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.
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 Big 4 prompts from this vault against a live engagement. Walk me through it.
This is NOT a Terminal or coding install. There is no `git clone`, no `npm install`. It is all inside the Claude app (claude.ai web, Claude desktop, OR Anthropic Console under firm SSO). Treat me like a tax / audit / advisory partner or senior manager who has never touched code.
What I am setting up: a Claude Project (or firm Workspace) that holds the engagement context — client industry, jurisdictions, governing framework — plus the firm's review-gate policy. Once the Project is set up, I paste one of the 16 prompts, replace the `{{TOKENS}}`, and Claude produces a tax memo, audit program, ERM register, PE diligence chapter, or legal opinion to the firm's 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 firm uses Anthropic Workspace with SSO, sign in through the firm portal — that keeps the engagement data inside our tenant. For lighter testing on closed matters, Pro + a personal account is acceptable.
2. Left sidebar → "Projects" → "Create Project". Name it after the engagement: e.g. "Acme Corp Tax FY26" or "Project Falcon Diligence".
3. In Project Knowledge, paste / upload:
- The client profile (sector, jurisdictions, revenue, fiscal year, governing framework — IFRS / US GAAP / UK GAAP)
- The engagement letter scope (so Claude refuses anything outside scope)
- The firm independence note for this client (which related-entity restrictions apply)
- The bundle's `audit-compliance-overlay.md` so Claude maps every output to PCAOB AS / AICPA AU-C / IFRS 15 / ASC 606 / GDPR / SOC 2 / ABA TriBar
- The bundle's `reality-check.md` ceiling note (workpaper retention, partner sign-off, multi-engagement scale — all human work, not prompt work)
4. In Custom Instructions, paste: "You are a senior partner at a Big 4 firm. Output only what passes the `<review_gate>` and `<constraints>` blocks. Never invent a case citation, statute number, or revenue ruling. Flag anything outside the engagement letter scope. End every output with a 'partner to verify' list."
5. Start with prompt 02 (Audit Program Architect). Copy from `kpmg-12-prompt-vault.md`, open a new chat inside the Project, paste, replace `{{TOKENS}}` with the client + material account + risk list, send.
6. Read Claude's output. Confirm:
- Every procedure maps to a specific assertion (existence, completeness, accuracy, valuation, R&O, presentation)
- Sample sizes cite AICPA guidance or PCAOB AS 2315
- "Partner to verify" list at the end is non-empty
- No invented case citations or revenue rulings
7. Once prompt 02 works, run prompts 01 (Tax Advisory), 04 (PE Diligence), 10 (SOX Controls Testing), 13 (PE 100-Day Plan from bonus extras). Those five cover the highest-dollar work the firm bills.
Rules for walking me through this:
- One step at a time. Tell me exactly where Projects sits in the Claude UI vs Anthropic Console.
- Define jargon once: Project, Project Knowledge, Custom Instructions, `<review_gate>`, assertion, BFOQ, TriBar, AS 1215, AU-C 230.
- Never tell me to install anything via Terminal. Big 4 work runs from a browser or the desktop app — IT is unlikely to whitelist Terminal-based AI for client engagements.
- Anti-pattern callouts:
- If I say "firm policy blocks claude.ai", tell me about Anthropic Workspace with SOC 2 + SSO, or Claude on AWS Bedrock under our firm tenant. Both keep client data inside our security perimeter.
- If I say "my engagement letter does not mention AI", flag the language to add (per the audit-compliance overlay) and walk me through the conversation with general counsel.
- If I say "Claude wrote a case cite that does not exist", tell me to ALWAYS run "partner to verify" against Westlaw / LexisNexis / official statute lookups before any client delivery. Never trust a citation that came from a prompt.
First message: ask "Are you on Claude web (personal account), claude.ai under firm SSO, or Anthropic Workspace — and is this engagement governed by US GAAP, IFRS, UK GAAP, or another framework?" Then start with step 1.
When prompts 01, 02, 04, 10, 13 run cleanly, switch into "engagement readiness mode" and help me run the audit committee Q&A drill (bonus prompt 15) so the firm is ready for the next quarterly meeting.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.
KPMG just rolled Claude out to 276,000 employees across 138 countries. We packaged the 12 Big 4 workflows behind it — the work firms charge $500K for, runnable yourself in 5 minutes.
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 wire the vault into a firm-branded workspace: client templates, redaction guardrails, partner review gates, and Notion or SharePoint delivery so the workflow runs the same way every time. You get Big 4 output without an unreviewed deliverable reaching a client.
Book a build call →Original prompt set authored by consultance.ai. Free to use inside your firm. 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
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.
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.
Big 4 Consulting Prompts for Claude is a big 4 advisory build in the consultance.ai AI Build Library. 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. It fits operators, finance leaders, in-house counsel, and consultancy founders who refuse to pay $500K for work Claude now ships in minutes. Setup difficulty is Easy, with 4 plain-English steps.
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.
It fits operators, finance leaders, in-house counsel, and consultancy founders who refuse to pay $500K for work Claude now ships in minutes.
Easy to set up — one guided setup instruction covering 4 plain-English steps, plus 12 ready-to-run prompts on the resource page.
We would wire the vault into a firm-branded workspace: client templates, redaction guardrails, partner review gates, and Notion or SharePoint delivery so the workflow runs the same way every time.
Original prompt set authored by consultance.ai. Free to use inside your firm. Re-distribution as a paid product requires written permission.
Big 4 Consulting Prompts for Claude 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.