Mike's Checks
Checks

Mike's Checks/grok-4.6/05 showrunner

05 showrunner

grok-4.6Grok CLIhigh effortrun 1 Sep 2026

Compare models
15/16
checks passed
94%
▸Instructions — the case's current instructions; none were saved with this result

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

ANSWER.md the model's output · 5.91 KBdownload

A 3.5-hour, Cowork-only session for Brightmoor’s accounting, payroll, bursar, and strategic finance teams. One monthly close, three artifacts they already make by hand.

Send Dana: agenda-for-dana.md
Run the room with: run-of-show-brightmoor.md
Send attendees Monday: prework.md
Live copy-paste: demo-prompts.md
Data + 15-page template: workshop-pack/brightmoor-feb-close/
Do not share with attendees: workshop-pack/facilitator/


What the run is

Not a Claude Code workshop. Not a tour of AI. Not a brainstorm.

It is their existing job, once:

  1. Dashboard — the wide NetSuite P&L Excel Accounting already sends, turned into a campus-filter HTML view leadership can read.
  2. Analysis — Cowork runs the numbers in Python and writes a tied-out Excel workbook (P&L, EBITDA bridge, payroll vs non-payroll, register-to-GL recon, control totals). Then ten minutes in Claude in Excel so they can do the same work inside the sheet.
  3. PowerPoint — the 15-page monthly template, filled from that workbook, including charts and commentary.

That is the 8-hour job Dana walked through on the 3 Apr call (NetSuite export → Excel → slides, every month). We do a compressed, checked version of it.

What we cut, on purpose

  • No “why AI, why now.”
  • No ASCII art / location icebreaker. First prompt is an Excel first-look against the February P&L.
  • No Claude Code, no terminal, no GitHub, no public deploy.
  • No vacation planner, no second toy build, no afternoon open-build.
  • No volunteer TAs from their team (Dana declined; they are too busy).
  • No Snowflake live connection. Files are NetSuite-shaped so the prompts transfer the day IT turns the connector on.

Keep from the standard beginners session: Cowork vs a chatbot (files + code), Talk → Jam → Make → Tune, the ASK Ladder, and a short number-checking block — the last one matters more here than in a PM room.

Timing (3h 30m inside a 4-hour block)

Clock (10:00 start) Mins Block
10:00–10:08 8 Why we’re here — the 8-hour pack, not a keynote
10:08–10:28 20 Cowork vs ChatGPT + first Excel prompt
10:28–11:15 47 Build 1 — HTML dashboard from the P&L export
11:15–11:22 7 Neighbor share
11:22–11:32 10 Break
11:32–11:42 10 Checking numbers + ASK Ladder
11:42–12:25 43 Build 2 — analysis workbook, then Claude in Excel
12:25–13:10 45 Build 3 — fill the monthly PowerPoint template
13:10–13:20 10 The Monday workflow (repeatable prompt)
13:20–13:30 10 Questions and close

Shift the clock to whatever start time is on the invite. The extra 30 minutes in the four-hour block is setup slack, not content.

The data

Synthetic February 2026 close for Brightmoor Education, Inc. Oracle NetSuite is the system of record; Snowflake is the warehouse. Files look like saved-search / worksheet extracts, not a data-science sandbox.

Dimensions they will recognize:

  • Location = campus: Bay Area, Austin, Chicago, Online, NYC
  • Department, Class (program), Subsidiary, Account Number
  • Month + YTD (Jan + Feb), budget, forecast locked 1 Feb
  • Payroll accounts 5000/5010/6000/6010 vs everything else
  • EBITDA with D&A add-back; Chicago opening costs on 7900 as a Controller judgment

Issues planted so the analysis is not a clean happy path:

  • Austin tuition 16% under budget (enrollment)
  • Online 11% over
  • Chicago new campus, $186.4k of opening costs on 7900, EBITDA near zero
  • Payroll $189k over budget; ADP register is $47,250 short of GL (2/28 wage accrual)
  • Three vendor bills totaling $18,740 sitting on account 1300 Clearing
  • Marketing underspend is timing, not a save
  • Company trial balance debits = credits ($37,401,931.62)

If Dana later shares real campus names or a real slide template, swap those labels. Do not swap in live numbers without an NDA.

Assumptions (nothing to wait on)

  • Headcount: 20–30, mostly accounting / payroll / bursar; ~3 strategic finance. ~90% beginners; Dana, Greg, and one modeler are further along. Give those three the “hard mode” extras in the run sheet — do not make them TAs.
  • Licenses: Cowork for every attendee is a blocker. On the call, only Dana’s three plus Greg had Claude. Confirm with Greg before Thursday.
  • Claude in Excel: Assume the add-in is available. If it is not, run that ten minutes as a Cowork “edit this workbook in place” prompt. Do not stall the room.
  • Snowflake: Optional. Same file shapes; connector is not required to run the session.
  • Session length: 3.5 hours of content, 4-hour hold, per Natalia/Dana.
  • Start time: Not specified; run sheet uses 10:00. Relabel.
  • Campus names: Invented. Transcript mention of “Ideal Info Cross” was unclear.
  • Brand: Navy #1F4E79 / gold #C4A35A on the template. Swap if they send a real deck.
  • Publishing a dashboard: Internal HTML file on a shared drive. Not a hosted app, not a password product, not GitHub Pages. Dana asked about “publish so other finance can open it.” Shared drive / SharePoint is the honest answer in this session.
  • Expectation Dana already heard: they will not walk out with a one-shot, pixel-perfect 15-pager. They will walk out with the process, a working dashboard, a tied workbook, and a filled pack they still have to Tune.

What “good” looks like on Thursday

Every attendee has, in their Cowork folder:

  1. 00_first_look.xlsx — 30-second CFO snapshot
  2. dashboard.html — campus dropdown, horizontal bars, month + YTD
  3. Feb_close_analysis.xlsx — control-totals tab that ties to the trial balance
  4. Brightmoor_Monthly_Review_Feb2026.pptx — template filled, not from scratch

And one sentence they can use on Monday: drop next month’s extract in the folder, run the same prompts, check the control totals, then send.

Checks

15/16
Script checks 3/4answered by a program
fail

Five-minute time markstime-grain

segment boundaries sit on 5-minute marks, at most one off-grid -- a schedule planned at :02/:08/:17 is arithmetic, not a plan

pass

Run of show existsexists

a run-of-show document was produced

pass

Coherent scheduleformat

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)

pass

Timings add uptimings-tie-out

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

Judge checks 12/12judged by Claude
pass

Q1Uses Cowork throughout

Judge's reasoning

Every segment is Cowork + Claude in Excel; run sheet and prework explicitly bar Claude Code, Terminal, GitHub ('Do not install or require Claude Code, and do not ask anyone to open Terminal').

▸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."

pass

Q2Dashboard exercise

Judge's reasoning

Build 1 (10:28–11:15, 47 min) has attendees produce dashboard.html from 06_Accounting_MonthlyPnL_Export_Feb2026.xlsx with Prompts 1/1b/1c including campus dropdown and horizontal bars.

▸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.

pass

Q3Financial analysis exercise

Judge's reasoning

Build 2 (11:42–12:25, 43 min) is a separate segment where Cowork uses Python to write Feb_close_analysis.xlsx (Control_Totals, EBITDA_Bridge, Payroll_Recon) plus a Claude-in-Excel pass.

▸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.

pass

Q4PowerPoint exercise

Judge's reasoning

Build 3 (12:25–13:10, 45 min) has attendees fill 07_MonthlyPack_TEMPLATE_Feb2026.pptx and save as Brightmoor_Monthly_Review_Feb2026.pptx, with fallback guidance for anyone 'still on slide 3'.

▸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.

pass

Q5Relevant business data

Judge's reasoning

The workshop pack contains real NetSuite-shaped files (chart of accounts, budget-vs-actual income statement by Location/Class/Department, trial balance, transaction detail, ADP register, FP&A forecast) with a header reading 'Source system: Oracle NetSuite → Snowflake → Excel extract'.

▸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."

pass

Q6No ASCII icebreaker

Judge's reasoning

Opening hands-on is Prompt 0, a first-look Excel snapshot of February revenue/EBITDA/campus misses; the doc states 'You have just replaced the ASCII map.'

▸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."

pass

Q7Explains Cowork versus ChatGPT

Judge's reasoning

Segment 2 keeps the framing: 'ChatGPT and Gemini answer. Cowork works on a folder: it reads the extract, runs the analysis, and writes the Excel, the HTML, and the PowerPoint.'

▸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."

pass

Q8No theory or hype

Judge's reasoning

No AI-context or future-of-work segment; the run sheet says 'No origin story. No "exciting time for AI"' and every block maps to close, dashboard, analysis or the monthly pack.

▸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."

pass

Q9Mostly hands-on work

Judge's reasoning

Build segments total 135 min (47+43+45) of 210, plus ~14 min of hands-on prompting in segment 2 — roughly 70% attendee build time.

▸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."

pass

Q10Realistic segment timings

Judge's reasoning

Build blocks are 47/43/45 min with Talk-Jam-Make-Tune sub-timings, a 9:45 door check, prework for licenses/downloads, and explicit expectation-setting that a 15-pager won't one-shot.

▸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.

pass

Q11Fits the booked time

Judge's reasoning

Schedule runs 10:00–13:30 = 3h30m, with the remaining 30 min of the four-hour hold called out as setup slack.

▸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."

pass

Q12Ready to run

Judge's reasoning

Facilitator has verbatim scripts, named data files, a full demo-prompts.md of paste-ready prompts, expected outputs ('Feb revenue $7.936M vs budget $8.100M'), an answer key, and a crash list.

▸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.