For allocators, PE deal teams, and IC members: the map of six agent desks that run a second underwrite on a live deal file with no seller narrative, from the quality of earnings rebuild and blind base case to the debt stress, concentration test, valuation attack, and the one page memo, with a refusal gate that leaves a cell empty rather than print a figure it cannot tie to source.
A short walkthrough of the exact mechanic: where the prompts go, what to answer when the first one asks, and what a good first output looks like. Same for every pack in the library.
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.
One tap. It changes how much Claude explains, and how slowly it goes. You can change it any 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 one question about your work, then guides you step by step until your first output is right. If anything looks wrong, tell Claude what you see, and it fixes it with you.
I am comfortable copy-pasting and following instructions, but I am not a developer. There is nothing to install for this one and no commands to type: it all happens inside Claude. If any instruction below implies a Terminal, translate it into the equivalent click path for me instead. - Plain English. Define jargon the first time it appears. - One step at a time, then wait for me to confirm before the next one. - Tell me what success looks like at each step, and diagnose any error before moving on. Follow the instructions below with those rules applied. This page is a map, not a vault. It contains no prompts. It lists six desk pages, and each desk page holds its own guide and its own prompts. Your job is to help me pick ONE desk and send me there. Do not guess at prompts. The list below is complete. The six desks: 1. Quality of Earnings Desk. Rebuilds adjusted EBITDA off the raw ledger. https://consultance.ai/library/qoe-second-read 2. Underwrite Desk. Re underwrites the base case from public filings, with no seller narrative. https://consultance.ai/library/pe-diligence-pack 3. Credit Desk. Stresses the debt stack and covenant headroom at base and downside. https://consultance.ai/library/private-credit-underwriting 4. Concentration Desk. Tests customer and supplier concentration, churn, and disclosure gaps. https://consultance.ai/library/diligence-red-flag-checklist 5. Valuation Attack Desk. Attacks a valuation you were handed. https://consultance.ai/library/dcf-attack-kit 6. Memo Desk. Writes the one page recommendation, including the decline, with sourced figures. https://consultance.ai/library/ic-memo-desk Your first message asks exactly ONE question and nothing else: "What seat are you in, and what do you need out of the file this week? For example: I do not trust the seller's EBITDA bridge. I need covenant headroom in a downside. I am writing the IC memo on Friday." Wait for my answer. Do not list the desks in that first message, and do not ask a second question. When I answer, do this: - Name ONE desk, not a shortlist. Say in one sentence why that desk fits what I told you. - Give me the exact URL for it from the list above. - Tell me to open that page and start the guided setup there, because the prompts live on that page, not this one. - If my answer is genuinely ambiguous between two desks, default to the Quality of Earnings Desk when the question touches earnings quality, and to the Memo Desk when I have a committee date. Say which default you used. - If I want the full sequence, the order is Quality of Earnings, Underwrite, Credit and Concentration, Valuation Attack, Memo. Still send me to the first one only. Model: pin Claude Opus 5 on the judgment desks, which are quality of earnings, credit, and the memo. After recommending, say once: each desk runs inside my own Claude account, so nothing I paste reaches Consultance, and each desk states its own honest ceiling on its own page. Then stop. Do not reconstruct any desk's prompts from memory.
Got the prompts. Want them wired into your actual stack? We map that on a free AI audit.
Book the free auditFor allocators, PE deal teams, and IC members: the map of six agent desks that run a second underwrite on a live deal file with no seller narrative, from the quality of earnings rebuild and blind base case to the debt stress, concentration test, valuation attack, and the one page memo, with a refusal gate that leaves a cell empty rather than print a figure it cannot tie to source.
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 ↑The desks are six separate guides you run by hand on one deal at a time. Consultance stands the underwrite up as one workspace in your own environment: your data room and ledger exports connected under governed access, the refusal gates wired to your IC standard, and the whole thing handed over so your team owns it. Reply "wire it" for a 30-minute slot.
Book a build call →Prompt sets authored by consultance.ai. Each desk carries its own honest ceiling, stated on its own page. This is decision support, not investment, legal, tax, or accounting advice, and no desk replaces a quality of earnings engagement or a control your LPs expect to see. A named human signs every output before it reaches an investment committee. Your data stays in your own Claude tenant, we never see it.
Want this wired into your stack instead of running it yourself? That is our AI deal desk and finance automation service.
The AI tools, launches, and shifts that actually matter, in plain English. New library drops the moment they land.
What is in this stack
For SBA buyers under LOI and PE deal teams: 13 Claude prompts that rebuild EBITDA from the tax returns, the bank statements and the general ledger instead of the broker recast, interrogate every add back, tie revenue to cash received, recast the working capital peg, and write the findings memo the lender reads with every figure traced to its document.
For PE deal teams and principals: 11 Claude prompts that underwrite a mid-market buyout end to end, the data room read, the LBO model, the quality of earnings, the covenant stress, and the IC memo, with a reconciliation self-check before anything reaches committee. Replaces the $250K associate grind and the $1M Big 4 transaction services engagement.
Underwrite direct lending deals inside Claude: read the data room, build the cash flow and DSCR model, stress test covenants, and draft the IC memo with every figure tied to a source.
A one page checklist of 15 places a deal model hides risk, written for PE deal teams and investment committees who run diligence before they commit capital.
For PE deal teams and IC members handed a DCF to trust: 11 Claude prompts that rank every input by leverage, name the one assumption carrying the valuation, run the bear case, and hand you the cell to attack before the vote. On your own data, inside Claude.
For PE deal teams, CFOs, and family office principals: 12 Claude prompts that write the investment committee memo, the bull case, the bear case, and the one line that sinks the deal, with a reconciliation gate that rederives every figure before the memo assembles. Replaces the principal week and the deal team behind every memo.
The person drowning in this every week is the one who'll actually want it.
The Blind Underwrite Kit is a finance and data build in the consultance.ai AI Build Library. For allocators, PE deal teams, and IC members: the map of six agent desks that run a second underwrite on a live deal file with no seller narrative, from the quality of earnings rebuild and blind base case to the debt stress, concentration test, valuation attack, and the one page memo, with a refusal gate that leaves a cell empty rather than print a figure it cannot tie to source. It fits Allocators, PE deal teams and investment committee members, family office principals, and fund CFOs who need a second read before the exclusivity clock runs out and will not get one from a six figure commercial diligence engagement in time. Setup difficulty is Medium, with 4 plain-English steps.
For allocators, PE deal teams, and IC members: the map of six agent desks that run a second underwrite on a live deal file with no seller narrative, from the quality of earnings rebuild and blind base case to the debt stress, concentration test, valuation attack, and the one page memo, with a refusal gate that leaves a cell empty rather than print a figure it cannot tie to source.
It fits Allocators, PE deal teams and investment committee members, family office principals, and fund CFOs who need a second read before the exclusivity clock runs out and will not get one from a six figure commercial diligence engagement in time.
Medium to set up — one guided setup instruction covering 4 plain-English steps on the resource page.
The desks are six separate guides you run by hand on one deal at a time. Consultance stands the underwrite up as one workspace in your own environment: your data room and ledger exports connected under governed access, the refusal gates wired to your IC standard, and the whole thing handed over so your team owns it. Reply "wire it" for a 30-minute slot.
Prompt sets authored by consultance.ai. Each desk carries its own honest ceiling, stated on its own page. This is decision support, not investment, legal, tax, or accounting advice, and no desk replaces a quality of earnings engagement or a control your LPs expect to see. A named human signs every output before it reaches an investment committee. Your data stays in your own Claude tenant, we never see it.
The Blind Underwrite 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 — see the full AI in finance guide and how we work with CFO teams.