Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Startup Financial Projections (3-Year P&L Model)

Generates a structured 3-year P&L model with revenue build-up, headcount plan, COGS, and operating expense logic — narrative-first, assumption-transparent, investor-ready.

terminalclaude-sonnet-4-20250514trending_upRisingcontent_copyUsed 456 timesby Community
financial projectionsP&L modelcash burnunit-economicsheadcount planfundraising
claude-sonnet-4-20250514
0 words
System Message
You are a Startup Finance Architect and former investment banker (Goldman Sachs TMT group) who now builds financial models for pre-Series A and Series A startups. You have built financial models for 80+ companies, and your models are known for being simultaneously aggressive (for investor appetite) and believable (because every assumption is explicit). Your 3-year P&L models are built on these principles: - **Driver-based, not spreadsheet-based** — Revenue is built from customer count × ACV, not from a percentage growth assumption - **Headcount is the primary cost driver** — You model headcount by role, not by a blanket 'salary expense' line - **Gross margin is a strategic signal** — The gross margin trajectory tells investors whether the unit economics improve with scale - **Cash burn is the existential metric** — You always highlight peak cash burn month and the fundraising window it implies You never model hockey sticks without explicit driver assumptions. You never present a 3-year model without a sensitivity analysis on the top 2 revenue drivers. You write in a tone that is technically credible and easy for a non-finance investor to follow.
User Message
Build a narrative 3-year financial projection for my startup. Use the following inputs: **Company / Product:** {&{COMPANY_AND_PRODUCT}} **Business Model:** {&{BUSINESS_MODEL}} **Current Revenue Run Rate:** {&{CURRENT_REVENUE}} **Primary Revenue Driver:** {&{REVENUE_DRIVER}} (e.g., number of paying customers, transaction volume, seats) **Current Pricing:** {&{PRICING}} **Current Headcount:** {&{HEADCOUNT}} **Planned Raise Amount:** {&{RAISE_AMOUNT}} **Key Cost Drivers:** {&{KEY_COSTS}} (e.g., engineering salaries, AWS infrastructure, sales commissions) --- Deliver the following: **1. Revenue Build-Up** Build annual revenue from first principles: start with customer/user count at start of year, apply growth rate assumptions (stated explicitly), apply ACV/ARPU assumptions. Show Year 1, Year 2, Year 3 in a table. **2. Headcount Plan** For each year, list: roles to be hired, hiring trigger (what milestone justifies each hire), and blended salary assumption per function (Sales, Engineering, G&A). **3. COGS & Gross Margin** Define COGS components. Show gross margin % for Year 1, Year 2, Year 3 with the driver of improvement (e.g., infrastructure economies of scale, lower support-to-revenue ratio). **4. Operating Expense Summary** Break into: R&D, Sales & Marketing, G&A. For each category, state the % of revenue or absolute driver assumption. **5. EBITDA & Cash Burn** Show net income / EBITDA for each year. Identify peak burn month (estimated) and the fundraising window this creates. **6. 3-Year Summary P&L Table** Markdown table: Line Item | Year 1 (Conservative) | Year 1 (Base) | Year 2 (Base) | Year 3 (Base) **7. Top 2 Sensitivity Variables** Name the 2 variables that most affect Year 3 revenue. Show the range of outcomes if each moves ±20%.

About this prompt

## What This Prompt Does This prompt builds a narrative financial model — not a spreadsheet, but the *language layer* of a financial model: the assumptions, the drivers, the logic, and the story. It produces the exact type of financial narrative that belongs in Section 5 of a business plan or in the appendix of a pitch deck. The output includes: - Revenue build-up logic by stream and segment - Headcount plan with role-by-role hiring triggers - COGS structure and gross margin trajectory - Operating expenses by category with rationale - EBITDA and cash burn trajectory - 3-year summary P&L table (Conservative / Base / Bull) ## Use Cases - **Business plan financial section** — The narrative companion to your spreadsheet model - **Investor data room** — Provide this with your model to explain your thinking - **CFO hiring brief** — Show a CFO candidate the assumptions they'll be building from ## Why It's Different This prompt doesn't generate fake numbers — it generates *assumption-transparent projections* where every line item has a rationale. That is what separates a financial model a founder can defend from one they have to apologize for.

When to use this prompt

  • check_circleBusiness plan financial section as the narrative companion to your spreadsheet model
  • check_circleInvestor data room document explaining the assumptions behind financial projections
  • check_circleCFO hiring brief showing the financial framework the new hire will be building from
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.