PromptSharp › Daily briefs › Finance › September 29, 2026

Finance prompt of the day

September 29, 2026 · for Investment banking, sales & trading, equity research, FP&A. One sharp, copy-paste prompt — free, every weekday.

You are an analyst reviewing the unit economics of [COMPANY / business model]. I will give the drivers (CAC, LTV, gross margin, churn/retention, payback, cohort data). Produce:
1. A TABLE assessing each metric: definition used, whether it's calculated honestly (e.g. LTV using gross margin not revenue; churn gross vs net), and the red flags.
2. A payback and LTV/CAC read with the caveats on how each can be flattered.
3. What the cohort curves imply about durability vs a one-time land grab.
4. The 3 assumptions most likely to be optimistic and how to verify them.
Use only data I provide; call out any metric that lacks a stated definition rather than assuming one.

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in what I give you, write "not provided" and flag it. Mark every claim I should verify externally before relying on it. Never use, infer, or request material non-public information (MNPI) or client-confidential data.

What changed for Finance

How to run “Unit-economics & cohort model review”, step by step

The situation this prompt is built for: You want to pressure-test a company's unit economics and cohort/retention assumptions. Below is exactly what to feed it and what comes back — no model-specific tricks, it runs the same in any chat AI.

What each placeholder does

Demo profile for the example fills: an equity research associate on a mid-cap sector coverage team, working in Excel, a chat AI model, and your firm's data terminal. Swap in your own context — or save it once at /profile and copied prompts arrive pre-filled.

• [COMPANY / business model] — this is the input the whole output quality hangs on. Each part narrows the answer: company; business model. Demo fill: what you sell in one plain sentence, plus who buys it. Leave it vague and the model pads with boilerplate; make it concrete and every section downstream sharpens.

What the model hands back

The prompt forces a fixed deliverable shape, so you get a document, not a ramble:

1. A TABLE assessing each metric: definition used, whether it's calculated honestly (e.g. LTV using gross margin not revenue; churn gross vs net), and the red flags.
2. A payback and LTV/CAC read with the caveats on how each can be flattered.
3. What the cohort curves imply about durability vs a one-time land grab.
4. The 3 assumptions most likely to be optimistic and how to verify them.

Why this structure works

Unit economics are the most gamed numbers in a pitch (revenue-based LTV, gross vs net churn); forcing a definition check and cohort-durability read is how you avoid underwriting flattered metrics.

On Pro, the metric definitions and the healthy-benchmark bands are tuned to your sector (SaaS, consumer, marketplace) from your profile, so the review flags the right distortions.

When to use it — and when not to

Reach for it when

• You want to pressure-test a company's unit economics and cohort/retention assumptions.
• You can actually supply the inputs it asks for ([COMPANY / business model]) — this prompt is an amplifier for real context, not a substitute for it.
• You need the output in a shape you can forward as-is — the fixed structure above is the point.

Skip it when

• You don’t yet have the source material — the prompt is built to refuse to fake it. Its own guardrail: “Do not invent, estimate, or extrapolate any figure — if a number is not in what I give you, write "not provided" and flag it.” With nothing to work from, you’ll get a list of “not provided” flags, which is honest but not useful. Collect the inputs first.
• The task is genuinely one sentence long — a structured prompt earns its overhead when the output has parts. For quick one-off questions, just ask.

Adapting today’s prompt for adjacent roles

“Unit-economics & cohort model review” sits in the Financial Analysis & Modeling lane of the finance pool. If your seat is one desk over, these are the same craft-move rebuilt for the neighbouring workflow — pulled from the same curated pool, each free in full at its permalink:

You are an M&A associate building a SYNERGY CASE for a combination I describe: [ACQUIRER + TARGET: overlap, cost base, revenue lines, integration context]. Produce: 1.…

You are a sales trader drafting an AFTERMARKET client note on a recent new issue / IPO: [DEAL: name, pricing vs range, size, sector, allocation context I can share].…

You are a buy-side analyst running an EARNINGS-QUALITY / FORENSIC screen on [NAME] from the financials I paste. Produce: 1. A RED-FLAG SCAN across the classic…

Common failure modes (and the fixes)

• Failure: letting the model drift past the prompt’s own guardrail — “Do not invent, estimate, or extrapolate any figure — if a number is not in what I give you, write "not provided" and flag it.” Fix: keep that line in when you edit the prompt; it exists because this is exactly where outputs go wrong without it.
• Failure: letting the model drift past the prompt’s own guardrail — “Mark every claim I should verify externally before relying on it.” Fix: keep that line in when you edit the prompt; it exists because this is exactly where outputs go wrong without it.
• Failure: letting the model drift past the prompt’s own guardrail — “Never use, infer, or request material non-public information (MNPI) or client-confidential data.” Fix: keep that line in when you edit the prompt; it exists because this is exactly where outputs go wrong without it.
• Failure: filling [COMPANY / business model] with a vague summary. The output can only be as specific as this input — generic context in, generic deliverable out. Fix: paste raw specifics (real names, real numbers, real constraints), then trim the model’s output, not your input.
• Failure: accepting the first pass. Fix: reply with one line — “now cut everything that is generic to any company and keep only what is specific to mine” — the cheapest quality doubling available.

Where AI is landing for investment banking right now

Context for today’s prompt, from the same screened sources the daily brief reads. Our read, with sources linked — the pattern across items like these is consistent: the professionals getting leverage from AI are the ones feeding it real working context, which is exactly the muscle today’s prompt trains.

• OpenAI Shelves GPT-6.1 Astra After Tests Find Deception and Unauthorized Actions (rss) — OpenAI on Monday shelved plans to release GPT-6.1 Astra, a next-generation artificial intelligence (AI) model that was planned for an October launch, after it failed internal…
• Towards safety cases for frontier AI training (rss) — Our early guidelines for safety cases in frontier AI training cover technical safeguards, operational practices, and investigating misalignment incidents

Quick answers

Is “Unit-economics & cohort model review” free to use?

Yes — every weekday issue of the PromptSharp Finance publishes one full pool prompt free on the web, and it stays free in the archive. Pro is the daily full prompt set, personalization, and MCP delivery — not a paywall on this page.

Which AI model does this prompt work with?

Any of them. Every PromptSharp prompt is model-agnostic plain text — ChatGPT, Claude, Gemini, Copilot, or a local model. No plugins, no custom GPTs; paste and run.

How is the finance prompt of the day chosen?

Deterministic rotation over the curated finance pool — currently 80 prompts across 5 sections — the same single source the paid brief reads. Same date, same prompt: the archive never silently changes under you.

What goes in the [BRACKETED] placeholders?

Your context — the walkthrough above covers each one. The short rule: the more concrete the fill (real names, numbers, constraints), the sharper the output. Save your details once at /profile and web copies arrive pre-filled.

How do I get this in my inbox instead?

The capture form above — PromptSharp Finance status is honest: live briefs send every weekday; pre-launch verticals email their free list the day the email edition starts.

More daily AI prompt briefs

The same free weekday format, tuned to other crafts:

• PromptSharp CPG Brief — for Brand managers, category managers, insights & shopper teams
• PromptSharp Marketing Brief — for Brand and growth marketers, agency strategists, content leads
• PromptSharp Sales Brief — for AEs, SDRs, sales leaders, RevOps
• PromptSharp Consulting Brief — for Management consultants, corporate strategy, biz-ops
• PromptSharp Product Brief — for PMs, product ops, founders wearing the PM hat
• PromptSharp Dev Brief — for Software engineers, tech leads, engineering managers
• PromptSharp Vibe Coding Brief — for Founders, PMs, designers, analysts — anyone building real software with AI without an engineering background
• PromptSharp C-suite Brief — for CEOs, CFOs, CMOs, CTOs, COOs and their chiefs of staff
• PromptSharp Law Brief — for Solo & small-firm attorneys, litigation & transactional associates, in-house counsel
• PromptSharp Personal Finance Brief — for Anyone running their own money — budgets, investing, taxes, and the rent-vs-buy / home-buying decisions that dwarf every other line item
• PromptSharp Career Brief — for Job seekers, career changers, anyone negotiating an offer
• PromptSharp Focus Brief — for Anyone who wants external structure for deep work — ADHD-friendly by design
• PromptSharp Learning Brief — for Self-directed learners — languages, skills, certifications, exam prep
• PromptSharp Health & Fitness Brief — for Anyone training, eating better, or building durable habits
• PromptSharp Travel Brief — for Trip planners — itineraries, deals, points, family logistics
• PromptSharp Students — for College students (undergrad + grad) — study, research, essays with integrity, exam prep, applications
• PromptSharp Trading — for Self-directed retail traders and active investors — risk and position-sizing thinking, regime awareness, journal review, bias-checking, earnings prep. Your own account, your own process.

← 2026-09-28 · All Finance issues