Best AI Prompts for Investing: 20 Templates

The best AI prompts for investing paste the source material in and constrain the output. Summarize a 10-K's risk factors with the sentence behind each, extract changed guidance from a transcript, rank peers on a table you supply. Below are 20 templates grouped by goal, from filings and valuation to screening and portfolio review, each with what to verify afterwards.

What makes an investing prompt actually good?

A good investing prompt does three things: it supplies the source material, it states the exact output you want, and it asks the model to flag what it is unsure about. The reason is simple. AI is strong at reading and structuring language and weak at recalling exact financials, so the prompt's job is to lean on the strength and design around the weakness.

That means the worst prompt is an open question like "is this stock a good buy?", which invites a confident verdict the model cannot justify. The best prompt is closer to "here is the filing; summarize the three biggest risks and list every figure you reference." Context plus format plus a verification hook turns a guessing machine into a research assistant. The prompts below all follow that shape. For the surrounding method, see our ChatGPT stock analysis workflow.

20 AI prompts for investing, by goal

Replace the bracketed parts, and paste the actual source material rather than relying on the model's memory. Every one of these ends with a constraint for a reason: unconstrained prompts are where invented figures come from.

Reading filings and transcripts

1. "Below is the risk factors section of [TICKER]'s latest 10-K. Summarize it into at most eight risks, ranked by how specific they are to this company rather than boilerplate. Quote the sentence behind each. Use only this text."
2. "Below is [TICKER]'s latest earnings call transcript. Extract: guidance as stated, any assumption that changed versus the prior call, and the three questions analysts pressed hardest on. List every figure you used and where it appeared."
3. "Below are the MD&A sections from [TICKER]'s last two 10-Qs. List what changed in management's language between them, quoting both versions side by side. Do not interpret motives, just report the change."
4. "Translate this footnote from [TICKER]'s annual report into plain English and say what a shareholder should take from it. If the footnote is ambiguous, say so instead of resolving it."

Fundamentals and valuation

5. "Using only the income statement and balance sheet pasted below, calculate gross margin, operating margin, net debt to EBITDA and return on equity for [TICKER]. Show the arithmetic for each. Write 'not in data' for anything missing."
6. "Here are five years of revenue and operating margin for [TICKER]. Describe the trend in each, name the year that breaks the pattern, and list what I would need to check to explain that year."
7. "Run a simple DCF on these assumptions: [revenue growth, margin, discount rate, terminal growth]. Restate the assumptions you used, show the output, then show how the output moves if the discount rate rises by one percentage point."
8. "Given this table of five sector peers with growth, margins and forward P/E, rank them on growth-adjusted valuation, justify each placement in one sentence, and flag any row whose numbers look internally inconsistent."
9. "Explain what a P/E of [X] implies about expected growth for a company with [margin] operating margins, and what would have to be true for that multiple to be reasonable."

Screening and shortlisting

10. "My goal is [describe it in plain words]. Convert it into a runnable screen for [name your screener]: exact field names, thresholds, and one sentence on why each threshold. Then name the three filters most likely to exclude a company I would want. Do not name any stocks."
11. "From this list of criteria [paste], explain what each filter implies for risk and what a screen built only on these would systematically miss."
12. "I am building a watchlist of [sector] companies. List the financial and qualitative criteria worth screening on, and for each, the way it can be gamed by a company's accounting."

Pressure-testing a thesis

13. "Here is my bull case for [TICKER] [paste]. Argue the strongest bear case using only publicly checkable claims, and list every assumption in my case that I have not justified."
14. "Here is my investment thesis [paste]. Write the post-mortem I would be writing in two years if this went badly, and name the earliest observable signal of each failure path."
15. "What data would falsify this thesis [paste]? Give me a checklist of specific figures or events, each with the source I should check it in."

Portfolio and process review

16. "Here are my current holdings with weights and sectors [paste]. Point out concentration by sector, by factor and by correlated names. Do not recommend trades, just describe the exposure."
17. "Here is my written investing policy [paste]. Find the places where it is vague enough that I could justify almost any decision, and suggest more testable wording."
18. "Here are my last ten investment decisions with my reasoning at the time [paste]. Group them by the type of reasoning I used and tell me which type has worked worst."
19. "Explain the difference between [two concepts, e.g. free cash flow and owner earnings] with one worked example each, using the figures I paste below."
20. "Build me a one-page research checklist for a new position, covering business model, financials, valuation, risks and what would make me sell, where every item has a checkable answer."

Each prompt produces a draft to verify, not a conclusion. The pattern below shows why the data-grounded versions outperform the open-question versions.

How do you prompt for technical analysis specifically?

For chart work, give the model the structure you measured and ask for scenarios, not a reading off the image. A reliable pattern is: "On the [asset] daily chart I see [trend], price holding above [level], and RSI near [value]. Lay out a bullish and a bearish scenario with the level that would invalidate each."

This works because it keeps the precise measurement with you, where it belongs, and uses the model for the reasoning, where it adds value. The reason to keep it that way is consistency: a general model has no fixed definition of support and no memory of the previous read, so the same screenshot can produce different levels on different days. Bullynx's chart analysis runs the same technical routine on every upload so the levels and invalidation come back comparable across sessions. It reads only the image you supply, has no order flow or news feed, and does not tell you what to buy. Asking it to read exact levels off a screenshot is unreliable, since vision models misread dense charts. For more on this split, see ChatGPT for technical analysis and our library of ChatGPT trading prompts. Grounding the prompt in real technical analysis terms also sharpens the output.

How do you verify AI investing output?

You verify by treating every concrete claim as unconfirmed until checked against a primary source. The model can produce a confident, specific, wrong number, which is the most dangerous output in finance.

This discipline is not optional in a regulated space. Both FINRA's AI guidance and the SEC's AI fraud alert stress that AI output and "AI can pick winners" claims warrant skepticism, not trust. Verify figures, demand both sides of a case, and never let a prompt's answer skip your own judgment.

Turning prompts into a repeatable process

The value of good prompts compounds when you use them in the same order every time: gather verified data, summarize, build both cases, pressure-test, verify, decide. The prompts are tools inside that loop, not a shortcut around it. Save the ones that work for you and reuse them so each research session starts from a consistent, balanced foundation.

When your research reaches the chart, a general chatbot reads busy charts inconsistently. The Bullynx AI trading copilot applies a structured, chart-aware prompt to a screenshot so the read follows a consistent framework, while keeping the same educational, scenario-based framing these prompts use.

Related reading: ChatGPT stock analysis prompts for equity research templates, ChatGPT trading prompts for the execution side, and how to value a stock.