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.
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 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.
I am comfortable copy-pasting and following instructions, but I am not a developer. - 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. I want to set up the Personal Desk Pack and run a full bull, bear, and risk pass on one name I already know, then check a backtest against a random control. Walk me through it step by step, one question at a time, and wait for my answer before moving on. I run my own book. I am not a developer. Define every term once. Keep me to one action per message. Keep the desk paper and read only the whole way. ## What this produces A desk that argues before I trade: a bull case, an adversarial bear case, and a risk officer that sizes by downside, all in my own Claude, with market data and backtests running locally on my machine. A backtest guard tells me whether the strategy actually beats a random control or is just fitting noise. Nothing trades on its own, this is research and I own every call. ## Step one, ask me this first, nothing else "What name do you want to run through the desk first, and is it one you already know well? Pick something you have a view on, so you can judge whether the bear case tells you something you missed." Wait for my answer. Then continue, one step per message: ## The path you walk me down - Classify my setup as CLI plus chat. Give me the one command to install the local engine and the one to initialize it, where to paste each, and what success looks like. - Have me point it at Claude and pin Opus 5, then confirm out loud that no broker is connected for live orders and the desk is paper and read only. Do not move on until that is confirmed. - Walk me through creating a Claude Project named "My Desk" and pasting the house rules (you are my research desk, not my decision maker; always build a real bear case; size by downside; show the reasoning, never a bare confidence score; never place an order). - Run the bull case on my name, then stop and have me read it. Then run the bear case and ask me what in it I had not considered. - Walk me through the risk frame: my account size and the most I will lose on one position, returned as a loss profile, not an order. - Run a backtest with a random control and read the result together, is the edge real or is it overfit. - Run the analysis on my own past trades and name my two priciest recurring mistakes with a rule for each. ## The first session drill By the end of this session I should have, on one name: a bull case with figures, an adversarial bear case with the number that breaks it, a downside loss profile at a few sizes, a backtest checked against a random control, and a one page trade note with the level that proves me wrong. Confirm the desk is still paper and read only. Before I act on anything, re check the view: separate what is grounded in the data from your inference, re state the one fact that would flip it, and confirm the backtest beat its random control. Do not tell me a view is ready until that holds. Markets will prove some of this wrong. I own every call.
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.
Build the bull case for {{TICKER}} from the data I loaded: the thesis, the three things that have to be true, the catalyst, and the time frame. Cite the specific figure behind every claim. If a claim has no number behind it, label it as opinion, not thesis. Then stop. I will ask for the bear case separately.Now attack the bull case for {{TICKER}} the way a short seller would. Give me the strongest bear thesis, the single number that would break the bull case, the thing the bulls are ignoring, and what would have to happen for this to be a bad trade. Do not be balanced. Make the hardest case against it.Act as a risk officer on {{TICKER}}. Given my account size {{SIZE}} and the most I am willing to lose on one position {{MAX_LOSS}}, frame the trade in terms of downside: if the bear case happens, what is the loss at different position sizes. Do not give me an order or a share count. Give me the loss profile so I size it myself.Here are the backtest results for the strategy and the results of a random control on the same universe and period. Tell me honestly: does the strategy beat the random control by a margin that means anything, or is this overfit to past data? If it is overfit, say so plainly and tell me which part of the rule is doing the overfitting.Write a one page trade note for {{TICKER}}: the thesis, the bull case, the bear case, the exact level or event that proves me wrong, the size rationale, and the date. Make it something I will understand in six months when I review whether I was right for the right reason.Here is the analysis of my past trades from my broker journal. Name my two most expensive recurring mistakes (early exits, chasing momentum, holding losers, overtrading), with the dollar cost of each, and one concrete rule that would have caught each one. Be specific, not generic.Here is the market data for {{TICKER}} and its peer set. Summarize the setup: price trend, valuation versus the peers, the one fundamental that stands out, and the one data point I should not trust without checking it myself. Flag the figure you are least sure about rather than presenting everything as equally solid.For your view on {{TICKER}}, show the full chain: which data points drove it, which way each one pushed the view, and the single new fact that would flip it. No summary score until the reasoning chain is on the page. A view that nothing could change is a belief, not analysis, tell me if that is what this is.Confirm this desk is paper and read only: no broker connected for live orders, no order placement enabled. List every place an order could be sent and confirm each is off. If I ever ask you to enable live trading, first walk me through the mandate, the position caps, the daily cap, and the kill switch, and make me confirm twice before anything is armed.Turn this into a fifteen minute morning routine: which names to scan, the order of prompts to run (setup, bull, bear, risk, backtest check, note), and a one line end of day review. Give me the checklist so the desk argues with me before every position instead of after.The code is public and free. The setup instruction above installs and wires it for you. You never need to open this link.
Got the prompts. Want them wired into your actual stack? We map that on a free AI audit.
Book the free auditFor 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
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 ↑We would deliver a deployed personal desk: the local engine installed and wired to your data, the prompts loaded into your Claude tenant, the backtest guard configured with a random control, your own trade history analyzed for recurring mistakes, and the paper and read only guardrails locked. Done with you, then handed over. We never enable live trading for you; that stays your decision behind a mandate and a kill switch.
Book a build call →Prompt set authored by consultance.ai. Vibe-Trading is MIT licensed and runs locally; the desk ships paper and read only and this pack never enables live trading. No affiliation with any broker or manager implied. Your positions stay on your own machine. Research and decision support, not investment advice. You own every call.
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 family offices and serious individual investors: run a portfolio backtest, tax loss harvesting, and model risk checks on your own holdings, locally, in your own Claude. Replaces the $250k quant seat you would otherwise hire.
For lower and mid market private equity origination teams: turn one mandate into a ranked, owner verified proprietary deal flow pipeline. Six Claude agents with Exa and Scrapling replace a rented deal sourcing subscription.
For PE deal teams and IC members still tracking a live process on a sprint board: a self hosted deal tracker your Claude can write to, plus 10 prompts that move a workstream only when the document actually lands.
The person drowning in this every week is the one who'll actually want it.
Personal AI Trading Desk is a finance and data build in the consultance.ai AI Build Library. 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. It fits solo allocators, angels, founder operators with real capital, and family office principals who self direct their own book and want a second opinion they can audit instead of a 1% advisory fee. Setup difficulty is Medium, with 5 plain-English steps.
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.
It fits solo allocators, angels, founder operators with real capital, and family office principals who self direct their own book and want a second opinion they can audit instead of a 1% advisory fee.
Medium to set up — one guided setup instruction covering 5 plain-English steps, plus 10 ready-to-run prompts on the resource page.
We would deliver a deployed personal desk: the local engine installed and wired to your data, the prompts loaded into your Claude tenant, the backtest guard configured with a random control, your own trade history analyzed for recurring mistakes, and the paper and read only guardrails locked. Done with you, then handed over. We never enable live trading for you; that stays your decision behind a mandate and a kill switch.
Prompt set authored by consultance.ai. Vibe-Trading is MIT licensed and runs locally; the desk ships paper and read only and this pack never enables live trading. No affiliation with any broker or manager implied. Your positions stay on your own machine. Research and decision support, not investment advice. You own every call.
Personal AI Trading Desk 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.