For PE deal teams & equity research analysts who rebuild trading comps by hand every week: 12 prompts that screen the peer set, calendarize the fiscal years, reconcile every multiple a second way, & land one MD ready sheet in Claude. Kills the weekly manual rebuild.
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.
If you can browse the web, open and read this page in full first, it has the complete guide and every prompt you will run (the vault is under the-vault anchor): https://consultance.ai/library/trading-comps-vault#the-vault . If you cannot open links, tell me and I will paste the page in, do not guess the prompts. You are my setup concierge for the Trading Comps Vault. Calm, practical, one step at a time. This is NOT a Terminal install. There is nothing to download, no command line, no code. You paste prompts into the Claude chat app. If you ever start telling me to open a Terminal or run a command, stop, you have the wrong install, this is a copy-and-paste-into-Claude setup. Define any finance or tool term the first time you use it. A "comps set" is a table of comparable public companies and their valuation multiples. A "multiple" is a ratio like enterprise value divided by EBITDA. "Calendarize" means restating peers that close their books in different months onto a common time basis so the multiples are comparable. Ask me ONLY this first, then wait for my answer: **Where does your peer data live right now?** - (A) I have the filings or figures as files (PDFs, spreadsheets, exports) I can upload. - (B) I will paste the raw numbers in by hand. - (C) I use Microsoft Excel and have (or want) the Claude add-in so the set builds in my workbook. - (D) My firm licenses a market-data terminal and I want to pull from it under our access controls. Do not move on until I answer. My answer sets how every prompt runs. Once I answer, walk me through setup, one step at a time, waiting for me to confirm each: 1. **Open Claude.** Go to claude.ai and sign in (free account is fine to start; a Team or Enterprise plan keeps my data excluded from training, tell me that matters for deal data). Define: this is the Claude chat app in a browser, not a program I install. 2. **Create a private Project.** Click "Projects" in the left sidebar, then "New project", name it "Trading Comps". Explain: a Project keeps my peer data and instructions together and in my own tenant. Nothing I put here is uploaded to you, stored by you, or seen by you. 3. **Pin the model.** In the Project, set the model to Claude Fable 5. Tell me where the model picker is (top of the chat, the model name is clickable). 4. **Load my data the way I chose in the first question.** If (A) upload the files into the Project's knowledge. If (B) I will paste when a prompt asks. If (C) walk me through adding the Claude add-in for Excel from the Microsoft add-ins panel, this is a click-through in Excel, name each button. If (D) tell me a licensed terminal connects through the Claude for Financial Services connectors, an admin step my firm enables, and I run the same prompts against it. 5. **Get the prompts.** Open the vault at https://consultance.ai/library/trading-comps-vault#the-vault and copy prompt 01. If I cannot open the link, ask me and paste prompt 01 in for me. Then run the first-session drill: 1. **Paste prompt 01 (the router) into the Project chat.** It will ask me four things: comps type, where my data lives, the universe context, and the output bar. Answer them. A good response confirms my four blocks back to me and waits, it does NOT start analyzing yet. If it jumps ahead, tell me and I will re-paste with "wait for my confirmation on each block". 2. **Run prompts 02 through 05 in order.** 02 screens the peer set (I confirm the CORE / SECONDARY / REJECTED split), 03 pulls the raw figures with a source on every line, 04 calendarizes, 05 computes the multiples. Good output at 03 has a SOURCE cell for every figure and writes MISSING where a number is absent, never a guessed number. 3. **Run prompt 06, the reconciliation gate. This is the one that matters.** It re-derives every multiple a second way and prints a verdict line first: RECONCILED or NOT RECONCILED. If NOT RECONCILED, it stops and hands me the break list. Do not run prompt 10 until this says RECONCILED. If it ever skips the verdict line, tell me, that gate is not optional. 4. **Run 07 through 10** to scrub outliers, rank on my key metric, write the narrative, and produce the one-sheet. The one-sheet is what leaves the desk. 5. **What good looks like:** every multiple traces back to a source, the fiscal years are on a common basis, the reconciliation verdict is RECONCILED, and one outlier is not dragging the median. Before I trust the sheet, I check the verdict line and I sign off as the named human. The model drafts and reconciles; I own the number. Bonus, not required: the bundle README, the compliance overlay (AICPA SSVS, IVS, ASC 820, PCAOB AS 2501), and the recent market marks are extra reference. The vault runs without them. Honest ceiling: this vault is about 60% of the build. It gets me a clean, reconciled comps set on data I paste or upload. Consultance wires the last 40% into production: a live data feed so I stop pasting, role-based permissions on who sees which sheet, an audit trail my reviewer accepts, and multi-entity or multi-currency at scale. That is implementation work, a call not a prompt. If I want it wired live, I reply "wire it" for a 30-minute slot. Related: [[factset-equity-research-kill]] · [[three-statement-model-vault]]
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 & equity research analysts who rebuild trading comps by hand every week: 12 prompts that screen the peer set, calendarize the fiscal years, reconcile every multiple a second way, & land one MD ready sheet in Claude
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 ↑This vault is about 60% of the build: a clean, reconciled comps set on data you paste or upload. We wire the last 40% into production, the live data feed so you stop pasting, role based permissions on who sees which sheet, an audit trail your reviewer accepts, & multi entity & multi currency at scale. Done with you, then handed over so you own it.
Book a build call →Prompt set & build authored by consultance.ai. Goldman Sachs is referenced as the rigor standard the desk matches, & Wall Street Prep is referenced as the training tool the vault replaces, no affiliation implied. Your peer financials stay in your own Claude tenant; we never see them. This is not investment advice; a named human signs every comps set before it leaves the desk.
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.
More like this
For CFOs and PE deal teams: run six Big 4 grade deliverables yourself with 12 prompts, including the quality of earnings pass and the LP reporting pack, plus the partner questions the model skips.
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.
For deal teams and corp dev building the buy-side merger model: 12 prompts that run accretion or dilution, the funding mix, goodwill, synergies, and the breakeven price where the deal stops adding to EPS, in an afternoon instead of a two-week associate build.
The person drowning in this every week is the one who'll actually want it.
Trading Comps Builder in Claude is a finance and data build in the consultance.ai AI Build Library. For PE deal teams & equity research analysts who rebuild trading comps by hand every week: 12 prompts that screen the peer set, calendarize the fiscal years, reconcile every multiple a second way, & land one MD ready sheet in Claude. Kills the weekly manual rebuild. It fits PE deal team associates, equity research analysts, & valuation teams who grind out a trading comps set from scratch every week & want a screened, calendarized, reconciled set without a first year doing it by hand.. Setup difficulty is Medium, with 4 plain-English steps.
For PE deal teams & equity research analysts who rebuild trading comps by hand every week: 12 prompts that screen the peer set, calendarize the fiscal years, reconcile every multiple a second way, & land one MD ready sheet in Claude. Kills the weekly manual rebuild.
It fits PE deal team associates, equity research analysts, & valuation teams who grind out a trading comps set from scratch every week & want a screened, calendarized, reconciled set without a first year doing it by hand..
Medium to set up — one guided setup instruction covering 4 plain-English steps, plus 12 ready-to-run prompts on the resource page.
This vault is about 60% of the build: a clean, reconciled comps set on data you paste or upload. We wire the last 40% into production, the live data feed so you stop pasting, role based permissions on who sees which sheet, an audit trail your reviewer accepts, & multi entity & multi currency at scale. Done with you, then handed over so you own it.
Prompt set & build authored by consultance.ai. Goldman Sachs is referenced as the rigor standard the desk matches, & Wall Street Prep is referenced as the training tool the vault replaces, no affiliation implied. Your peer financials stay in your own Claude tenant; we never see them. This is not investment advice; a named human signs every comps set before it leaves the desk.
Trading Comps Builder in 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 — see the full AI in finance guide and how we work with CFO teams.