Finance and data
AI Discovery Playbook
Run the enterprise AI discovery a consultancy charges around $1,000,000 and months to deliver, in your own Claude, in days. 16 prompts (12 core plus 4 bonus) map the stakeholders, audit the current state, inventory the pain, score every workflow for AI fit, separate the quick wins from the strategic bets, audit the capability gaps, heatmap the adoption risk, design the pilot portfolio, self-check the numbers, and write the board-ready synthesis memo. The work a $1MM discovery engagement delivers, on your own organization. Plus a live discovery-cost calculator.
🔥 optional · live interactive tool
Open the AI Discovery Engagement Cost Calculator
Browser-based. No signup. Drop in your numbers and see the trade in real time. Opens in a new tab so the prompts stay where you left them.
Rent it forever, or own it once.
Run the enterprise AI discovery a consultancy charges around $1,000,000 and months to deliver, in your own Claude, in days
Path A
Set it up yourself
The setup prompt and 16 task prompts are below — free. The cost is your time, and the risk of wiring it wrong on live data.
Jump to the prompts ↓Path B
We wire it into your business
We would deliver a deployed discovery workspace: the prompts loaded into your Claude tenant, governed connectors to your CMDB, process-mining, and data catalog, the fit scoring and risk heatmap wired to your real inventory, an AI governance operating model aligned to NIST AI RMF and ISO 42001, and a board-ready synthesis memo and steering deck. Done with you, then handed over so you own it.
Book a build call →Step 1
Paste this setup prompt — Claude installs it for you
Easy mode · paste this into Claude
Claude installs it for you, step by step.
Never used Claude before? It is free to start. Open it in a new tab, copy the prompt, paste it in. It asks one question, then walks you through everything.
- Step 1Open claude.ai ↗
Sign up free. No card. Takes 30 seconds.
- Step 2
One click. Lands on your clipboard.
- Step 3Paste + send
Claude asks what you need + guides you the rest of the way.
▸Tune the prompt for your level (optional)
▸Preview the prompt (you do not need to read it)
I want to INSTALL the real setup so Claude runs the AI discovery on my actual organization, not just a chat demo. Walk me through it step by step, do not skip the install. Treat me like a CIO or transformation lead who has never built a Claude Project or installed an Office add-in, and define every term once.
This is NOT a Terminal or coding install. There is nothing to compile. It is two paths: a private Claude Project for the discovery inputs (recommended) and an optional Word and Excel add-in for the fit-score matrix, the risk heatmap, and the synthesis memo.
## Path 1 (RECOMMENDED) — a private Claude Project for the discovery
This is where the org charts, process maps, system inventory, and strategy docs live so every prompt reads from one governed place.
Walk me through ONE step at a time, waiting for me to confirm each:
1. **What I need.** A Claude account on a Team or Enterprise plan so the data stays in my tenant. Pin **Opus 4.8**. Nothing to install for this path.
2. **Create the discovery workspace.** In Claude, create a new **Project** named for the organization and the scope. A Project is a private workspace with its own knowledge that other chats cannot see. Your org charts, process maps, system inventory, and strategy docs stay in your own tenant.
3. **Load the inputs.** Drop the org charts, the process maps, the system and data inventory, the strategy docs, and any prior assessments into the Project knowledge. For a single function or workflow, load just that area.
4. **Run the vault.** Run prompt 01, pick your discovery scope (whole enterprise, one function, a single workflow, post-pilot scale-up, M&A integration) and data source (A) upload (or (D) connector if you pull from a CMDB, a process-mining tool, or a data catalog under governed access). Run 02 to 12 in order: stakeholder map, current-state audit, pain inventory, fit score, quick wins, strategic bets, capability-gap audit, adoption-risk heatmap, pilot portfolio, the numbers self-check, and the synthesis memo.
5. **Gate it.** Treat prompt 11 (the numbers self-check) as a hard gate. Any rank flip or out-of-tolerance score blocks the board memo until you understand why. The fit scores and the heatmap are decision-support, a named executive owns the decision to fund pilots. A prompt cannot make that call.
6. **Pressure-test first.** Walk the fit scores and the heatmap with the real function owners before the board reads them. See the 90 day rollout in the bundle.
## Path 2 (OPTIONAL) — Word and Excel add-in for the matrix, heatmap, and memo
If I want the fit-score matrix and the risk heatmap to live in real cells and the synthesis memo in a real document:
1. In Excel or Word (Microsoft 365 desktop or web): **Home** or **Insert** tab, **Add-ins** / **Get Add-ins**, search **"Claude"**, **Add**. Tell me where the button is in my version.
2. Sign in to the docked Claude side panel.
3. In vault prompt 01 choose data source (C) add-in. For prompt 05 (fit score) and prompt 09 (heatmap) say "build this into my workbook as a real scored matrix," so the scores recompute and the prompt 11 self-check runs on live cells. For prompt 12 say "draft this in my Word document."
4. Pin **Opus 4.8** for the scoring, the heatmap, the self-check, and the memo.
## Rules for walking me through this
- One step at a time. Define every term once: Project, knowledge, stakeholder map, current-state audit, fit score, rubric, quick win, strategic bet, capability gap, adoption-risk heatmap, pilot portfolio, stage-gate, AI governance, NIST AI RMF, ISO 42001, `<review_gate>`, `{{TOKEN}}`.
- Do NOT tell me a step is "not possible." If the Office add-in is missing, check Microsoft 365, try the web version, or AppSource. For the Project path there is nothing to install.
- Never paste confidential strategy docs or personal data into a public Claude window outside a Project. Use a Project with your tenant controls; respect your data governance.
- This produces decision-support, not the decision. It does not replace the named executive who owns the strategy, the AI governance program (NIST AI RMF, ISO 42001) you need before any build, or the execution and change management that is the real work. Read the audit and compliance overlay before you act on it. Not legal or compliance advice.
First message: ask me "Path 1 (Claude Project for the discovery inputs, recommended) and do you also want Path 2 (Office add-in for the fit matrix and memo)? And is this discovery for the whole enterprise, one function or business unit, or a single high-value workflow?" Then start step 1.Step 2
Step 1 installed it. Now run these 16 prompts on your own data.
the vault
The 16 prompts
Tap a prompt to jump to it. Hit copy. Replace the tokens. Paste into Claude Opus 4.7.
where it breaks
Before you connect live data
- • Run dummy data first. Real client data is not a test bed.
- • API keys never go in a public repo. Use env vars and a secrets manager.
- • Add logging, access control, monitoring, and a rollback path before launch.
- • Read the license. Forking a repo without checking is how lawsuits start.
license note
Credit the original author
Prompt set authored by consultance.ai. McKinsey and QuantumBlack are referenced as the discovery standard the pack matches, no affiliation implied. Your organizational data stays in your own Claude tenant; we never see it. This produces decision-support, not the decision; a named executive owns the call to fund pilots, the execution and change management is the real work, and a formal AI governance program (NIST AI RMF, ISO 42001, EU AI Act and GDPR where in scope) is required before any build. Not legal, compliance, or investment advice.
the newsletter
AI news worth opening.
The AI tools, launches, and shifts that actually matter, in plain English. New library drops the moment they land.
100% freeNo paywall, everUnsubscribe anytime
Want this running in your business, not just your laptop? We build it and hand you the keys.
More like this
Other builds worth a weekend
Finance and data
Setup guide →Fincept Terminal
Kill your Bloomberg envy with a free download. Live stocks, bonds, crypto, and 37 AI agents that pick like Buffett, Munger, and Lynch.
Finance and data
Setup guide →Finance Reporting Pack — Claude vs the BI stack
AI now builds financial reporting that rivals JPMorgan analysts, packaged as 12 prompts your finance team runs on its own data. Board P&L packs, 3-statement models, variance commentary, KPI scorecards, cash forecasts, and consolidations, for the price of a Claude seat instead of Power BI plus Tableau plus a BI hire. Plus a live Reporting Stack Spend Calculator.
Finance and data
Setup guide →Firefly CFO Trust Ladder
No CFO trusts AI with company books on day one. Firefly III plus Claude is the trust ladder. Personal books first. Real reps. Then the company.