---
name: al-689-run-a-private-equity-diligence-agent-like-a-27-hour-analy
description: "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. Use when the user wants help with ultra-long-horizon pe / ib deal diligence agent (finance) for a small business."
---

# 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

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.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- Buy-side PE / IB coverage
- Codename
- Folder / VDR
- IC memo, comps, LBO sketch, risk list

## Instructions

Do the task below with the user's inputs in place of each [bracket].

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.

## Safety checks (share these with the user)

- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Claude, ChatGPT, Gemini, your VDR / data room, spreadsheet tools
- Based on this real-world example: https://www.juliusresearch.ai/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-689-run-a-private-equity-diligence-agent-like-a-27-hour-analyst/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/