For private credit funds, direct lenders, and CLO desks: the map of ten agent desks that run origination through surveillance inside your own Claude, from the underwrite and the data room to quality of earnings, the tape, covenant tests, payment rec, the IC memo, and the forensic second read, plus the order to install them in.
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.
Set me up with The Private Credit Agent Stack in my own Claude. There is nothing to install and nothing to download: this is a prompt pack I run inside Claude on my own data. Guide: https://consultance.ai/library/private-credit-stack What it does: For private credit funds, direct lenders, and CLO desks: the map of ten agent desks that run origination through surveillance inside your own Claude, from the underwrite and the data room to quality of earnings, the tape, covenant tests, payment rec, the IC memo, and the forensic second read, plus the order to install them in. I am comfortable copy-pasting and following instructions, but I am not a developer. Rules: - Plain English. Define jargon the first time it appears (repo, env var, port, dependency). - One step at a time. Exact command in a code block. Tell me which app to paste it into (Terminal on Mac, PowerShell on Windows). - One sentence per command explaining what it does and what success looks like. - After each command, wait. I will tell you the output before you move on. - If a tool is missing (git, node, docker, python), give me the one-line install for my OS first. - If something errors, diagnose before the next step. Do not skip. First message: ask only "What is your operating system, macOS, Windows, or Linux?" Then start step 1. Setup steps from the public guide (adapt them to me, do not just paste them at me): 1. Start with the Underwriting Desk on one live deal. A stack installed against a credit memo deadline survives, a stack installed on a quiet Sunday does not. 2. Add the Data Room and Quality of Earnings Desks next. The covenant tests and the recovery view inherit whatever the earnings rebuild gets wrong. 3. Add the Tape and Surveillance Desks once you hold facilities worth watching between committee dates, then Payment Rec and Private Asset Rec so the servicer report is not a PDF you hope is right. 4. Pin Claude Opus 5 for underwriting, covenants, and the memo. The IC Memo Desk goes last, it packages what the other nine produce, and the Forensic Desk is the gate before anything reaches committee. Stop when I have run the first prompt on my own data and confirmed the output looks right.
Got the prompts. Want them wired into your actual stack? We map that on a free AI audit.
Book the free auditFor private credit funds, direct lenders, and CLO desks: the map of ten agent desks that run origination through surveillance inside your own Claude, from the underwrite and the data room to quality of earnings, the tape, covenant tests, payment rec, the IC memo, and the forensic second read, plus the order to install them in.
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 ten separate guides you run by hand. Consultance stands the stack up as one workspace in your own environment: the desks your book actually needs, your VDR, loan admin, and servicer feeds connected under governed access, review gates where your IC requires them, 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. The desks do not talk to each other, you run them by hand and carry output between them yourself. This is decision support, not a credit rating, not a covenant certification, and not investment advice. No desk replaces a credit officer, a borrower call, or a control your LPs expect to see. A named human signs every output before it reaches 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
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.
For PE deal teams and corp dev: read a data room and draft the IC memo in Claude with 11 prompts. Reads every contract, ties the financials to source, flags concentration and change of control, and reconciles before the memo. Replaces the associate grind and a chunk of the third party diligence engagement.
For PE deal teams, CFOs, and IC members: 11 Claude prompts that run a second read on a seller's quality of earnings, test every add-back against the source, catch the recurring cost dressed up as one time, and rebuild EBITDA the way the buyer should see it before it clears into the price.
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 private credit and CLO teams tracking 500-plus loans by hand: 11 Claude prompts that read the loan tape and credit agreements, recompute every covenant test with the period cited, reconcile payments against the servicer report, and write the weekly exception memo, every flag carrying its clause and number so you can check it in seconds.
For private credit funds and direct lenders: 11 Claude prompts that monitor covenants, recalculate the borrowing base, read amendment redlines, and draft the LP note, on documents that never leave your own tenant, so a covenant drift is caught before quarter end, not after.
For CFOs, controllers, and fund accountants: 10 prompts plus an offline extractor that match scanned bank, custodian, and brokerage statements to your ledger in seconds and return only the breaks, on your own machine. An alternative to BlackLine.
For fund operations teams matching payment agent notices by hand: 12 Claude prompts that parse notices, match cash to the custodian file, reconcile units, and land every break as green, yellow, or red with the evidence attached. Runs in your own Claude, on your own data.
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.
8 prompts that turn Claude into a forensic accountant for any financial statement. Catch fake cash, revenue tricks, and the red flags hiding in the footnotes before you invest, short, or lend.
manual now, installed when you're ready
The free version above. It runs this read on a file you paste in, in your own Claude. Yours to keep.
The same read, wired into your private credit stack, running the second a report lands. Nothing to upload, no new login.
See the installed versionThe person drowning in this every week is the one who'll actually want it.
The Private Credit Agent Stack is a finance and data build in the consultance.ai AI Build Library. For private credit funds, direct lenders, and CLO desks: the map of ten agent desks that run origination through surveillance inside your own Claude, from the underwrite and the data room to quality of earnings, the tape, covenant tests, payment rec, the IC memo, and the forensic second read, plus the order to install them in. It fits Private credit PMs, direct lending analysts, CLO managers, PE credit teams, and family offices with a private debt sleeve who have seen the individual packs and want one map of which desk to install first instead of installing all ten in a weekend and using none. Setup difficulty is Easy, with 4 plain-English steps.
For private credit funds, direct lenders, and CLO desks: the map of ten agent desks that run origination through surveillance inside your own Claude, from the underwrite and the data room to quality of earnings, the tape, covenant tests, payment rec, the IC memo, and the forensic second read, plus the order to install them in.
It fits Private credit PMs, direct lending analysts, CLO managers, PE credit teams, and family offices with a private debt sleeve who have seen the individual packs and want one map of which desk to install first instead of installing all ten in a weekend and using none.
Easy to set up — one guided setup instruction covering 4 plain-English steps on the resource page.
The desks are ten separate guides you run by hand. Consultance stands the stack up as one workspace in your own environment: the desks your book actually needs, your VDR, loan admin, and servicer feeds connected under governed access, review gates where your IC requires them, 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. The desks do not talk to each other, you run them by hand and carry output between them yourself. This is decision support, not a credit rating, not a covenant certification, and not investment advice. No desk replaces a credit officer, a borrower call, or a control your LPs expect to see. A named human signs every output before it reaches committee. Your data stays in your own Claude tenant, we never see it.
The Private Credit Agent Stack 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.