Mike's Checks/claude-fable-5-1/05 showrunner
05 showrunner
claude-fable-5-1Claude Codehigh effortrun 22 Sep 2026169,990 tokens
▸Instructions — what the model was asked
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
Answer
Brightmoor run of show: cover note
The full run sheet is in run-of-show-brightmoor.md. It follows the same format as the Nvalo sheets: numbered blocks with times, then a data-pack spec, pre-work, what changed, and open items.
The shape of the session (3.5 hours)
- What we're doing today (5 min). No AI framing. Three builds, two rules.
- First prompt (15 min). Top-5 expenses by campus from the NetSuite GL export into a new Excel file, verified by the attendee with a pivot. Then Claude in Excel on the same workbook. Replaces the ASCII map.
- Build 1: HTML dashboard from the income statement export (45 min). Includes Dana's tune requests (horizontal bar, filters) and a publish step.
- Pulse check and break (20 min).
- Build 2: month-end flux analysis and payroll-to-GL reconciliation in Excel (45 min). Ends with Claude writing its own instructions file so next month is one prompt.
- Build 3: monthly PowerPoint pack updated from the Excel (45 min). Includes "mirror this chart for the other five campuses".
- ASK Ladder, monthly rhythm, guardrails, optional Snowflake demo (15 min).
- Wrap-up and Q&A (20 min).
Assumptions made
- Start time set to 10:00 AM PT. Times shift with the actual start.
- Every provides 2 TAs in chat since Dana declined client-side volunteers.
- The synthetic data pack is described in the run sheet but not yet built. Building it is the next step once you approve the shape.
- Snowflake is demo-only, for Dana, and only if her connector is live.
- Password-protected hosting of the dashboard is treated as an IT follow-up rather than a live build step.
Suggested next step
Approve the data-pack spec and I can generate the Excel files, the GL exports with the seeded reconciliation items, and the two PowerPoint decks.
Checks
17/17No AI-tell wordingai-wordingevery task
deliverable text contains none of the shared AI-tell phrases in bench/ai-tells.txt. Task checks may add narrower contractual bans, but must not repeat this shared floor.
inspected run-of-show-nvalo.md, ANSWER.md, brightmoor-education-call-notes.md, run-of-show-brightmoor.md
Run of show existsexiststhis task
a run-of-show document was produced
Coherent scheduleformatthis task
it parses as a run of show: one coherent schedule, no segment that ends before it starts, >=5 time-ranged rows carrying activity text (md table rows, list items, bold headings "(9:00-9:15)", single-clock table rows, or plain lines all count)
Five-minute time markstime-grainthis task
segment boundaries sit on 5-minute marks, at most one off-grid -- a schedule planned at :02/:08/:17 is arithmetic, not a plan
Timings add uptimings-tie-outthis task
per schedule, segments are contiguous: no overlaps, no gap over 30 min, >=85% of the span scheduled, and a span between 45 and 600 minutes
Q1Uses Cowork throughoutthis task
Judge's reasoning
The header says 'Claude Cowork... and Claude in Excel. No Claude Code, no terminal, no GitHub.' Every step attendees do is in Cowork or Excel.
▸Rubric
Cowork-only. Do all attendee-facing steps stay inside Claude Cowork (and Claude in Excel)? FAIL if any step the attendees are asked to do involves Claude Code, the terminal/CLI, git or GitHub, or installing developer tooling. The prompt: "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."
Q2Dashboard exercisethis task
Judge's reasoning
Build 1 (45 min) has everyone build an HTML dashboard from income_statement_by_campus_FY26.xlsx, with Talk/Jam/Make/Tune steps and a tie-out.
▸Rubric
Dashboard use case. Is there a hands-on segment where attendees build a dashboard from existing spreadsheet data? FAIL if dashboards are only mentioned, described or promised for later rather than built in the session.
Q3Financial analysis exercisethis task
Judge's reasoning
Build 2 (45 min) is a flux analysis and payroll reconciliation that Claude builds with Python from the GL exports, output as a 3-tab Excel workbook.
▸Rubric
Financial analysis use case. Is there a hands-on segment where attendees do financial analysis (Claude writing/running code over their numbers, e.g. Excel in, analysis out)? FAIL if absent or folded into the dashboard segment as a passing remark.
Q4PowerPoint exercisethis task
Judge's reasoning
Build 3 (45 min) has attendees update Brightmoor_Monthly_Pack_Template.pptx from the Build 2 Excel into the August deck, including mirroring charts across campuses.
▸Rubric
PowerPoint use case. Is there a hands-on segment where attendees update a PowerPoint template/deck from the data — the client's monthly reporting pack? FAIL if absent, or if it is only a demo the facilitator drives while attendees watch.
Q5Relevant business datathis task
Judge's reasoning
The data pack specifies a NetSuite GL transaction-line export (Subsidiary, Department, Class/campus), a NetSuite chart of accounts, an income statement by campus × month plus YTD with an EBITDA subtotal, budget and forecast files, and a payroll register.
▸Rubric
NetSuite/Snowflake-shaped data. Is the synthetic data used in the exercises shaped like this client's actual data — NetSuite/Snowflake-style finance records (GL export, revenue and budget vs actual, EBITDA build-up, payroll vs non-payroll, campus/entity breakdown, monthly and year-to-date columns)? FAIL if the exercises use generic sample data (a demo CSV, sales widgets, made-up SaaS metrics) or leave the data unspecified. The prompt: "the shape of the tasks, the shape of the data should be like NetSuite shaped."
Q6No ASCII icebreakerthis task
Judge's reasoning
The first prompt replaces the ASCII map with a 'top 5 expense accounts by campus' Excel task on the NetSuite GL export, which attendees verify with a pivot table.
▸Rubric
No ASCII icebreaker. Is the opening hands-on exercise a practical finance/Excel task? FAIL if the run of show keeps the ASCII-image-of-your-location icebreaker or substitutes another whimsical non-work exercise. The prompt: "maybe the ASCII image idea that I normally do where I ask it to create an ASCII image based on my location isn['t] like that useful... maybe we use an Excel implementation instead."
Q7Explains Cowork versus ChatGPTthis task
Judge's reasoning
Section 2 keeps it: 'chat gives you text to paste; Cowork works in your folder, runs code, and hands you files.'
▸Rubric
Cowork vs ChatGPT explained. Does the run of show keep the explanation of how Cowork differs from ChatGPT — that it has access to the file system and can run code? FAIL if that framing is dropped. The prompt: "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."
Q8No theory or hypethis task
Judge's reasoning
The opening is 'No AI framing', 'why now' and roadmap content was removed, and the troubleshooting section works through problems attendees hit during the builds.
▸Rubric
No theory, no AI cheerleading. Is every segment tied to a task these people do at work? FAIL if any segment is devoted to AI industry context, the future of work, model capabilities, prompt-engineering theory, or excitement-building. The prompt: "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."
Q9Mostly hands-on workthis task
Judge's reasoning
About 150 of the 210 minutes are attendees working with Claude (15-min first prompt plus three 45-min builds).
▸Rubric
Mostly hands-on. Is at least half the scheduled time attendees working with Claude themselves? FAIL if presentation, discussion and Q&A segments outweigh build segments. From the call: "we try and make at least 50% of it them actually you know working with us to do some of these tasks."
Q10Realistic segment timingsthis task
Judge's reasoning
Each build gets 45 minutes, setup is handled by pre-work plus a check at the start, and 2 TAs are staffed in chat.
▸Rubric
Per-segment timings realistic. Could a room of 20–30 beginners actually finish each segment in the time allotted? FAIL if any build segment is implausibly short (a dashboard, an analysis or a deck refresh built end to end in ~15 minutes), or if setup/handholding time for first-time users is ignored.
Q11Fits the booked timethis task
Judge's reasoning
The session runs 10:00–13:30 (3.5 hours), leaving 30 minutes of the 4-hour block as buffer.
▸Rubric
Total length fits the booked slot. Does the session run about three and a half hours, inside the four-hour block? FAIL if the total is materially shorter or longer (under ~3 hours or over ~4 hours) without the run of show explaining the change. From the call notes: "we have a four hour block for next week and the session itself is three and a half hours."
Q12Ready to runthis task
Judge's reasoning
It includes prompts to paste, named input files, what each build outputs, a full data-pack spec and pre-work steps.
▸Rubric
Usable as a run of show. Could a facilitator run the session from this document alone? FAIL if segments are titles without content — no prompts to paste, no data files named, no statement of what attendees produce — so the facilitator would still have to design the session.