Skip to main content
MethodFinance & AccountingPlanning & modellingAdvanced

Build a startup financial model

A driver-based 3–5 year model (revenue, costs, hiring, cash, runway) laid out so you can build it in a spreadsheet.

This is a practical, copy-paste process for preparing to fundraise.. Use it when you want a clear structure, then add your own details and the linked evidence.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

  1. 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
  2. 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
  3. 3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md
# Build a startup financial model
Method by Deepstory Research: deepstoryresearch.com/method/startup-financial-model

You are a startup CFO who has built models for seed to Series B rounds. Follow the method below step by step. Goal: A driver-based 3–5 year model (revenue, costs, hiring, cash, runway) laid out so you can build it in a spreadsheet.

## My inputs
- Business model: [BUSINESS_MODEL]  (example: B2B SaaS, monthly subscriptions)
- Current numbers: [CURRENT_NUMBERS]  (example: MRR, customers, burn)
- Funding plan: [FUNDING_PLAN]  (example: raise $1.5M in 6 months)
- Hiring plan: [HIRING_PLAN]  (example: known roles)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. List the revenue drivers (e.g. leads → conversion → customers → ARPA → churn).
2. List cost drivers: headcount by role, COGS, marketing, overhead.
3. Lay out monthly assumptions for year 1 and annual for years 2–5.
4. Produce P&L, cash flow and runway.
5. Add base, upside and downside cases.
6. Give spreadsheet structure: tabs, rows and formulas.

## Deliver the output in this structure
- Driver tree
- Assumptions sheet
- Revenue build
- Headcount plan
- P&L and cash flow summary
- Runway and funding need
- Scenario comparison
- Spreadsheet layout & formulas

## Quality rules
- Every output traces to an assumption cell.
- Churn and ramp times must be realistic; cite benchmarks or label assumptions.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

What you need to give the AI

InputPlaceholderExample
Business model[BUSINESS_MODEL]B2B SaaS, monthly subscriptions
Current numbers[CURRENT_NUMBERS]MRR, customers, burn
Funding plan[FUNDING_PLAN]raise $1.5M in 6 months
Hiring plan[HIRING_PLAN]known roles

Use it when

  • Preparing to fundraise.
  • Deciding how many people you can hire.

Best with: An AI tool that can create spreadsheets (e.g. with code or file output), or paste the layout into Excel/Sheets.

What you get

  • Driver tree
  • Assumptions sheet
  • Revenue build
  • Headcount plan
  • P&L and cash flow summary
  • Runway and funding need
  • Scenario comparison
  • Spreadsheet layout & formulas

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

  1. 1

    List the revenue drivers (e.g. leads → conversion → customers → ARPA → churn).

  2. 2

    List cost drivers: headcount by role, COGS, marketing, overhead.

  3. 3

    Lay out monthly assumptions for year 1 and annual for years 2–5.

  4. 4

    Produce P&L, cash flow and runway.

  5. 5

    Add base, upside and downside cases.

  6. 6

    Give spreadsheet structure: tabs, rows and formulas.

Quality checks built into the prompt

  • • Every output traces to an assumption cell.
  • • Churn and ramp times must be realistic; cite benchmarks or label assumptions.
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence to use with this method

Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.

EvidenceFinance

US Inflation & the Fed

The full 2026 inflation story on one page: the CPI path and category breakdown, the mid-year turn and the still-rising core PCE outlook, and the Fed’s rate response — fed funds, the 10-year Treasury, and the 30-year mortgage.

Run next

Methods that chain well after this one.

Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.