Run a private-equity diligence agent like a 27-hour analyst job: sift a messy data room, build valuation assumptions and produce an auditable memo a human partner still signs: AI agent prompt
Julius Research's DeepFinance benchmark (updated Nov 5, 2026) measures models on real private equity and investment banking workflows: 21 anonymised deal tasks averaging 27.1 human hours each, with about 19 data-room files and 84 rubric criteria per task covering diligence, valuation, assumptions and auditable deliverables. Top configurations (Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra) score around 54–55% mean rubric—showing agents can tackle multi-day deal work but still miss human judgment on assumptions and input selection. Use it as a template for structuring long-horizon finance agents with rubrics and human sign-off.
The prompt
Design a DeepFinance-style diligence agent for [buy-side PE / IB coverage] on deal [codename]. Data room: [folder / VDR]. Deliverables: [IC memo, comps, LBO sketch, risk list]. Hard rules: never invent numbers not in the room; every claim cites a file+page; flag missing data instead of guessing; partner signs the memo—agent drafts only; no outbound emails. 1) Break the ~20–30 hour human job into agent phases with timeboxes. 2) Write the rubric (at least 15 graded criteria). 3) Draft the orchestrator + specialist agent prompts (model selection, quality gate under 8/10 retries). 4) Human review checklist before IC. Output a deal-team runbook.
Fill in the blanks, then copy
This prompt has 4 [bracket]s to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into Claude, ChatGPT, Gemini and review the answer before you use it.
Works with: Claude, ChatGPT, Gemini, your VDR / data room, spreadsheet tools
Real-world example: juliusresearch.ai/
Featured in: AI prompts for writing SOPs, reports, policies and checklists
Before you use it: what to check
Already built into this prompt
- Hard rules: never invent numbers not in the room; every claim cites a file+page; flag missing data instead of guessing; partner signs the memo—agent drafts only; no outbound emails.
Check yourself
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free