain questions rather than asserted facts.
Day 06Refresh scenarios within clear limits
Have a proactive agent recalculate an approved sample model when a driver changes. Keep the model, changed assumptions and resulting scenarios distinct.
- 6.1
Build a driver-update proactive agent
Specify which approved drivers may change, how updates arrive and which model version to use. Save the assumption set and recalculate through a permitted spreadsheet or analysis workflow.
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 forecast proactive agent and a scenario version register.
- 6.2
Test missing and extreme inputs
Introduce a missing driver and an implausible value. Stop dependent calculations, request a reviewer’s choice and compare the resumed run with the prior accepted scenario.
Proactive agent practice. Confirm when the proactive scenario role checks approved drivers and which changes need an alert. Change one driver and withhold another; return affected scenarios and missing inputs without inventing an assumption.
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 scenario workflow with exception and comparison reports.
By the end of the day
A forecast update process that makes the effect of each accepted assumption visible.
Review checkpoint
Recheck formulas and constraints. The proactive agent may prepare scenarios; it does not approve budgets, cash movements or investment decisions.
Day 07Run the reporting cycle end to end
Connect the proactive agents around a small management pack. Use several simulated periods to test ongoing execution without waiting for a real monthly close.
- 7.1
Assemble the recurring management pack
Configure a scheduled proactive reporting agent to collect accepted reconciliations, variance notes and scenarios. Retain source versions and show incomplete sections instead of substituting old results silently.
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 management-reporting proactive agent and a traceable sample pack.
- 7.2
Test late data and recovery
Delay a file, revise a driver and interrupt a run. Check saved state, bounded retries, duplicate prevention and the route for finance approval before a report is marked ready.
Proactive agent practice. Let Reporting Watch continue a cloud-capable assignment while you leave the chat. Inspect the result, block one input and test recovery. Then retire the responsibility: stop active delegates, cancel future schedules and retain the reviewed instructions. Recheck access and inputs before calling it back into service.
Suggested time for this task: 2 hours 20 minutes in Full Course; 1 hour 10 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A reporting-cycle test log and operating instructions.
By the end of the day
A tested cycle from data arrival to a finance review pack.
Review checkpoint
Confirm that every table and narrative uses the same accepted period and that stale or provisional inputs are visibly labeled.
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 08Organize the reporting Factory
Move from individual proactive agents to three coordinated proactive AI agent teams: Data and Control, Planning and Analysis, and Management Reporting. Give each a deliverable the next proactive AI agent team can accept.
- 8.1
Assign proactive AI agent team responsibilities
Group intake and reconciliation proactive agents into Data and Control; variance and scenario proactive agents into Planning and Analysis; and pack assembly and consistency proactive agents into Management Reporting. Define decision 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 finance Factory plan with proactive AI agent team outputs and responsibilities.
- 8.2
Define the reporting handoffs
Specify the dataset, control status, assumption version and exception status that must travel between proactive AI agent teams. Reject a handoff if its reporting period or control checks are incomplete.
Proactive agent practice. Give the Dot the finance proactive AI agent teams’ responsibilities, accepted input formats and review gates. Test how Data and Control passes an approved dataset to downstream analysis. 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
- Proactive AI agent team handoff contracts and a shared reporting record.
By the end of the day
A Factory design with clear ownership of data, analysis and the final reporting pack.
Review checkpoint
Check that each number in the intended pack has a source owner and that unresolved control exceptions block affected analysis.
Day 09Carry changes across the proactive AI agent teams
Run the Factory with an approved reporting snapshot, then introduce a late correction. Test whether its effect reaches analysis, narrative and presentation.
- 9.1
Connect the three proactive finance AI agent teams
Pass the accepted control dataset into analysis, then send the approved scenarios and commentary to reporting. Record acceptance, rejection and revision requests between proactive AI agent teams.
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 coordinated reporting run with proactive AI agent team handoff evidence.
- 9.2
Reconcile a late-period correction
Change a sample source amount after a draft pack exists. Mark dependent work out of date, rerun affected analysis and compare the revised pack before finance review.
Proactive agent practice. Introduce a late-period correction and have the Dot coordinate the affected proactive AI agent teams. Check that tables, scenarios and commentary all use the same corrected source version. 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
- An impact log and a reconciled second version of the pack.
By the end of the day
A reporting Factory that can explain what changed after a late correction.
Review checkpoint
Verify that tables, charts, commentary and scenario labels agree; no proactive AI agent team may treat the correction as approved merely because it arrived later.
Day 10Release a pack you can defend
Demonstrate a complete reporting cycle and document the controls needed for further use. Keep the classroom system separate from live accounting and payment operations.
- 10.1
Refine the operating rules
Use the failure tests to clarify each proactive AI agent team’s permissions, retry limits and record retention within the exercise. Define who resolves missing evidence and inconsistent assumptions.
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 finance Factory operating guide and exception ownership map.
- 10.2
Set the finance release checks
Specify the reconciliation, assumption, consistency and sign-off conditions for the final pack. Require a named finance owner to accept or return the work.
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 finance approval checklist and revision procedure.
- 10.3
Run the full reporting simulation
Process a sample reporting cycle with one late input and one returned section. Review how the prompts, proactive agent instructions and proactive AI agent team records support an accurate management report.
Proactive agent practice. Receive a complete sample management pack with reconciliation evidence and release status. The finance reviewer approves the result; verify that no payment, posting or external distribution was made. Retire the Factory’s active work and schedules, then rehearse a restart from its reviewed roles and a fresh approved input.
Suggested time for this task: 1 hour 40 minutes in Full Course; 50 minutes in Crash Course. Part of your class day, not extra time.- Practice result
- A demonstrated reporting Factory and a reviewed sample management pack.
By the end of the day
Practice running a reporting Factory and checking its calculations, handoffs and approval decisions.
Review checkpoint
Inspect the calculation trail and the release decision. A successful class simulation is not an audit opinion, a forecast guarantee or authorization to post transactions.
Days 8–10 · MasterCourse - Capstone
A Factory with clear handoffs.
Prepare a consistent management pack over recurring reporting cycles, with controlled data, transparent assumptions and a finance owner’s approval.
Proactive AI agent team 1
Data and Control
- Proactive agent roles
- Data intake, Mapping, Reconciliation
- Deliverable
- An accepted reporting dataset with control totals and unresolved exceptions.
- Handoff
- Pass the controlled dataset to Planning and Analysis; return rejected source files to their owner.
- Acceptance check
- The entity, period, currency and account mapping are explicit, and required control checks pass or have a recorded reviewer decision.
Proactive AI agent team 2
Planning and Analysis
- Proactive agent roles
- Variance, Scenario, Assumption-checking
- Deliverable
- Supported variance explanations and versioned financial scenarios.
- Handoff
- Send accepted analysis and assumptions to Management Reporting; send unexplained movements to the finance reviewer.
- Acceptance check
- Figures reconcile to the accepted dataset, formulas are checked and provisional explanations are marked.
Proactive AI agent team 3
Management Reporting
- Proactive agent roles
- Pack-assembly, Consistency, Release-checking
- Deliverable
- A management pack with a clear decision narrative and review record.
- Handoff
- Return inconsistent sections to their proactive AI agent team and present complete work to the finance owner.
- Acceptance check
- Tables, commentary and charts use the same source versions; the finance owner approves release.
Simulate successive reporting periods, late files and revised assumptions. proactive AI agent teams preserve accepted versions and exchange explicit acceptance or revision messages; exceptions remain assigned until resolved.
The finance owner approves assumptions and release. No classroom proactive agent posts accounting entries, moves money or executes financial decisions.
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 Data and Control, Planning and Analysis and Management Reporting as teams of proactive AI agents. The Dot maintains the accepted reporting version across cycles. Reconciliation failures block dependent analysis; late corrections return to every affected table and explanation before finance approves release.
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 variance commentary, check the numbers and explain a scenario with clear assumptions.
Choose Intro to improve individual analysis and explanation tasks using supplied sample tables. You review the calculations and direct each prompt.
Intensive
Learn to build and supervise data, reconciliation, variance, forecast and proactive reporting agents that process successive updates and route exceptions to a finance reviewer.
Choose Intensive when you can frame an analytical task and want proactive agents to execute recurring work within limits. The five days cover curriculum days 3–7.
Create and test proactive AI agents for reporting preparation. Name a role such as Reporting Watch, then hand suitable work to OpenAI Dots to revisit the reporting record at agreed intervals and prepare updates when accepted figures change. 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 financial prompts, proactive reporting agents and a Factory of proactive AI agent teams for data, planning and management reporting, with finance approval before release.
Choose MasterCourse for the full ten-day pathway and exclusive three-day Capstone. Build a bounded management-reporting system with simulated reporting cycles.
Build a Factory of proactive AI agent teams for reporting preparation. Use a Dot to coordinate continuing work across their handoffs and return reconciliations, variance explanations and unresolved differences. Test changing inputs, blocked work and a later restart. Finance approves assumptions and release; preparation does not authorize payments, postings or trades.
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.
Microsoft 365 Copilot
Research, analysis and document work in Microsoft 365; supported agent creation and workflows are listed.
Plan and access
Copilot Business $25.20/user/month on monthly subscription.A separate qualifying Microsoft 365 license is required. Advanced agent usage may be metered; do not imply every workflow is bundled.
Julius AI
Analyze supplied data, make charts and reports; paid plans expand credits and supported connectors.
Plan and access
Free plan; Plus $20/month or $16/month equivalent billed annually.Check relevant connector, scheduled-run and custom-agent allowances. Verify calculations against source data.
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 Microsoft 365 Copilot and Julius AI examples to examine sample actuals, budgets and drivers. Recalculate material results and keep assumptions visible in the financial explanation.
Intensive · Proactive Agents
Use Microsoft 365 Copilot and Julius AI outputs in recurring data, reconciliation and reporting tasks. Execute through supported automation or controlled sample runs, with calculations checked against the underlying workbook.
MasterCourse - Capstone · Factory
Pass reviewed Microsoft 365 Copilot and Julius AI outputs through the Data and Control, Planning and Analysis, and Management proactive Reporting AI agent teams. Test corrected inputs and finance approval without unrestricted access to live systems.
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.
Access to a spreadsheet does not grant access to the accounting system behind it. Production connections and data residency must follow the organization’s approved setup; finance retains release authority.
Before you choose
FAQ
Clear scope makes it easier to choose a course and arrive ready to work.
Which level should I choose?
Choose Intro to improve individual analysis and explanation tasks using supplied sample tables. You review the calculations and direct each prompt. Choose Intensive when you can frame an analytical task and want proactive agents to execute recurring work within limits. The five days cover curriculum days 3–7. Choose MasterCourse for the full ten-day pathway and exclusive three-day Capstone. Build a bounded management-reporting system with simulated reporting cycles.
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 synthetic or organization-approved financial extracts with only the fields the exercise needs. Keep customer identifiers, account credentials and nonpublic reporting information out of unapproved cloud contexts. The exercise does not authorize payments, trades, ledger postings, filings or decisions about a person’s access to credit.