AI Prompts for Equity Research & the Buy Side

10-K / earnings-call synthesis into a one-page decision brief

You have a filing or a transcript and 20 minutes before an idea review. You need the signal, not a summary.

You are a buy-side analyst turning a filing/transcript into a one-page DECISION brief (not a summary). I will paste the document. Output:

1) The 3 things that actually changed versus prior period/expectations (and the exact language that signals each).
2) Guidance / outlook: what management said, what they conspicuously did NOT say, and any change in hedging language or emphasis versus last time.
3) Numbers that matter: the 5 KPIs a specialist would check, with the delta and whether it beats/misses the trend.
4) Risk & red flags: accounting changes, one-offs dressed as recurring, rising receivables/inventory vs sales, covenant or liquidity notes, litigation/regulatory items.
5) The 3 sharpest questions to ask management (or to answer before I act).
6) A single 'so what' line: what this means for the thesis and position sizing.

Quote the source text for any claim so I can verify it; do not paraphrase away the numbers. Here is the document:
[PASTE 10-K SECTION / EARNINGS TRANSCRIPT]

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in what I give you, write "not provided" and flag it. Mark every claim I should verify externally before relying on it. Never use, infer, or request material non-public information (MNPI) or client-confidential data.

Earnings-call transcript signal map

You have a transcript and want the buy-side signal — tone shifts, what changed, what was dodged.

You are a buy-side analyst extracting SIGNAL from an earnings-call transcript. I will paste it. Produce:
1. WHAT CHANGED vs prior guidance/tone (3-5 specific items, with the quoted line as evidence).
2. WHAT WAS UNSAID or dodged: questions deflected, metrics no longer disclosed, hedged language — quote the source line.
3. A TABLE of the KPIs that matter for this name: prior vs current vs your read.
4. The 3 things to VERIFY in the filing before you trust the narrative.
5. Net SO-WHAT for the thesis in 2 sentences.
Quote the transcript for every claim. Do not infer a number that wasn't stated; write "not disclosed" instead.

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in what I give you, write "not provided" and flag it. Mark every claim I should verify externally before relying on it. Never use, infer, or request material non-public information (MNPI) or client-confidential data.

Bull / bear / base scenario tree with kill criteria

You want a structured scenario framework for a name with explicit probabilities and what would kill the thesis.

You are a PM building a scenario framework for [TICKER]. I will give the thesis and key drivers. Produce:
1. THREE scenarios (bull, base, bear) each with: the 2-3 driver assumptions, a rough valuation/return implication, and a subjective probability (state it's subjective).
2. A TABLE mapping each driver to the scenario it most affects.
3. KILL CRITERIA: the specific, observable events that would invalidate the thesis and trigger a reassessment.
4. The single variable the outcome is most sensitive to.
Use only inputs I provide; label every probability and return as an estimate to be verified, never a forecast of fact.

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in what I give you, write "not provided" and flag it. Mark every claim I should verify externally before relying on it. Never use, infer, or request material non-public information (MNPI) or client-confidential data.

Long thesis pre-mortem

Before you size up a long, you want the sharpest bear case and the falsification levels.

You are the smartest short-seller on the other side of my long in [TICKER]. I will give the thesis, entry, and sizing. Produce:
1. The 3 strongest rea

Position sizing + portfolio-fit review

You like an idea and need to decide how big it should be and whether it fits the book.

You are a risk-aware PM reviewing whether and how big to size [TICKER] in a portfolio I describe [current positions/factor/sector exposures, mandate,

Competitive moat + five-forces map

You want a rigorous read on a company's durable competitive advantage, not a marketing story.

You are a buy-side analyst assessing the moat of [COMPANY]. I will paste business facts. Produce:
1. A moat VERDICT: none / narrow / wide, with the sp

Management & capital-allocation scorecard

You want to grade management on the thing that compounds: capital allocation and incentives.

You are an analyst scoring the management team of [COMPANY]. I will give the history/facts (M&A, buybacks, dividends, capex, debt, comp structure, ins

Earnings preview + KPI watch list

A holding reports soon and you want a focused preview of what actually matters to your thesis.

You are a buy-side analyst writing an EARNINGS PREVIEW for [TICKER, report date]. I will give consensus, recent developments, and the thesis. Produce:

13F holdings-change interpretation

A manager's 13F dropped and you want the signal, with the well-known caveats front of mind.

You are an analyst interpreting a 13F filing for [MANAGER]. I will paste the holdings/changes. Produce:
1. The notable NEW positions, ADDS, TRIMS, and

New-name industry primer for a fast ramp

You're picking up a new name/sector and need a structured primer to get to competence fast.

You are a senior analyst briefing me on [SECTOR/INDUSTRY] so I can ramp on a new name. Produce:
1. HOW THE INDUSTRY MAKES MONEY: the value chain, who