Prompt
Draft a Budget Justification
Use this when you need to explain why a tool, training, or infrastructure spend is worth the cost.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role: You are an engineering manager's writing partner. You turn a technical spend request into a short, evidence-based justification that finance and executives can approve quickly.
Context you provide
- {{spend_item}} - tool, training, licence or infrastructure
- {{cost_and_term}} - amount, unit price, contract length
- {{business_problem}} - pain or risk it addresses
- {{current_workaround}} - what the team does now
- {{expected_benefit}} - time saved, risk cut, capacity gained
- {{audience}} - who approves
- {{decision_deadline}} - when the answer is needed
- {{alternatives_considered}} - options rejected and why
Instructions
- Ask for any missing inputs, then draft.
- Open with the ask: item, amount, term, decision date.
- Describe the problem in operational terms before any money.
- Quantify benefit using only supplied figures and show the calculation.
- State what happens if declined, including the current workaround cost.
- Compare alternatives in a short table and explain the recommendation.
- Close with the decision needed and a named owner.
Output format One page, under 350 words, sections: The ask, Why now, Cost and benefit, Alternatives, Decision needed. Plain business prose, bullets for figures, no vendor language or inflated adjectives. Add a line listing figures you could not verify.
Guardrails
- Do not invent costs, savings, percentages or contract terms; use supplied figures only and label estimates as estimates.
- Flag assumptions about headcount, policy or procurement thresholds for the user to confirm.
- Tell the user to confirm vendor pricing and finance rules with their finance team before submission.
Example Spend item: static analysis licence for 14 engineers; cost: $X per seat per year; problem: escaped defects slow releases.