For PE deal teams and CFOs: three Claude agents that monitor tax and regulation exposure, read a data room like an FDD associate, and draft the IC memo. The diligence work KPMG advisors bill at $400 an hour, run in house.
Never used Claude? It is free and takes 30 seconds to open. Copy the instruction below, paste it into Claude, and it reads this page and walks you through everything, one question at a time.
A short instruction plus a link to this page lands on your clipboard. First copy asks for your email once. That unlocks every button across the whole library.
Free account, no card, 30 seconds. This tab stays open so you can come back.
Open claude.ai ↗Claude reads this page, asks which computer you are on, then guides you step by step until it works. If anything errors, tell Claude what you see, and it fixes it with you.
I want to start running the Advisor to Agent Swap Kit against a live deal or a live entity. Walk me through it. This is NOT a Terminal or coding install. There is no `git clone`, no `npm install`. It all runs inside the Claude app (claude.ai web, Claude desktop, OR Anthropic Workspace under your firm or fund SSO). Treat me like a PE deal lead, corp dev operator, or CFO who has never touched code. What I am setting up: a private Claude Project that holds one engagement — a deal or an entity — with its data room, financials, and tax positions in the Project knowledge, plus the review-gate policy. Once the Project is set up, I paste the router prompt (01), it asks which of the three agents I need and where my data lives, then I run the numbered prompts and Claude produces a tax exposure brief, a QoE bridge, or an IC memo to standard. Walk me through this, one step at a time. Wait for me to confirm before moving on: 1. Open `claude.ai` (web) OR the Claude desktop app. If my fund or firm uses Anthropic Workspace with SSO, sign in through that portal, it keeps the deal data inside our own tenant. For a personal test on a closed deal, Pro on a personal account is fine. 2. Left sidebar, "Projects", "Create Project". Name it after the engagement: e.g. "Project Falcon Diligence" or "Acme Tax FY26". One Project per deal or entity, never mix two. 3. In Project Knowledge, upload or paste: - The data room, financials, CIM, or tax positions for this engagement (whatever you have) - The bundle's `audit-compliance-overlay.md` so Claude maps every output to Pillar Two, ASC 740, ASC 805, the SEC Marketing Rule, ISO 42001, NIST AI RMF, GDPR, SOX 404 - The bundle's `reality-check.md` so the model knows the ceiling (live data wiring, RBAC, retention, human sign-off are your job, not the prompt's) 4. In Custom Instructions, paste: "You are a Big 4 tax Vice Chair, an FDD partner, and a PE Principal in one. Never invent a number, a citation, or a rule. Match every prompt to the data source chosen in prompt 01. Label every estimate ASSUMPTION. End every high-stakes output with a named human sign-off line." 5. Open a new chat inside the Project. Paste prompt 01 (the router) from `kpmg-advisor-agent-swap-kit-prompt-vault.md`. Answer its four blocks: which agent, where your data lives, the context, and the output bar. It confirms back, then you run the numbered prompts for that agent. 6. Read Claude's output and confirm: - Every figure ties to a document you uploaded or an input you gave, or is labeled ASSUMPTION - The diligence numbers are not trusted until prompt 08 returns RECONCILED - The sign-off line at the end is present - No invented rule, citation, or number 7. Pin the model per prompt: Opus 4.8 for reasoning (tax delta, QoE, reconciliation, IC memo), Sonnet 4.6 for the high-volume data-room read (prompt 05). Rules for walking me through this: - One step at a time. Tell me exactly where Projects sits in the Claude UI vs Anthropic Workspace. - Define jargon once: Project, Project Knowledge, Custom Instructions, router, `<review_gate>`, QoE, NWC peg, debt-like items, RECONCILED, Pillar Two. - Never tell me to install anything via Terminal. Deal and finance work runs from a browser or the desktop app. - Do NOT tell me this is "not possible" from the app. It is all in-app. If I hit a wall it is a setup step, not a dead end. - Anti-pattern callouts: - If I say "fund policy blocks claude.ai", tell me about Anthropic Workspace with SOC 2 + SSO, or Claude on AWS Bedrock under our own tenant. Both keep deal data inside our perimeter. - If I say "the data room is huge", tell me to run prompt 05 on Sonnet 4.6, split by folder, and bring findings back to Opus. - If I say "Claude gave a tax figure I cannot trace", stop and re-run prompt 08 (reconciliation). Never trust a number a prompt produced until it ties out a second way. First message: ask "Are you running the tax monitor, the diligence agent, or the IC memo drafter first, and are you on claude.ai personal, firm SSO, or Anthropic Workspace?" Then start with step 1. When the first agent runs cleanly, switch into "engagement readiness mode" and help me run prompt 10 (the IC Q&A red-team) so I walk into committee knowing the fifteen hardest questions before they are asked.
Grab the whole pack as one file, or tap any prompt below to copy it on its own. Placeholders that look like {{THIS}} get swapped for your own numbers — and if you ran Step 1, Claude fills them in for you.
For PE deal teams and CFOs: three Claude agents that monitor tax and regulation exposure, read a data room like an FDD associate, and draft the IC memo
The setup rail and every prompt above are free and stay free. The cost is your time, and the risk of wiring it wrong on live data.
Back to the prompts ↑We would wire the kit into your fund or firm workspace: deal templates, VDR and Capital IQ connectors under governed access, reconciliation gates, and IC-memo delivery so every deal runs the same way.
Book a build call →Original prompt set authored by consultance.ai. Free to use inside your firm or fund. Re-distribution as a paid product requires written permission.
Want this wired into your stack instead of running it yourself? That is our AI strategy consulting service.
The AI tools, launches, and shifts that actually matter, in plain English. New library drops the moment they land.
More like this
Finance and ops teams run 12 Claude prompts for Big 4 consulting workflows like financial analysis and due diligence, shipping advisory work in minutes instead of weeks.
For anyone who signs off on an AI-assisted report, model, or board pack: 13 Claude prompts that fact-check every citation, quote, and number before you ship it.
A second review on financials someone already signed, in your own Claude. 8 prompts test every estimate and reserve, hunt fraud flags, and write a red-flag memo before you trust the numbers.
The person drowning in this every week is the one who'll actually want it.
Free Big 4 Advisory Agent Kit is a big 4 advisory build in the consultance.ai AI Build Library. For PE deal teams and CFOs: three Claude agents that monitor tax and regulation exposure, read a data room like an FDD associate, and draft the IC memo. The diligence work KPMG advisors bill at $400 an hour, run in house. It fits PE deal teams, corp dev, principals, and CFOs who refuse to pay Big 4 rates for tax and diligence work Claude now runs in minutes. Setup difficulty is Easy, with 4 plain-English steps.
For PE deal teams and CFOs: three Claude agents that monitor tax and regulation exposure, read a data room like an FDD associate, and draft the IC memo. The diligence work KPMG advisors bill at $400 an hour, run in house.
It fits PE deal teams, corp dev, principals, and CFOs who refuse to pay Big 4 rates for tax and diligence work Claude now runs in minutes.
Easy to set up — one guided setup instruction covering 4 plain-English steps, plus 10 ready-to-run prompts on the resource page.
We would wire the kit into your fund or firm workspace: deal templates, VDR and Capital IQ connectors under governed access, reconciliation gates, and IC-memo delivery so every deal runs the same way.
Original prompt set authored by consultance.ai. Free to use inside your firm or fund. Re-distribution as a paid product requires written permission.
Free Big 4 Advisory Agent Kit is the starting point. On a free AI audit we map where it fits your stack and what consultance.ai would build around it.
This build comes from our AI consulting and AI implementation practice, serving businesses across the USA and Canada.