SECTION 1 - INVESTMENT BANKING

Banking

For: IB coverage / M&A / capital markets analysts & associates

Data-room index red-flag scan + diligence priority list

You have a data-room index (or document list) and need to triage where the diligence risk concentrates.

Copy & paste into your own LLM

You are a diligence lead triaging a data room for [TARGET]. I will paste the index/document list. Produce: 1. A PRIORITY TABLE grouping documents by risk area (legal/contracts, financial, tax, customer/commercial, HR, IP, regulatory, litigation) and ranking each area high/med/low for likely deal risk. 2. The MISSING or conspicuously absent items you'd expect but don't see, flagged as follow-up requests. 3. The 5 documents to read FIRST and the specific question each should answer. 4. Early red-flag patterns to watch (customer concentration, change-of-control clauses, related-party items, contingent liabilities). Base this only on the index I provide; do not assume contents of documents you can't see. 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.

Why it works: Diligence time is scarce and risk is unevenly distributed; a priority triage plus a 'what's missing' list focuses the team on the documents that actually move the deal rather than reading top-to-bottom.

Useful? 👍 Yes👎 No

SECTION 2 - SALES & TRADING

Sales & Trading

For: S&T desk (color / flow / risk) + client-facing sales

Block-trade execution + market-impact plan

You have a large order to work and want a structured execution plan with honest impact framing before you touch the market.

Copy & paste into your own LLM

You are a trader planning EXECUTION of a large order. Details: [NAME, side, size vs ADV, urgency, current liquidity/spread, any benchmark]. Produce: 1. An EXECUTION-STRATEGY comparison (agency vs risk/block, VWAP/TWAP, POV, dark vs lit, opening/closing auction participation): mechanics, when each fits, and the trade-off between impact and timing risk. Do not quote a slippage number I did not give you — describe direction and drivers. 2. A MARKET-IMPACT framing: the qualitative drivers (size vs ADV, volatility, spread, news) and how each pushes impact, clearly labeled as framing, not a measured estimate. 3. A SCHEDULING sketch across the session with the checkpoints to reassess. 4. The RISKS: information leakage, adverse selection, and what would make me pause the order. 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.

Why it works: Execution plans go wrong when a made-up slippage number is treated as a measurement; separating strategy trade-offs from clearly-labeled impact framing keeps the plan honest and desk-ready without false precision.

Useful? 👍 Yes👎 No

SECTION 3 - INVESTMENT MANAGEMENT

Investment Management

For: Buy-side analysts & PMs (research / theses / portfolio)

Short thesis construction + borrow & catalyst path

You have a short idea and want it built with the risk asymmetry, borrow, and catalyst path made explicit before you size it.

Copy & paste into your own LLM

You are a buy-side analyst constructing a SHORT THESIS for [NAME]. Using only what I provide, produce: 1. The CORE SHORT logic in 3-4 sentences: what breaks, why the market is wrong, and the mechanism that closes the gap. 2. A RISK-ASYMMETRY read: realistic downside-to-target vs the squeeze/borrow/multiple-rerate risk on the upside. Where a figure is not provided, write "not provided". 3. A CATALYST PATH: the events that would confirm the thesis, with a rough time horizon, and the single data point I should watch each quarter. 4. A BORROW & CROWDING check and the specific conditions under which I should NOT be short this. 5. The strongest LONG rebuttal to my own short. 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.

Why it works: Shorts blow up on the risk nobody wrote down — borrow, crowding, or a re-rate; forcing the asymmetry, the borrow check, and the best long rebuttal surfaces the unswept risk before it's a P&L problem.

Useful? 👍 Yes👎 No

SECTION 4 - CROSS-CUTTING

Financial Analysis & Modeling

For: All roles — IB modeling, IM valuation, S&T scenario work

WACC build interrogation

Your discount rate drives the whole valuation and you want every component of the WACC challenged before you trust it.

Copy & paste into your own LLM

You are a valuation reviewer interrogating a WACC build I paste: [COMPONENTS: risk-free, ERP, beta, cost of debt, tax rate, capital-structure weights]. Produce: 1. A COMPONENT-BY-COMPONENT challenge: for each input, is the source/convention defensible, what range is reasonable, and how sensitive is WACC to it. Where a figure is not provided, write "not provided" — do not supply a market number from memory. 2. A CONSISTENCY check: does beta match the assumed capital structure (relever?), is the risk-free tenor matched to cash-flow horizon and currency, is the tax rate marginal vs effective. 3. A SENSITIVITY read: the WACC range across reasonable inputs and which single input moves it most. 4. The 3 assumptions a PM/VP will push on first, and my best answer for each. 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.

Why it works: WACC is precision theater when unlabeled guesses are ranked like measurements; forcing each component's defensibility, an internal-consistency check, and a sensitivity range replaces a false-precision point estimate with a defensible band.

Useful? 👍 Yes👎 No

SECTION 5 - CROSS-CUTTING

Pitch & Presentation

For: All roles — IB pitchbooks/IC memos, IM idea write-ups, S&T client notes

Board / discussion-materials storyline for a decision ask

You're preparing discussion materials for a board or committee that must decide something, and the deck needs to drive to the ask, not narrate.

Copy & paste into your own LLM

You are structuring BOARD / DISCUSSION MATERIALS for a specific decision. Context: [THE DECISION / ASK, the audience, the options, what I know]. Produce: 1. The ONE-SENTENCE ask and the recommendation up front. 2. A STORYLINE: an ordered list of section action-titles (each a conclusion, not a topic) that walk the board from situation -> complication -> options -> recommendation -> decision. 3. Per section, the EXHIBIT or evidence that proves that title and the single takeaway it must land. 4. A DECISION slide: the options, the recommendation, the trade-offs, and the explicit decision being requested with a default-if-deferred. Flag anywhere I'm asserting something the materials don't yet support. 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. Treat the output as a first draft for professional review before any external use.

Why it works: Board decks fail when analysis never resolves into a decision story; forcing conclusion-titles, an evidence-per-section map, and an explicit decision slide with a default turns a data dump into materials that actually drive a call.

Useful? 👍 Yes👎 No

Which section is most useful to you this week?

One tap — it shapes which prompt leads next week.

What would you like to see more of?

Prompt of the Week (Pro)

This week's bonus: a 'comps table builder' that turns a peer set into a formatted trading-comps grid with the multiples flagged as clean vs adjusted. Pro members get the full prompt in the archive.

Your prompt archive

Every prompt we’ve shipped — browse the full back-catalog.