Showrunner
gpt-6.1-solrun 1 Sep 2026
Instructions
Instructions — the case's current instructions
Hi, I need to create a modified Claude code for beginners session, like run sheet basically, run of show, that has the following modifications. So I'm going to upload a few different examples of things I've done in the past, just so you have them to work from. But basically, there's a few modifications for this one which make it unique. One is that this is only using Claude Cowork, so we should...
Hi, I need to create a modified Claude code for beginners session, like run sheet basically, run of show, that has the following modifications. So I'm going to upload a few different examples of things I've done in the past, just so you have them to work from. But basically, there's a few modifications for this one which make it unique. One is that this is only using Claude Cowork, so we should not be using Claude Code, either in the desktop app or in the terminal, because this team is non-technical. The team are all working in financial services slash accounting for a education company. So what kind of workplace education company called Brightmoor Education. So the sorry that spelled b the uh team is very busy and um doesn have a lot of like time to explore speculative use cases of ai they want this to be incredibly practical and based on their existing workflows. I'm uploading some transcripts from a call we had with them and also just some notes on what I think could work. Specifically, they're interested in... creating the dashboards and specifically they mean just making the information look visibly better like like creating a html dashboard in a nice kind of style from from existing say data that contained in Excel They also interested in doing financial analysis So more of a, you know, like, I guess, a cloud coworker would use Python to do the analysis and then maybe output the analysis in Excel or the input would be in Excel. And then the third thing was like making a PowerPoint where they update the PowerPoint template automatically using Claude Cowork so that they can do kind of weekly or monthly presentations on the data. So that's the goal, is to kind of make it very focused on that. I still want to keep the way that we introduce Claude Cowork, where we explain to it that the difference between Claude Cowork and ChatGPT is that it has access to the file system. It can run code. I think that important But maybe the ASCII image idea that I normally do where I ask it to create an ASCII image based on my location isn like that useful I think we need to make it more practical for them So maybe we use an Excel implementation instead. The assumption is... oh, so they use Snowflake, by the way, for all their data, and that is powered by NetSuite, which is our accounting software. I guess that's by Oracle. So when we create synthetic data, we'll be, for these tasks that we're going to demo, we'll be focused specifically on solving that, solving those problems. So like the shape of the tasks, the shape of the data should be like NetSuite shaped, if that makes sense. So make it very tight run down, make it very condensed and practical. No real like wider theory or like, hey, we're excited about AI things. I think these guys just want to get stuff done.
So yeah, let me know what the run should be.
some very specific asks in here
- definitely non-technical (claude cowork only + claude in excel)
- core focus on accounting/finance function
- use cases to demo: creating a dashboard, doing financial analysis, making a powerpoint
heavy focus on practical stuff rather than theory - they're just super busy and want to get stuff done, have heard from friends at other companies you can do it with claude
For accounting: put financials together, doing reconciliations, identifying trends in data sets, putting together repeatable compliance reports For planning & forecast: build financial models (make assumptions and pull & clean data from snowflake)create dashboards, and publish to executivesAutomate charts on slides
Brightmoor Education: practical finance work with Claude
Run of show · 3½-hour session + 30-minute buffer · Cowork and Claude in Excel only
The session follows one familiar job: turn a monthly NetSuite/Snowflake export into checked financials, an executive dashboard and an updated PowerPoint. No coding, speculative projects or broad AI presentation.
Designed for the 20–30 attendees described in the call: mainly accounting, payroll and bursar colleagues, with a small strategic finance group. Everyone uses the same synthetic education-finance data; nobody needs to bring live company data.
Run of show
Times are elapsed from the start. The four-hour booking includes the final 30-minute buffer, not four hours of content.
| Time | Segment | Facilitator runs | Participants do / checkpoint |
|---|---|---|---|
| 00:00–00:05 | Show the job we're finishing | Show a prepared Excel analysis, campus dashboard and three-slide monthly pack. “Today we'll make these from the same export, then practise updating them.” | Open the supplied workshop folder. No introductions round or AI theory. |
| 00:05–00:20 | First win: Excel in, Excel out | In the desktop app's Cowork area, give access to the workshop folder. Ask Claude to inspect the workbook and save a short Excel readout. Explain file access and behind-the-scenes code execution in two minutes. | Spend 10 minutes creating and opening their readout. Identify periods, campuses and a data-quality warning. The first result is a useful file, not an ASCII image. |
| 00:20–01:05 | Build 1: checked financial analysis | Demo 12 min: inspect the export, propose cleaning rules, approve a working copy, produce monthly/YTD actual-versus-budget financials and a payroll reconciliation. Switch to Claude in Excel to trace one variance to its source cells. | Build 25 min; review 8 min. Check revenue, payroll, non-payroll operating costs and EBITDA; find the largest variances and a trend. Confirm a seeded duplicate, mapping gap and reconciliation difference are flagged—not silently “fixed.” Save the checked workbook. |
| 01:05–01:15 | Break | Resolve access issues individually; keep a checked checkpoint workbook ready. | 10-minute break. |
| 01:15–01:55 | Build 2: a readable executive dashboard | Demo 8 min: turn the checked Excel summary into a self-contained HTML dashboard, opened locally in a browser. Show KPI cards, campus comparison and actual-versus-budget views. | Build/tune 25 min; check 7 min. Change a chart to horizontal bars, add campus and period filters, and make adverse variances obvious. Compare one filtered total with Excel. This is presentation of existing data, not a new business system. |
| 01:55–02:35 | Build 3: update the monthly PowerPoint | Demo 10 min: give Cowork an existing three-slide template and the checked workbook. Update numbers, chart data, dates and evidence-based commentary while preserving the layout. Then duplicate the reference chart's style for another campus. | Build/tune 25 min; check 5 min. Open the resulting .pptx in PowerPoint, inspect formatting and trace one chart value to Excel. Correct one visual issue in plain English. PowerPoint is used for review; no Claude PowerPoint add-in is required. |
| 02:35–02:45 | Break | Prepare the next-month input and saved report instructions. | 10-minute break. |
| 02:45–03:10 | Make it repeatable next month | Demo 5 min: replace February's input with the complete March export and reuse saved instructions. Start with validation; regenerate the dashboard and deck only after approval. | Practise 17 min; review 3 min. Refresh the workbook and save the repeatable steps. Accounting/payroll: refresh the exception/control report. FP&A: use Claude in Excel to add a simple assumption-driven April forecast. Choose one extension, not both. |
| 03:10–03:25 | Share with executives safely | Demo 6 min: distinguish a local HTML file from a hosted dashboard. Show the approved internal handoff route, or explain it if access is not ready. Show a static PDF alternative. | Spend 7 minutes checking the delivery checklist: period, units, reconciliation status, sources, permissions and reviewer. Review 2 min. Save a share-ready draft; do not publish financial data to a public service. |
| 03:25–03:30 | Close on the next real report | Recap: specify the output → check the plan → make it → check and tune. Each person records one existing report to try next and its reviewer. | Leave with files, reusable prompts and a next-month checklist—not a new exploratory project. |
| 03:30–04:00 | Reserved buffer / optional troubleshooting | Handle unfinished builds and specific workflow questions. | Optional support; no additional core teaching. |
Hands-on time: approximately 109 minutes within the 210-minute session. Facilitator/support staff handle questions; do not recruit Brightmoor's more experienced finance colleagues as unpaid teaching assistants—the call explicitly ruled this out.
The two-minute explanation
“With permission, Cowork can work with files in a folder you choose, run code behind the scenes to process them, and save new workbooks, dashboards and presentations. You describe the job; you don't write or run code. Claude in Excel works alongside you inside the workbook, which is useful for understanding formulas and checking changes.”
“ChatGPT can also analyse uploaded files and run code in some modes. The distinction we're demonstrating today is Cowork's permissioned folder-based workflow and saved deliverables—not a claim that chat tools can only answer questions.”
Prepare before the session
- Access: provision approved Claude accounts, install/test the desktop app's Cowork area, and test the Claude in Excel add-in on attendee devices. Open one workbook, save one output, and confirm folder permissions before training. No terminal, Claude Code, GitHub or software installation during teaching.
- Inputs: prepare a small, synthetic NetSuite-shaped export, payroll control totals, budget, account mapping and a three-slide reporting template. The facilitator pack specifies these assets and supplies copy/paste prompts. These are preparation requirements, not files already supplied with this agenda.
- Rehearsal: generate and manually check a workbook, dashboard and deck in advance. Keep each as a checkpoint so slow generation or a broken layout does not consume the next segment. Rehearse template fidelity; do not promise a perfect 15-slide refresh on the first attempt.
- Snowflake: the default is an exported workbook: NetSuite → Snowflake → Excel → Cowork. A live pull is optional only if IT has already approved and tested read-only access to the required reporting view. No connector setup, credentials or SQL lesson during the workshop.
- Data and sharing: use synthetic data throughout. Real financial or payroll data requires Brightmoor's approval and appropriate agreements; an NDA alone does not grant tool or publishing permission. Confirm an access-controlled internal destination before demonstrating live sharing.
Keep the scope tight
Retain the earlier workshop's guided-build-and-tune structure, but replace the ASCII exercise, generic app builds, open-ended brainstorming, formal showcases and deployment tutorials with this single reporting workflow. Troubleshooting is simple: show Claude the specific error or screenshot, request one correction, recheck the result; if needed, restart from the last checked file.
Success means a reviewed draft and a repeatable process. It does not mean unattended accounting, automatic journal posting, an approved compliance filing, a production dashboard or guaranteed time savings. Compliance work here means an internal control/exception report; actual requirements and sign-off remain with Brightmoor.
Basis and assumptions
Based on Brightmoor's call notes and the supplied previous run of show. The 3½-hour teaching block, four-hour booking, audience mix, monthly pack and dashboard requirements come from the call. Start time, three-campus synthetic example, reporting periods and simplified template are planning assumptions. No real workbook, corporate PowerPoint template or compliance specification was supplied.
Current product documentation could not be retrieved in this environment. Verify account eligibility, device support, add-in permissions and the file-generation workflow during preflight; this agenda does not assert current plan-specific availability or a working Snowflake connector.