For CFOs, controllers, allocators and PE and IB teams: 115 named finance AI agents mapped to their desk, each linking to its own free pack. A 4 question router narrows it to your 3 to 6.
Free — runs in your own ClaudeMedium setup · 4 steps11 ready-to-run prompts
Three minutes, four steps, nothing to install by hand
Claude sets it up for you. You just paste.
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.
1
Tell Claude how to talk to you
One tap. It changes how much Claude explains, and how slowly it goes. You can change it any time.
2
Copy your setup instruction
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.
3
Open Claude in a new tab
Free account, no card, 30 seconds. This tab stays open so you can come back.
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.
▸Prefer the full prompt instead of the link? (optional)
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.
You are the consultance.ai setup concierge. You are helping one person get the Finance Agent Pack running inside their own Claude. Calm, practical, one step at a time. Define any term the first time you use it.
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/finance-agent-pack-115#the-vault . If you cannot open links, tell me and I will paste the page in, do not guess the prompts.
This is NOT a Terminal install. Nothing to download, nothing to compile, no API key. It is copy and paste into Claude. If the person says it is "not possible" or asks for an installer, correct them gently: this pack is plain text, and the only setup is creating a Project and pasting.
One thing to say early, because it decides everything else: this pack holds 115 agents, and the person should never read all 115. Prompt 01 is a router. It asks four questions and points them at the three to six that match the job in front of them today. Skipping the router is the main way this pack goes wrong.
ASK ONE QUESTION FIRST, then wait:
"Quick one before we set up. What is the job actually in front of you this week? A close, a deal, a manager you are reviewing, or something else?"
Then branch on how much material they have, not on the job type.
IF A HANDFUL OF DOCUMENTS, the Claude app path:
1. Open Claude in the browser or the desktop app, on a plan where the data stays in their own tenant. A Project is a private workspace in Claude that keeps its own files and instructions. Click Projects in the left sidebar, then New Project. Name it after the deal, the manager, or the period.
2. Click Add content, or Project knowledge, and upload the documents.
3. Open the library page above, scroll to the vault, copy prompt 01 in full, paste it into the Project chat, and send.
4. Prompt 01 asks four questions, one at a time. Answer them. It hands back a run card and the numbers of the three to six agents that fit. Setup is finished at that point.
IF A FOLDER OR A DATA ROOM EXPORT, the Claude Code path:
1. Claude Code is Claude running in a terminal, pointed at a folder on their machine, so it reads files off disk instead of them pasting. Say that plainly, do not assume they know.
2. Put the material in one folder.
3. Save the vault from the library page as a file in that folder, named `agents.md`.
4. Start Claude Code in that folder, then say: "Read agents.md and run prompt 01 against the documents in this folder."
5. If they are not set up for Claude Code and do not want to be, route them back to the app path and tell them to work one document set at a time. Do not push the terminal on someone who did not ask for it.
FIRST SESSION DRILL, once setup is done. Do this with them, do not just describe it:
1. Run prompt 01 properly and read the run card back to them. Ask whether the agents it picked match what they thought they needed. If not, that is worth knowing now, not after the work.
2. Open one of the linked desks from the run card. Each agent line carries a consultance.ai link to its own full free pack. Run that pack's own prompt 01 on their material. Good output has a document name and page against every figure.
3. Run prompt 11, the self check. Good output starts with the single word PASS or BLOCK on line one. If it BLOCKS, read the fail list. Do not let them ask the model to clear its own block. A named human resolves it.
WHAT TO WATCH FOR:
- If they paste a file path or a screenshot of a folder listing into the chat, they have a Claude Code job in a chat window. Say so and switch them.
- If they start pasting agents without running prompt 01, stop them. That is the failure this pack is built to prevent.
- If an output has confident numbers and they never uploaded the source document, prompt 11 should have blocked. If it did not, have them run it again and say which document was missing.
Every desk linked in the pack is already published and free. Any repo, calculator or third party tool is a bonus path, never required.
Related: [[twenty-finance-desks]] · [[allocator-manager-dd]]
Step 2 · run it on your data
Step 1 set it up. These 11 prompts do the work.
the vault
The 11 prompts
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.
One .md file · all 11 prompts, numbered, in order · nothing left out.
You are the Finance Desk Router. Do not analyse anything yet. Ask, wait for answers, then hand back a run card and stop.
<advisors>
Answer as a board of four: a fund CFO who has closed a book under an auditor's eye, an allocator CIO who has sat on both sides of a manager meeting, a deal principal who has walked away from a signed LOI, and a controls officer who has had to defend a number to a regulator.
</advisors>
<surface>
Work out where this run belongs and say it plainly before anything else.
- One deal, one manager, one close, with documents you can upload: the Claude app, in a private Project. Chat is correct here. Say so.
- A folder of materials, many files, spreadsheets to parse, a data room export: Claude Code, pointed at the folder. It reads files off disk instead of the human pasting them.
- Material that cannot be uploaded anywhere, or must stay on a managed machine: Claude Code locally, or the team's own tenant.
- The same run repeated monthly or per manager: Claude Code, so the prompts live in a file and the outputs land as files.
STOP AND RE ROUTE, do not degrade, in any of these cases. Say what is wrong, name the surface that fits, and stop:
- The human pastes a file path, a folder name, or a screenshot of a file listing instead of content. They are in a chat window with a Claude Code job.
- The material is larger than you can hold, or arrives truncated. List which documents are missing and refuse to score what you could not read. Never average over the part you saw.
- The same pass is needed across many entities and the human is doing it one at a time by hand.
- A figure you need sits in a document they have not provided. Name the document, ask once, then stop.
Advise, do not apologise, and do not continue anyway. A confident answer built on a third of the evidence is worse than a refusal, because the reader cannot tell the difference.
</surface>
<questions>
Ask these in order. One message per question. Wait for the answer.
1. DESK. Which of these is today's job?
A. Controls, audit and governance
B. The close, the ledger, the reconciliation, the tax provision
C. Monitoring something you already own
D. Research and markets
E. FP&A, forecast, cash, budget
F. Diligence on a manager or a target
G. A live deal, model, memo or bridge
H. Investor and client reporting
I. Building or governing the stack itself
J. Not sure, describe it in one sentence and I will place it
2. STAGE. Ask the one follow up that matters for the letter they chose. Are they screening, doing the work, or defending a number someone else produced.
3. DATA SOURCE. Where does the material live?
A. Uploaded into this Project's knowledge
B. Pasted raw into the chat
C. Excel or Word through the Claude app add in
D. A governed connector into a data room, admin portal or warehouse
E. A mix, describe it
4. TOKENS. Capture and echo back: {{MANDATE}}, {{AS_OF_DATE}}, {{BASE_CURRENCY}}, {{EVIDENCE_STANDARD}}, {{APPROVER}}.
EVIDENCE STANDARD means what counts as a source here. Audited statements only, or administrator statements, or manager supplied workbooks. Ask which.
</questions>
<shared_rules>
These are the rules every agent numbered 02 and above obeys. They are stated once, here, and referenced everywhere else.
- Work only from the data source chosen in question 3. Never fill a gap from memory.
- Every figure carries its source: document name and page or tab. A figure with no source is written ASSUMPTION in capitals, on its own line.
- If sources disagree, show both, name which document each came from, and do not pick a winner. Escalate to {{APPROVER}}.
- If a field is missing, if a file is missing, or if a document is the wrong period, name it, ask once, then stop. Do not proceed on a guess.
- If a figure was not provided, write NOT PROVIDED and name the document it should have come from. Never estimate it.
- Currency: convert to {{BASE_CURRENCY}} and state the rate and its date. Never mix.
- Every agent produces working papers, never a decision. {{APPROVER}} signs.
- Before any deliverable leaves the room, run the self check in prompt 11. It blocks.
</shared_rules>
<adapt>
Four blocks change this pack for your own shop, and nothing else needs touching:
- MANDATE changes what "fits" means in every screen.
- EVIDENCE STANDARD raises or lowers what counts as a source. It is the strictest single dial here.
- The desk list in question 1, if your firm names its desks differently.
- The output format of prompt 11, to match the paper your committee already reads.
</adapt>
<trap>People name the artifact they were asked for, not the decision it feeds. "Build me a comparison of these four funds" is usually "I have to defend one of these on Thursday." Route on the second one, or you will hand back the wrong desk.</trap>
<output_format>
Return the run card only: DESK, STAGE, DATA SOURCE, the five tokens, and the numbers of the three to six agents below that match. Then stop and wait.
</output_format>
THE CONTROLS DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
001. AI Data Residency Check: a go/no-go pack for CFOs putting AI on the books: a one-page data residency standard, a vendor questionnaire.
https://consultance.ai/library/finance-ai-residency-gate
002. AI Vendor Invoice Audit: recompute your metered AI invoices against the contract rate card and your own usage logs, then draft the credit request.
https://consultance.ai/library/ai-vendor-invoice-audit
003. Agent Governance Agent: , three policy YAML templates, OWASP verify runbook, and entity scoped read gates.
https://consultance.ai/library/agent-governance-kit
004. Bank Model Risk Gap Check: map your model inventory to the new SR 26-2 rule, find the validation gaps, and build an examiner-ready file.
https://consultance.ai/library/model-risk-gap-check
005. Board Variance Bridge Second Read Agent: run a second read on your board variance bridge, split the revenue miss into price, volume, and mix.
https://consultance.ai/library/variance-second-read
006. AI Build Hardening Agent: harden what you already built.
https://consultance.ai/library/builder-hardening-checklist
007. Portfolio Look Through Exposure Audit: see true position overlap across every manager in one exposure map.
https://consultance.ai/library/allocator-look-through-audit
008. Private Fund Fee Audit: recompute the management fee against the actual LPA base, rebuild the carry and the crystallization.
https://consultance.ai/library/advisor-fee-audit
009. Quality of Earnings Second Read Agent: run a second read on a seller's quality of earnings, test every add-back against the source.
https://consultance.ai/library/qoe-second-read
010. Second Opinion on Audited Financials Agent: a second review on financials someone already signed, in your own Claude.
https://consultance.ai/library/audit-second-read
011. AI Output Verification Agent: fact-check every citation, quote, and number before you ship it.
https://consultance.ai/library/ai-output-verification-pack
012. Agent Tripwire Agent: six agent desks that run the sell side pack end to end, plus the four stop conditions that halt a run before it ships.
https://consultance.ai/library/agent-tripwire-pack
013. Twenty Finance Desks Control Room: a prompts router that puts any manager or deal job on the right desk and blocks the memo when figures do not tie.
https://consultance.ai/library/twenty-finance-desks
THE CLOSE DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
014. AI vs Payroll Trade-Off Calculator: a free calculator for CFOs, founders, and ops leads.
https://consultance.ai/library/ai-capex-reshuffle-calculator
015. CFO AI Close Agent: run the monthly close in your own Claude, connect your own Gamma account via Claude.
https://consultance.ai/library/cfo-ai-close-kit
016. Claude Bookkeeping Stack to Replace QuickBooks Agent: replace QuickBooks with prompts that handle reconciliation, categorisation, AR chasing, and month-end close.
https://consultance.ai/library/quickbooks-bookkeeping-stack
017. Cut Your Month End Close to One Day Agent: match the bank feed, book the accruals with the working shown, chase every variance to the journal line.
https://consultance.ai/library/fast-close-desk
018. Daily Fund NAV Tie-Out Agent: tie positions, cash, and accruals to the custodian every day, trace each break to the trade that caused it.
https://consultance.ai/library/nav-tieout-engine
019. Finance Back Office Prompt Agent: draft journal entries, run variance analysis, write the board pack, and model the annual plan.
https://consultance.ai/library/customer-zero-finance-ops
020. 3-Statement Model Builder: build a tied-out income statement, balance sheet, and cash flow from your own filings inside Claude Opus 5.
https://consultance.ai/library/three-statement-model-vault
021. Group consolidation without Hyperion Agent: for group controllers who consolidate several country P&Ls in Excel each month.
https://consultance.ai/library/month-end-consolidation
022. In-House Fund NAV Close Agent: run your monthly fund NAV close in-house, so COOs and controllers reconcile, book fees, run the LP waterfall.
https://consultance.ai/library/fund-nav-close-pack
023. Income Tax Provision Builder: build your ASC 740 income tax provision, run the Pillar Two tests, and clean up messy K-1s.
https://consultance.ai/library/tax-desk-pack
024. Month End Close Reconciliation Engine: run the month end close reconciliation itself, match bank and subledgers both directions.
https://consultance.ai/library/blackline-close-kill
025. Month-End Close Automation Agent: prompts for controllers and CFOs to run the month-end financial close in Claude: reconcile accounts, post accruals.
https://consultance.ai/library/month-end-close-kill
026. Month-End Close and Consolidation Agent: run a CPA-grade month-end close and multi-entity consolidation on your own books.
https://consultance.ai/library/cpa-far-bookkeeper-test
027. Oil & Gas Statement Reader Agent: reads an operator's oil and gas revenue or JIB statement PDF, codes each line to your wells, applies your decimals.
https://consultance.ai/library/oil-gas-non-op-statement-pack
028. Practice AI Bookkeeping On Your Own Books Agent: no CFO trusts AI with the company books on day one.
https://consultance.ai/library/firefly-cfo-trust-ladder
029. Private Asset Reconciliation Engine: parse notices, match cash to the custodian file, reconcile units, and land every break as green, yellow.
https://consultance.ai/library/private-asset-recon-pack
030. Private Ledger Stack: run reconcile, covenants, redaction, and a board pack publish gate inside your own Claude tenant.
https://consultance.ai/library/private-ledger-stack
031. Replace Concur Expense and AP Agent: run expense and AP inside Claude instead of Concur.
https://consultance.ai/library/concur-expense-ap-kill
032. Statement Matching and Reconciliation Agent: bank, custodian, and brokerage statements to your ledger in seconds and return only the breaks, on your own machine.
https://consultance.ai/library/statement-matching-recon
THE MONITORING DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
033. CLO Covenant and Payment Monitor Agent: read the loan tape and credit agreements, recompute every covenant test with the period cited.
https://consultance.ai/library/clo-covenant-monitor
034. Credit Memo AI Workflow Layer: get credit memos past the two day AI plateau.
https://consultance.ai/library/past-the-plateau-workflow-layer
035. Covenant Monitoring Desk: recompute leverage and coverage covenants from the borrower's own financials, not the compliance certificate.
https://consultance.ai/library/covenant-watch-desk
036. Portfolio Monitoring Desk: normalize portfolio company KPIs, flag covenants, and build the LP review, no iLevel alternative contract.
https://consultance.ai/library/portco-monitoring-desk
037. PE Portfolio Monitoring Prompt Agent: 12 AI prompts plus a live monitor that read your PE portfolio's quarterly reports like a credit analyst.
https://consultance.ai/library/pe-portfolio-monitoring-pack
038. Private Credit Surveillance Engine: monitor covenants, recalculate the borrowing base, read amendment redlines, and draft the LP note.
https://consultance.ai/library/moodys-surveillance-kill
039. Private Credit Underwriting Agent: underwrite direct lending deals inside Claude: read the data room, build the cash flow and DSCR model.
https://consultance.ai/library/private-credit-underwriting
040. Private Credit Agent Stack: the map of ten agent desks that run origination through surveillance inside your own Claude, from the underwrite.
https://consultance.ai/library/private-credit-stack
THE RESEARCH DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
041. AI Market Reader Prompt Agent: a free pack of 12 ChatGPT and Claude prompts that read any chart for you and call it buy, hold.
https://consultance.ai/library/market-ai-starter-kit
042. AI stock research and backtest desk Agent: a hedge fund research desk that runs in Claude Code: seven AI agents argue both sides of a stock.
https://consultance.ai/library/quant-desk
043. Claude Market Research Prompt Agent: claude prompts that run market research on your own question: scan the market, size the TAM, score vendors.
https://consultance.ai/library/gartner-research-synthesis
044. Daily Macro Morning Note: run a daily macro morning note in your own Claude.
https://consultance.ai/library/allocator-morning-note
045. Equity Research Desk That Replaces FactSet Agent: a FactSet alternative for equity analysts: run comps, build a DCF, read 10-Ks.
https://consultance.ai/library/factset-equity-research-kill
046. Bloomberg Terminal Agent: a free, open source terminal for analysts and finance founders.
https://consultance.ai/library/fincept-terminal
047. Portfolio Quant Research Desk: run a portfolio backtest, tax loss harvesting, and model risk checks on your own holdings, locally, in your own Claude.
https://consultance.ai/library/portfolio-quant-desk
048. IPO Valuation and Comps Builder: build IPO comps, run the DCF cross-check, and draft the valuation memo in Claude on live SEC EDGAR.
https://consultance.ai/library/ipo-comp-models
049. Personal AI Trading Desk: turn your own Claude into a bull, bear, and risk desk that argues before you trade, with a backtest guard.
https://consultance.ai/library/vibe-trading-personal-desk
050. Private Equity Deal Sourcing Agent: turn one mandate into a ranked, owner verified proprietary deal flow pipeline.
https://consultance.ai/library/deal-origination-engine
051. Private Equity Deal Sourcing in Claude Agent: run deal sourcing and target screening in Claude with 12 tested prompts.
https://consultance.ai/library/pe-analyst-confession
052. Private Equity Diligence Prompt Agent: 10 AI prompts that run private equity deal diligence: the LBO model, quality of earnings, covenant stress test.
https://consultance.ai/library/pe-lbo-diligence-kill
053. Private Equity Diligence and Deal Agent: turn Claude into a private equity diligence and deal toolkit for deal teams, principals, and credit investors.
https://consultance.ai/library/kkr-style-guide-to-claude
054. Sector Overview Engine: build a full sector overview from public filings, market size, players, margin pools, the shift incumbents miss.
https://consultance.ai/library/sector-overview-engine
055. Shared Desk Terminal for Buy-Side Teams Agent: k terminal the whole team reads, pulling the comps, the overnight screen, and a reconciled morning note on your own book.
https://consultance.ai/library/desk-terminal
056. Private Equity Agent Stack: the map of ten agent desks that run the deal in your own Claude, from the blind underwrite.
https://consultance.ai/library/pe-stack
057. Trading Comps Builder in Claude Agent: screen the peer set, calendarize the fiscal years, reconcile every multiple a second way.
https://consultance.ai/library/trading-comps-vault
THE FP&A DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
058. Board Strategy Deck Prompt Agent: turn your own data into a board ready strategy deck and a live dashboard.
https://consultance.ai/library/mckinsey-strategy-dashboard
059. CFO 13 Week Cash Forecast Agent: run a 13 week rolling cash forecast, three downside scenarios, and variance commentary inside your own Claude.
https://consultance.ai/library/cfo-cash-forecast-kit
060. FP&A Rolling Forecast Engine: rebuild the rolling forecast off your actuals the day the close lands, explain every variance to plan.
https://consultance.ai/library/fpna-forecast-engine
061. Finance reporting without Power BI Agent: finance teams run prompts on their own data to build board P&L packs, 3-statement models, variance commentary.
https://consultance.ai/library/finance-reporting-pack
062. Live Reports That Replace Tableau Agent: turn raw finance numbers into a live, shareable board pack and dashboard.
https://consultance.ai/library/live-reporting-pack
063. Quarterly Client Report Builder: build the quarterly multi asset client report, roll all custodians into one household view, flag allocation drift.
https://consultance.ai/library/wealth-client-report-pack
064. FP&A Agent Stack: the map of ten agent desks that run the planning cycle inside your own Claude, from the overnight analyst roster.
https://consultance.ai/library/fpna-stack
065. Treasury Agent Stack: for CFOs and treasurers paying $75,000 to $1,000,000 a year for Kyriba or a PwC treasury engagement: prompts covering.
https://consultance.ai/library/treasury-agent-stack
THE DILIGENCE DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
066. AI Deal Diligence Prompt Agent: read a data room and draft the IC memo in Claude with prompts.
https://consultance.ai/library/deal-room-autopilot
067. AI Portfolio Manager Prompt Agent: write the investment policy statement, set the asset allocation, run the liquidity check.
https://consultance.ai/library/cfa-level3-ai-test
068. Allocator Excel Desk: demo the desk on a public sample you can show in a meeting.
https://consultance.ai/library/allocator-excel-desk
069. Allocator Red Flag Desk: cross the DDQ against the audited financials, verify the auditor and administrator actually match.
https://consultance.ai/library/allocator-red-flag-desk
070. Commercial Due Diligence in Claude Agent: a 9-prompt commercial due diligence build for PE deal teams and corp dev.
https://consultance.ai/library/bain-cdd-diligence-kill
071. Quality of Earnings Agent: run quality of earnings due diligence yourself, EBITDA addbacks included.
https://consultance.ai/library/quality-of-earnings-desk
072. Manager Due Diligence Agent: nine Claude prompts that run full manager due diligence: screen managers, check fees, attribute performance.
https://consultance.ai/library/allocator-manager-dd
073. PE Diligence Pack for Deal Teams Agent: underwrite a mid-market buyout end to end, the data room read, the LBO model, the quality of earnings.
https://consultance.ai/library/pe-diligence-pack
074. Side Letter Review Desk for Allocators Agent: read the LPAs and side letters you've already signed in your own Claude and find the MFN clauses you never elected.
https://consultance.ai/library/allocator-side-letter-desk
075. Spot Accounting Red Flags Agent: turn Claude into a forensic accountant for any financial statement.
https://consultance.ai/library/forensic-skeptic-pack
076. Startup Diligence Pack for VCs Agent: run the diligence a VC partner uses to kill a deal before you wire a term sheet.
https://consultance.ai/library/vc-startup-diligence-pack
077. Submission to Quote Underwriting Agent: read a submission, pull the loss runs, build the technical price, and draft the quote.
https://consultance.ai/library/insurance-underwriting-pack
078. Blind Underwrite Agent: the map of six agent desks that run a second underwrite on a live deal file with no seller narrative.
https://consultance.ai/library/blind-underwrite-kit
079. Deal Model Red Flag Checklist Agent: a one page checklist of 15 places a deal model hides risk, written for PE deal teams.
https://consultance.ai/library/diligence-red-flag-checklist
THE DEAL DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
080. AI Agent P&L Board Template Agent: price every AI finance agent against the salary it replaces and prove its output.
https://consultance.ai/library/agent-pnl-board-pack
081. Anthropic vs OpenAI Valuation Model: at builds a sourced IPO valuation model in 20 minutes.
https://consultance.ai/library/anthropic-vs-openai-comp-vault
082. Build a CIM in Claude Agent: anthropic's free finance plugin drafts the CIM from your data room and outputs a Word document with an Excel appendix.
https://consultance.ai/library/cim-builder
083. Cap Table Desk: rebuild the cap table from the signed documents instead of the spreadsheet.
https://consultance.ai/library/cap-table-desk
084. DCF Assumption Attack Agent: rank every input by leverage, name the one assumption carrying the valuation, run the bear case.
https://consultance.ai/library/dcf-attack-kit
085. DCF Model Builder: build a full discounted cash flow model on your own numbers inside Claude.
https://consultance.ai/library/dcf-model-builder
086. Jira Alternative for Deal Teams Agent: a self hosted deal tracker your Claude can write to.
https://consultance.ai/library/agent-writable-deal-tracker
087. Sell Side Deal Desk: draft the teaser, the CIM, and the buyer list in Claude Opus 5, not a six week cycle.
https://consultance.ai/library/sell-side-deal-desk
088. Sell-Side Teaser Agent: turn raw financials into the anonymized 2-page M&A teaser a banker bills a retainer to write, run inside your own Claude.
https://consultance.ai/library/sell-side-teaser-kit
089. IC Memo Bull Bear and Kill Line Agent: write the investment committee memo, the bull case, the bear case, and the one line that sinks the deal.
https://consultance.ai/library/ic-memo-desk
090. LBO Model and Returns Calculator: build an LBO model in an afternoon with prompts: sources and uses, debt schedule, MOIC and IRR, sensitivity grid.
https://consultance.ai/library/lbo-returns-model
091. Purchase Price Bridge Desk: rebuild the enterprise value to equity value bridge, price every debt like item.
https://consultance.ai/library/purchase-price-bridge-desk
THE INVESTOR DESK. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
092. Big 4 Advisory Agent: three Claude agents that monitor tax and regulation exposure, read a data room like an FDD associate.
https://consultance.ai/library/kpmg-advisor-agent-swap-kit
093. Hedge Fund Risk Desk: turn your own position export into a morning risk management brief before the open, covering exposure report.
https://consultance.ai/library/morning-risk-pod
094. TAMP Alternative Desk: run household drift checks, tax loss harvesting scans, and rebalancing in Claude Opus 5.
https://consultance.ai/library/ria-advisor-desk
095. Portfolio AI Maturity Scan Agent: point your own Claude at a company and score where AI takes cost out, what a buyer marks it up or down for.
https://consultance.ai/library/portfolio-ai-maturity-scan
096. Family Office Agent Stack: the map of ten agent desks that run the mandate in your own Claude, from the morning macro read, manager due diligence.
https://consultance.ai/library/family-office-stack
097. Family Office Investment Team Agent: seven Claude agents that run a family office investment team: daily portfolio consolidation, manager drift alerts.
https://consultance.ai/library/family-office-investment-pack
THE STACK BUILDERS. Every agent here obeys the shared rules in prompt 01, and nothing it produces is released until prompt 11 passes.
Pick by job, not by curiosity. Each link opens that agent's own free page. Most carry a full prompt vault; a few carry a guided setup instead, and the page says which.
098. AI Discovery Playbook Agent: run the enterprise AI discovery a consultancy charges $1M for, inside your own Claude, in days.
https://consultance.ai/library/ai-discovery-playbook
099. AI Investment Committee Agent: install the open ai-berkshire repo and turn your own Claude Code or Codex into a value investing committee that forces.
https://consultance.ai/library/ai-investment-committee
100. Accretion Dilution Merger Model: run accretion or dilution, the funding mix, goodwill, synergies.
https://consultance.ai/library/merger-model-kit
101. Big 4 Consulting Prompts Agent: finance and ops teams run prompts for Big 4 consulting workflows like financial analysis and due diligence.
https://consultance.ai/library/kpmg-big4-prompt-vault
102. Big 4 Deliverables Prompt Agent: run six Big 4 grade deliverables yourself with prompts, including the quality of earnings pass.
https://consultance.ai/library/big4-judgment-gate
103. Claude finance prompts for Excel Agent: finance teams that run inside Excel, Word, PowerPoint and Outlook.
https://consultance.ai/library/claude-m365-finance-pack
104. Finance Skills OS: the diligence desk an EY or PE team spins up for a deal, rebuilt as 21 Claude skills inside your own tenant.
https://consultance.ai/library/finance-skills-os
105. PE Ops Intel Screen From Exports Agent: inventory exports, score each function against the plan you underwrote, flag breaks weekly.
https://consultance.ai/library/ops-intel-screen
106. Post Earnings Model Update Agent: for equity analysts and PMs who lose three nights a print week to the copy paste between the filing.
https://consultance.ai/library/earnings-update-kit
107. Run Your Finance Team in Slack Agent: run your month-end close, AP, and FP&A inside Slack with Claude Tag, 24/7, in place of a controller seat or BlackLine.
https://consultance.ai/library/claude-tag-finance-team
108. Seven Finance Agents That Run Overnight Agent: stand up seven finance analysts as scheduled agents on your own account.
https://consultance.ai/library/always-on-finance-analyst
109. Strategy Consulting Skills Agent: run a full strategy engagement inside your own Claude.
https://consultance.ai/library/pe-strategy-skill-pack
110. Technology Vendor Quote Teardown Agent: split a technology vendor quote into the part AI turned into a commodity and the part that still genuinely costs money.
https://consultance.ai/library/vendor-quote-teardown
111. CFO Agent Stack: the map of six agent desks that run the close and the reporting cycle inside your own tenant.
https://consultance.ai/library/cfo-agent-stack
112. CFO Claude Stack: the map of seven finance desks, deal, diligence, close, tax, underwriting, family office, and market.
https://consultance.ai/library/cfo-claude-stack
113. FRM Part II Risk Judgment Agent: run the applied risk judgment calls on your own numbers: VaR breach triage, wrong way risk pricing.
https://consultance.ai/library/frm-risk-judgment-pack
114. Investment Bank Agent Stack: the map of ten agent desks that run the sell side workflow in your own Claude, from sector coverage, comps.
https://consultance.ai/library/investment-bank-stack
115. Which AI model for each finance job Agent: a free routing map for which AI model wins each finance job: Claude for diligence, GPT for sourcing.
https://consultance.ai/library/finance-ai-model-map
You are an independent reviewing manager. You did not do the work above and you are not trying to defend it.
<task>
Re derive the load bearing figures from the source documents, independently, before reading anything the run produced. Then compare.
Check: does every figure tie to a document supplied in prompt 01's data source, at the page cited. Is every unsourced figure labelled ASSUMPTION. Is every NOT PROVIDED still marked NOT PROVIDED rather than quietly filled. Did any agent above proceed past a missing document instead of stopping.
</task>
<output_format>
PASS or BLOCK on the first line, nothing before it.
Then one row per check: check, result, evidence, and for a fail, the specific figure and document.
</output_format>
<constraints>
Obey the shared_rules block in prompt 01. This agent appends nothing to the deliverable and softens nothing.
On BLOCK, do not produce the deliverable. Return the fail list only.
BLOCK is cleared one way only: {{APPROVER}}, a named human, resolves the specific discrepancy or accepts it in writing on the record. It is not cleared by re running this prompt, and it is not cleared by an argument that the discrepancy does not matter.
Constructing a case for why a fail is immaterial is itself the failure mode. Do not do it.
</constraints>
<trap>A reviewer that reads the run's own output first will agree with it. Re derive from the source documents before opening anything the run produced.</trap>
<review_gate>This is the gate. Nothing sits above it except {{APPROVER}}.</review_gate>
Got the prompts. Want them wired into your actual stack? We map that on a free AI audit.
• Run last quarter's numbers first. Live data is not a test bed.
• Nothing here uploads to us. It runs in your own Claude account, on your own machine.
• A named human reviews and signs every output before it reaches a board, lender, or client.
• Mask account numbers and names to the minimum the task needs.
the fine print
Straight answers on ownership
Prompt set authored by consultance.ai. It is an index over packs already published free on this site and replaces no named product. Your documents stay in your own Claude tenant; we never see them. The agents produce working papers for a named human to sign, not a valuation, an audit opinion, a tax filing, or investment, audit or legal advice.
Want this running in your business, not just your laptop? We build it and hand you the keys.
115 Finance AI Agents Directory is a finance and data build in the consultance.ai AI Build Library. For CFOs, controllers, allocators and PE and IB teams: 115 named finance AI agents mapped to their desk, each linking to its own free pack. A 4 question router narrows it to your 3 to 6. It fits CFOs and fund CFOs, controllers, allocators and family office principals, PE and investment banking teams who want the whole shelf in one file and a router that stops them running the wrong three agents. Setup difficulty is Medium, with 4 plain-English steps.
What does 115 Finance AI Agents Directory do?
For CFOs, controllers, allocators and PE and IB teams: 115 named finance AI agents mapped to their desk, each linking to its own free pack. A 4 question router narrows it to your 3 to 6.
Who is 115 Finance AI Agents Directory for?
It fits CFOs and fund CFOs, controllers, allocators and family office principals, PE and investment banking teams who want the whole shelf in one file and a router that stops them running the wrong three agents.
How hard is 115 Finance AI Agents Directory to set up?
Medium to set up — one guided setup instruction covering 4 plain-English steps, plus 11 ready-to-run prompts on the resource page.
How would consultance.ai build this out?
We would wire the shelf into your tenant: the router pointed at your own internal desks alongside the published ones, governed connectors to your ERP, administrator and data room so the evidence assembles itself, your evidence standard encoded as tests, and the self check set as a standing gate before anything reaches a board or an investment committee. Done with you, then handed over so you own it.
What are the licensing terms?
Prompt set authored by consultance.ai. It is an index over packs already published free on this site and replaces no named product. Your documents stay in your own Claude tenant; we never see them. The agents produce working papers for a named human to sign, not a valuation, an audit opinion, a tax filing, or investment, audit or legal advice.
Want this built into your workflow?
115 Finance AI Agents Directory is the starting point. On a free AI audit we map where it fits your stack and what consultance.ai would build around it.