FinancePromptFree
Cap Table Napkin Math
Run dilution on a SAFE + Series A round. Pre, post, founder %, ESOP refresh.
**Role:** Startup CFO consultant who has modeled 100+ cap tables for seed/A/B companies. You know which assumptions blow up the math. **Context:** Current cap table: [founders %, ESOP %, investor classes]. Round details: [$ raised, valuation, pre-money / post-money]. SAFEs outstanding: [if any, with caps + discounts]. ESOP refresh requested: [target % post-close]. Pro-rata participants: [who, how much]. **Task:** Run the dilution math. 1. Compute pre-money valuation, total raised, post-money valuation. 2. Trigger any SAFE conversions at the appropriate cap/discount. Show the per-SAFE conversion math. 3. Apply pro-rata participation. Show pre-conversion % vs post. 4. Apply ESOP refresh — note whether it comes from pre or post (this is the dilution gotcha). 5. Final cap table: every shareholder class with pre-round %, post-round %, $ contribution if applicable. 6. Surface the founders' total dilution this round (combined). **Constraints:** - Show every formula, not just answers - Distinguish pre-money vs post-money ESOP impact - If SAFEs convert with discount AND cap, show both calculations and which one wins per SAFE - Round to nearest 0.1% for ownership, nearest $1k for dollars **Output format:** Step-by-step math + final cap table + 1-paragraph "founders' dilution story" summary.
- Built from
- Role
- Context
- Task
- Constraints
- Output format
How to use it
- Read it, then replace anything in [BRACKETS] with your details — the more concrete the context, the sharper the answer. The Studio lists the blanks for you and can add your project's background.
- Copy it (or download the .md) and paste it into the AI you already use — it knows your work, so that is where the prompt does the most.
- Not sure what it produces? Give it a test run in the Studio first, then refine with self-critique prompting.
Techniques in this prompt
Role-Based
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueChain-of-Thought
Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueOutput-Format
Specifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
Learn this techniqueWorks with
Any chat AI — ChatGPT, Claude, Gemini, Copilot, Grok, Mistral or a local model. The structure does the work, so you are not tied to one vendor or one model version.
New to structured prompts? Start with how to prompt AI, the RCTCO prompt framework this prompt is built on, and role prompting examples.