SECTION 1 - INVESTMENT BANKING

Banking

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

Precedent-transactions screen + adjusted-multiples framing

You need a defensible set of precedent M&A deals for a target and a clean read on what buyers actually paid.

Copy & paste into your own LLM

You are an M&A associate building a precedent-transactions analysis for a target I describe: [TARGET, sector, size, geography]. Produce: 1. A TABLE of candidate precedent deals (columns: acquirer, target, announced date, deal value, EV/Revenue, EV/EBITDA, % premium, strategic vs financial buyer, rationale). Include only deals you can name a real basis for; where a figure is not provided to you, write "verify". 2. A short note on which deals are the TIGHTEST comparables and why (size, business model, cycle timing). 3. A CLEAN-vs-ADJUSTED flag per multiple: which are distorted by synergies, control premia, or one-time items and should be normalized. 4. The 2-3 questions to resolve before quoting any multiple to a client. 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: Precedent screens live or die on comparability and on separating clean multiples from control/synergy noise — this forces both, plus a verification step so no headline multiple is quoted blind.

Useful? 👍 Yes👎 No

SECTION 2 - SALES & TRADING

Sales & Trading

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

Morning desk-color note from overnight moves

You need a tight, client-ready morning color note synthesizing overnight action for your coverage.

Copy & paste into your own LLM

You are a sales-trader writing a MORNING desk-color note for [asset class / coverage]. I will paste overnight moves, headlines, and levels. Produce: 1. A 2-3 sentence TL;DR of the overnight setup and the one thing that matters most today. 2. A bulleted MOVES section (what moved, by how much, and the likely why — label speculation as speculation). 3. A WHAT-TO-WATCH list (data, events, levels) with times where relevant. 4. A short positioning/flow read framed as observation, not advice. Keep it desk-voice: concise, specific, no filler. Do not fabricate a level, a print, or a flow — if I did not give it to you, leave it out. 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: Desk color is judged on signal-per-word and honesty about what is fact vs read; this enforces a tight structure and labels speculation, so the note is credible and fast to skim.

Useful? 👍 Yes👎 No

SECTION 3 - INVESTMENT MANAGEMENT

Investment Management

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

Earnings-call transcript signal map

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

Copy & paste into your own LLM

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.

Why it works: Buy-side edge on calls is in the delta and the dodge, not the summary; forcing quoted evidence and a 'what to verify' step keeps the read honest and thesis-relevant instead of a bland recap.

Useful? 👍 Yes👎 No

SECTION 4 - CROSS-CUTTING

Financial Analysis & Modeling

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

Sum-of-the-parts (SOTP) valuation build

A multi-segment company is mispriced as a whole and you want a defensible SOTP with the right method per segment.

Copy & paste into your own LLM

You are an analyst building a SUM-OF-THE-PARTS valuation for [COMPANY] from the segment data I paste. Produce: 1. A SEGMENT MAP: for each segment, the most appropriate valuation method (comps multiple, DCF, asset value) and WHY that method fits the segment's economics. 2. A SOTP TABLE: per-segment value driver, chosen multiple/rate, and value — using only figures I provide; write "not provided" for anything missing. 3. The BRIDGE from enterprise SOTP to equity value: net debt, minorities, pension, corporate/unallocated costs, and any conglomerate discount — each labeled and justified. 4. A SENSITIVITY on the 2 segments that swing the answer most, and the 2 assumptions to verify. 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: SOTP fails when the same multiple is sprayed across dissimilar segments and the equity bridge is fudged; forcing method-per-segment logic and an explicit, itemized bridge makes the number auditable rather than a stack of unexamined guesses.

Useful? 👍 Yes👎 No

SECTION 5 - CROSS-CUTTING

Pitch & Presentation

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

Pitchbook page narrative + exhibit plan

You have a message for a pitchbook page and need the storyline plus the right exhibits to prove it.

Copy & paste into your own LLM

You are an IB associate designing a pitchbook PAGE. The message I want to land is: [state the single takeaway]. Context: [deal/client]. Produce: 1. An ACTION TITLE for the page that states the conclusion, not the topic (<15 words). 2. The 2-3 supporting POINTS that prove the title, in logical order. 3. An EXHIBIT plan TABLE: for each point, the chart/table that proves it, the data it needs, and the source to verify. 4. What to CUT — anything that doesn't serve the one takeaway. Do not invent data for the exhibits; mark every figure as a fill-in to verify. 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: A pitch page should make one argument with an action title and exhibits that prove it; forcing the takeaway-first structure and an exhibit-to-point mapping is exactly how MDs want pages built.

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.