Finance & Analysis

Verified against ChatGPT · 2026-08-09

Compress the finance section of a board deck down to the three questions the board will actually ask

Rebuilds a sprawling finance update into the three questions a board is realistically going to ask, with the answer to each one pre-built, instead of a slide deck the board has to reverse-engineer questions from.

ChatGPT (GPT-5.1)5 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

You're helping me prepare the finance section of an upcoming board update. I don't want a slide-by-slide summary of every metric — boards ask a small, predictable set of questions, and I want this brief built around answering those directly.

COMPANY STAGE
Series B, 65 employees, 18 months post-raise

PERIOD FINANCIALS
MRR $340k (up 6% MoM); gross margin 74%; net burn $210k/month

RUNWAY / CASH POSITION
$4.1M in the bank; ~19 months of runway at the current $210k/month burn rate

ANYTHING OFF-PLAN THIS PERIOD
Churn ticked up from 2.1% to 3.4% monthly in the SMB segment; enterprise sales cycle running longer than modeled

BOARD COMPOSITION NOTE
Two operator-investors who ask sharp unit-economics questions; one newer board member still ramping on the business

STEP 1 — Identify the three questions.
Based on the company stage and what's off-plan this period, identify the three questions this specific board is most likely to ask about the finances — not a generic list ("how's growth," "how's burn") but the three shaped by what's actually unusual or notable this period. If nothing is meaningfully off-plan, say so and build the three questions around what a board at this stage typically scrutinizes instead.

STEP 2 — Answer each one directly.
For each question, give the direct answer in the first sentence — not the supporting data first and the answer buried at the end. Follow with the two or three numbers that actually support that answer, and one sentence on what it means for a decision the board might make (e.g., approving a raise, approving a budget change) if relevant.

STEP 3 — Anticipate the follow-up.
For each of the three, add one likely follow-up question a sharp board member would ask next, and pre-answer it in a sentence — this is what separates a brief that survives the actual meeting from one that gets picked apart live.

WHAT NOT TO DO
Do not pad the brief with metrics that don't connect to one of the three questions just to look thorough. Do not present cash runway as a single confident number without stating the assumption behind it (e.g., current burn rate held flat) — runway changes with burn, and stating it as a bare fact rather than a projection under a named assumption is misleading.

OUTPUT FORMAT
Three sections, one per question, each with: Question, Direct Answer, Supporting Numbers, Likely Follow-Up + Pre-Answer. Close with one line noting these are the three most likely questions based on what's off-plan, not a guarantee of what will actually be asked, and that runway/cash figures are projections under stated assumptions, not guarantees.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Anchoring the brief to three anticipated questions rather than a metric-by-metric readout is a direct fix for the most common failure of board materials: a comprehensive deck gives every reader an equal amount of everything, which means the board still has to do the work of finding the one or two things they actually care about, and a model asked to "summarize the finances" defaults to comprehensiveness because that reads as thorough. Forcing the direct answer into the first sentence of each section, before the supporting numbers, matters because GPT-5.1's default structure for a data-backed answer is context-then-conclusion — lead with the setup, land the point at the end — which works for an explainer but fails a board member skimming under time pressure who needs the verdict before deciding whether to read the supporting detail at all. The anticipated-follow-up step is what actually differentiates a brief that holds up in the room from one that doesn't: boards rarely stop at the first answer, and pre-building the second-order question (why did churn move, not just that it moved) means the presenter isn't caught reconstructing an answer live in front of investors. Requiring the runway figure to be stated as a projection under a named assumption rather than a bare fact addresses a specific and consequential failure mode — burn rate is not fixed, and presenting "19 months of runway" without qualifying it as "at current burn" implies a false precision that could shape a board's confidence about fundraising timing incorrectly if burn changes even modestly next quarter.

What you get back

Q1: Why did SMB churn jump from 2.1% to 3.4%? Direct answer: it's concentrated in one onboarding cohort from a channel partner test, not a broad product or pricing issue. Supporting numbers: 80% of the increase traces to accounts from that single channel; churn in all other acquisition channels held flat at 2.0%. Likely follow-up: is this partner channel being paused? Pre-answer: yes, new sign-ups from that channel paused pending a cohort review.

Verified against

ChatGPT GPT-5.1 · 2026-08-09

Changelog

  • 2026-08-09 Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.

EXPLORE WHAT SCULT BUILDS
All Finance & Analysis prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY