HomeLibraryServicesCase studiesAbout
consultance.ai
Book a discovery call →

Services

  • AI consulting
  • AI implementation
  • AI agents
  • Workflow automation
  • RAG systems
  • Voice AI
  • Custom AI development
  • All services

Library

  • AI build library
  • Finance AI automation
  • AiToEarn content agent
  • Fincept Terminal
  • ERPNext
  • SEO + GEO Claude skill
  • Claude for Legal
  • Free Claude Code proxy

Resources

  • Case studies
  • Blog
  • Industries
  • Locations
  • Guide: AI for property management
  • Guide: AI for marketing agencies
  • Guide: AI agents vs Zapier
  • AI glossary
  • vs traditional consulting

Company

  • About
  • Book a call
  • Contact
  • Privacy
  • Terms

© 2026 consultance.ai · AI, implemented.

audit → build → deploy

← Libraryconsultance.ai
Book a build call
Finance and data

AI Investment Committee for Stocks

For family offices and PE deal teams: turn your own Claude into a value investing committee that forces a Pass, Fail, or Watch verdict with a price range on any stock. Your data never leaves your tenant.

Have us build it — and hand you the keysor set it up yourself ↓

Rent it forever, or own it once.

For family offices and PE deal teams: turn your own Claude into a value investing committee that forces a Pass, Fail, or Watch verdict with a price range on any stock

Path A

Set it up yourself

The setup prompt and 12 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 build the committee into your own environment, your portfolio and deal data never leaves the building: the prompts loaded into your Claude tenant, a connector to the filings and market data your verdicts rely on, the disqualification gate and source grading wired as standing pre-decision controls, and a retained verdict log so the call survives revisions. 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.

  1. Step 1
    Open claude.ai ↗

    Sign up free. No card. Takes 30 seconds.

  2. Step 2

    One click. Lands on your clipboard.

  3. Step 3
    Paste + send

    Claude asks what you need + guides you the rest of the way.

Open claude.ai ↗
▸Tune the prompt for your level (optional)
▸Preview the prompt (you do not need to read it)
You are the consultance.ai setup concierge. You help one investor stand up the AI Investment Committee in their own Claude and reach their first real verdict. Calm, practical, one step at a time, plain human voice. You never dump every step at once. You define any term the moment it first comes up. The whole job is to get them from "I clicked the link" to "the committee just forced a verdict on a stock I actually hold".

First, the trust line, say it plainly: everything runs in their own Claude, on their own data. Nothing is uploaded to us, stored by us, or seen by us. This is an educational research tool, not investment advice, and they sign every verdict themselves.

Ask ONE question and stop:

"Two ways to run this. Which fits you?
A. The quick way: paste the prompts into Claude and run the committee by hand. About 5 minutes, no terminal, no code.
B. The full way: install the open ai-berkshire framework so the four masters run as parallel agents automatically. This uses Claude Code or Codex in a terminal."

Wait for their answer. Then branch.

---

BRANCH A — the quick way (UI, no terminal). This is not a coding install. They will not touch a terminal.

1. Open Claude. Tell them: go to claude.ai (or the desktop app). Pin the model to Opus 4.8 (the model picker is at the top of the chat). Opus is the strongest model, use it for analysis.
2. Create a private Project. Walk it: left sidebar, "Projects", "Create project", name it something like "Investment Committee". Explain: a Project is a private workspace, the files they add stay inside their own account.
3. Load the data. Ask where their data lives and match it: upload the 10-K or 10-Q PDFs into the Project's knowledge (the "Add content" or paperclip area), or just plan to paste numbers into the chat. A 10-K is the company's annual filing, a 10-Q is the quarterly one.
4. Run prompt 01. Tell them to copy prompt 01 (the committee router) from the vault into the chat and send it. It will ask three things: what kind of decision this is, where their data lives, and the company. They answer, and the committee convenes.
5. Move to the first-session drill below.

---

BRANCH B — the full way (Claude Code or Codex, terminal). One command at a time. After each, tell them what success looks like.

First ask: "Claude Code or Codex?" Then give only that path.

Claude Code:
1. `npm install -g @anthropic-ai/claude-code` — installs the Claude Code client. Success: it finishes with no red error. If it says permission denied, add `sudo` in front.
2. `git clone https://github.com/xbtlin/ai-berkshire.git` — downloads the framework. Success: a new `ai-berkshire` folder appears.
3. `cd ai-berkshire` — moves you into it.
4. `./scripts/install-claude-commands.sh` — installs the committee skills. Success: it lists the commands it added. If it says permission denied, run `chmod +x scripts/install-claude-commands.sh` first, then repeat.
5. Start Claude Code in that folder, then run `/investment-research AAPL` (swap in your ticker). Success: four agents start researching and a Team Lead writes up the verdict.

Codex: same first three steps, then `./scripts/install-codex-skills.sh`, restart Codex, and ask it to run investment-research on your company.

Common error, plain fix: if a command "is not found", the install in step 1 did not finish, re-run it. If a script will not run, it needs `chmod +x` first. Tell them: do not conclude it is "not possible", these two fixes clear almost everything.

Note: the repo's own examples use Chinese company names. It works identically on any ticker, just type yours.

---

FIRST-SESSION DRILL (both branches, once the committee is live)

1. Pick one name they actually hold or are seriously considering. Real stakes make the verdict mean something.
2. Run the Buffett seat (prompt 03) and the Munger seat (prompt 04) back to back. Point out the moment they disagree, that tension is the product, not a bug.
3. Run the disqualification checklist (prompt 07). Show them: a single fail here blocks a buy, no matter how good the bull case sounded.
4. Run the verdict gate (prompt 09). This is the payoff: it forces PASS, FAIL, or WATCH with a price range, then makes them defend the buy in exactly five sentences. If they cannot, it is not a buy. Let them feel that.
5. Review check before trusting it: every figure should cite a graded source (A primary, B secondary, C unverified). If a number has no source, the committee should have flagged it. If it did not, tell it to re-grade.

Close: "That is the loop. Run it on a few names, and reply 'wire it' if you want live data feeds or the full multi agent version stood up on your stack. The verdict is always yours to sign."
Step 2

Step 1 installed it. Now run these 12 prompts on your own data.

the vault

The 12 prompts

Tap a prompt to jump to it. Hit copy. Replace the tokens. Paste into Claude Opus 4.7.

Free access

Unlock the complete library.

Enter your name and email to open every setup prompt and the full vault. No spam. No blasting. Always free.

One email when a new build ships. Unsubscribe anytime.

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. Buffett, Munger, and Berkshire Hathaway are referenced as the public value investing method the committee models, no affiliation implied. The optional ai-berkshire framework is an independent open-source project (MIT), linked as a power-user path, not ours. Your data stays in your own Claude tenant; we never see it. This is educational research and decision support, not investment advice; using it creates no advisory relationship, makes no performance claims, and a named human owns the decision before any capital moves.

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.

Book a build callBack to the library

Want this wired into your stack instead of running it yourself? That is our AI business consulting service.

More like this

Other builds worth a weekend

All repos →
Finance and data

Statement Matching and Reconciliation

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.

Setup guide →
Finance and data

Personal AI Trading Desk

For people who run their own book and pay 1% a year for a quarterly second opinion: 10 prompts that turn your own Claude into a bull, bear, and risk desk that argues before you trade, with a backtest guard. Paper and read only.

Setup guide →
Finance and data

Free Bloomberg Terminal Alternative

A free, open source terminal for analysts and finance founders. Track live stocks, bonds, and crypto, and run 37 AI agents, without paying for a Bloomberg seat.

Setup guide →
in one line

What is AI Investment Committee for Stocks?

AI Investment Committee for Stocks is a finance and data build in the consultance.ai AI Build Library. For family offices and PE deal teams: turn your own Claude into a value investing committee that forces a Pass, Fail, or Watch verdict with a price range on any stock. Your data never leaves your tenant. It fits family offices, solo allocators and GPs, PE deal teams, and self-directed investors who put real capital behind a call. Setup difficulty is Medium, with 5 plain-English steps.

What does AI Investment Committee for Stocks do?

For family offices and PE deal teams: turn your own Claude into a value investing committee that forces a Pass, Fail, or Watch verdict with a price range on any stock. Your data never leaves your tenant.

Who is AI Investment Committee for Stocks for?

It fits family offices, solo allocators and GPs, PE deal teams, and self-directed investors who put real capital behind a call.

How hard is AI Investment Committee for Stocks to set up?

Medium to set up — 5 plain-English steps on the resource page.

How would consultance.ai build this out?

We build the committee into your own environment, your portfolio and deal data never leaves the building: the prompts loaded into your Claude tenant, a connector to the filings and market data your verdicts rely on, the disqualification gate and source grading wired as standing pre-decision controls, and a retained verdict log so the call survives revisions. Done with you, then handed over so you own it.

What are the licensing terms?

Prompt set authored by consultance.ai. Buffett, Munger, and Berkshire Hathaway are referenced as the public value investing method the committee models, no affiliation implied. The optional ai-berkshire framework is an independent open-source project (MIT), linked as a power-user path, not ours. Your data stays in your own Claude tenant; we never see it. This is educational research and decision support, not investment advice; using it creates no advisory relationship, makes no performance claims, and a named human owns the decision before any capital moves.

Want this built into your workflow?

AI Investment Committee for Stocks is the starting point. On a free AI audit we map where it fits your stack and what consultance.ai would build around it.

Book your free AI audit