The Finance Prompt Library

Build a comps table from a list of tickers

Stop hand-assembling comps. Give the model the peer set and the metrics you judge on.

Build me a comparable-companies table for this peer set: {TICKERS}. Columns: EV/Sales, EV/EBITDA, P/E (fwd), revenue growth, gross margin, FCF margin, net leverage. I'll paste the 

Turn any 10-K into a first-draft IC memo

A 10-K is 200 pages engineered to be exhaustive, not useful. Extract the decision, not the document.

You are a senior investment analyst writing an investment-committee (IC) memo. I will paste a company's latest 10-K (or its EDGAR URL). Produce a structured first-draft IC memo with EXACTLY these sections:
1. BUSINESS MODEL — how the company actually makes money, in 3 sentences.
2. SEGMENT ECONOMICS — revenue mix, growth, and margin by segment (table).
3. CAPITAL ALLOCATION — capex / buybacks / M&A / debt and the trend.
4. RISK FACTORS — the 5 risks that actually matter (ignore boilerplate).
5. RED FLAGS — language, accounting, or disclosure items worth a second look.
6. THESIS — the bull case in 3 bullets.
7. VARIANT VIEW — where consensus could be wrong (your non-obvious take).
8. VALUATION FRAMING — the 2-3 metrics this name should be judged on and why.
9. DECISION — PASS / DILIGENCE / BUY-AT-PRICE + the one question that would change your mind.
Rules: cite figures with the page/section. If a number isn't in the document, write "not disclosed" — never estimate.

Read a macro release faster than the desk

The alpha in CPI/FOMC/jobs isn't the number — it's what CHANGED in the language. Diff it.

Here are two consecutive {FOMC statements / CPI reports / releases}: PRIOR and NEW. Do a change-diff:
1. List every phrase that was ADDED, REMOVED, or REWORDED.
2. Classify each change hawkish / dovish / neutral and say why in one clause.
3. Give me the 5-bullet 'what actually changed' read a PM could act on within 60 seconds of the print.
4. One line: what the market is likely mispricing about this change.
Quote both versions for any change you flag. Do not summarize the whole document — only the deltas.

Make a macro headline make sense for your positions

The Fed moved. What does that actually mean for the 6 stocks you own?

I'm a retail investor. Here's a macro development: {PASTE}. Here's what I own: {TICKERS}. In plain English:
1. What did this actually change (rates / inflation / growth expectation

Make Claude match your firm's deck format

The reason AI decks look 'off' is you never showed it YOUR house style. Point it at an existing deck first.

I'm giving you an example of my firm's slide format (attached / pasted below). Study it and produce a STYLE SPEC I can reuse: the headline pattern, bullet density, tone, the standa

Match a company's site/PPT tone for a client-ready page

Point the model at the target's own materials and it will mirror their voice — instant client-ready output.

Below is text from {COMPANY}'s website / investor deck. First, extract their voice: reading level, sentence length, favorite framing words, how formal, how they describe their own 

Point Claude at your Bloomberg/terminal export

You don't need an API integration to put AI on your terminal data — you need a clean export and the right framing.

I'm pasting a data export from my Bloomberg terminal (a security's history / a portfolio / a comps grid). First, tell me exactly what columns you see and infer their meaning. Then:

Turn a screen into ranked, thesis-tagged ideas

A screen gives you 40 names. The model turns them into 5 you can actually pitch.

Here's a raw screen: {TICKERS + columns}. My mandate is {e.g. quality compounders / deep value / GARP}. For each name:
1. In one line, why it passed the screen.
2. Tag it with the 

Screen for setups without a Bloomberg

Free data + the right prompt gets you 80% of what a screener does.

I'm a retail trader. Here's a list of tickers with price, 50-DMA, 200-DMA, RSI, and recent volume: {PASTE}. Group them into:
1. TREND (above rising 50 & 200-DMA),
2. PULLBACK (uptr

Compress an earnings call to what moved the stock

60 minutes of transcript, 5 minutes of signal. Separate the guide from the noise.

Here's the earnings-call transcript for {COMPANY}. Give me:
1. GUIDANCE CHANGES — anything raised, cut, or newly qualified vs prior (with the exact quote).
2. TONE SHIFTS — where m

A pre-open brief ranked by materiality to YOUR book

Don't read the whole firehose. Read only what moves YOUR positions, ranked.

Here are my positions with weights: {TICKERS + weights}. Here are overnight developments (headlines / filings / price moves): {PASTE}. Produce a pre-open brief:
1. Rank every item 

Accounting red-flag pass on a filing

The tells are in the footnotes and the language. Point the model there.

Do a forensic-accounting red-flag pass on this filing. Look specifically for: revenue-recognition changes, growing gap between net income and operating cash flow, rising DSO/invent

Stress-test your own thesis before you size up

The cheapest edge in retail: argue the other side before you buy.

I'm a retail investor. Here's my thesis on {TICKER}: {PASTE}. Act as a sharp skeptic:
1. What's the strongest BEAR case against me?
2. What am I assuming that I haven't verified?
3

Turn your trades into a coaching journal

Your P&L is a scoreboard. Your journal is where the edge actually compounds.

Here are my recent trades: {entry, exit, why I took it, result}. Act as a trading coach:
1. What patterns show up in my WINNERS vs my LOSERS (setup, hold time, sizing, was there a 

Turn an earnings call into a trade plan

You don't have a research team — you have a transcript and 20 minutes. Make them count.

I'm a retail trader. Here's {COMPANY}'s earnings call/release. In plain English:
1. Did they beat, miss, or meet — on revenue, EPS, AND guidance? (guidance matters most.)
2. What are the 3 things that could move the stock this week?
3. If I were considering a trade, what's the BULL case, the BEAR case, and the level/catalyst that would prove me wrong?
4. What am I likely to get wrong here as a retail trader?
Be blunt. This is not advice — help me think, don't tell me what to do.

Understand an options chain in plain English

Before you trade options, have the model explain the trade back to you.

I'm a retail trader considering this options trade: {e.g. buy the $X call expiring {date} on {TICKER}}. In plain English:
1. What has to happen for this to make money — price AND t