Syndicated Data

CPG Data & Insights

For: Category managers, insights analysts, and sales analytics teams working in Nielsen, Circana, or SPINS

Due-to bridge: explain exactly why volume moved

Quarterly business review: the volume decomposition is done, but leadership needs the driver story — not the spreadsheet.

Copy & paste into your own LLM · open in archive →

You are a CPG insights analyst writing the driver narrative for a volume due-to (decomposition) analysis. I will paste the decomposition outputs and context. Produce:

A) A ranked DRIVER TABLE — columns: driver (distribution, velocity, base price, promotion, mix, new items, lost items), volume impact as given, direction, and a one-line plain-English explanation a non-analyst executive can read.
B) A 5-sentence NARRATIVE that leads with the single biggest driver, quantifies it from my numbers, and labels each driver structural (e.g., distribution losses) vs temporary (e.g., promo timing).
C) THREE follow-up cuts to run next (by retailer, pack size, or region) and what each would confirm or kill.

Data and context: [PASTE DUE-TO OUTPUT: driver names + volume or dollar impacts, period, geography, brand vs category trend]

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in the data I give you, write "not provided" and flag it. Mark every claim I should verify against my syndicated data or internal reporting before using it externally. Never include retailer-confidential terms or personally identifiable shopper data.

Why it works: Due-to outputs are where most category managers stall: the math is done but the story is not. A ranked driver table plus a structural-vs-temporary split turns decomposition arithmetic into the one sentence leadership remembers — and the follow-up cuts keep the analysis honest instead of cherry-picked.

Useful? 👍 Yes👎 No

Category Management

Category & Shopper Insights

For: Category managers, category advisors/captains, and shopper insights leads

Category review skeleton: retailer-first, brand-last

The annual category review is due. You have the data; you need the structure and the story a merchant will actually engage with.

Copy & paste into your own LLM · open in archive →

You are a category advisor building a retailer category review. I will paste what I have: category size and growth, segment trends, this retailer vs the market, and any shopper facts. Produce:

A) A 10-slide SKELETON as a numbered list — every slide gets a full-sentence HEADLINE (the 'so what', not a topic label) and the single data cut that belongs on it.
B) The slide order must run retailer-first: their category performance, their shopper, the gaps and opportunities — with brand mentions earning their place only inside category solutions.
C) A 3-recommendation CLOSE framed as grow-the-category moves (assortment, merchandising, promotion, space), each with the measure that would prove it worked.

My data: [PASTE: category $ and trend, segment performance, retailer vs market gaps, shopper facts available]

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in the data I give you, write "not provided" and flag it. Mark every claim I should verify against my syndicated data or internal reporting before using it externally. Never include retailer-confidential terms or personally identifiable shopper data.

Why it works: Merchants sit through a dozen category reviews a season and can smell a brand pitch wearing a category costume. Headline-first slides in retailer-first order is the exact structure the best category captains use — and demanding the proving measure per recommendation makes the close accountable.

Useful? 👍 Yes👎 No

Innovation Pipeline

Innovation & New Products

For: Brand managers, innovation leads, and new-product analytics teams

White-space map from the data you already have

Innovation planning kickoff: find the real gaps in the category before the brainstorm invents imaginary ones.

Copy & paste into your own LLM · open in archive →

You are an innovation strategist mapping category white space. I will paste segment sizes and growth, price tiers, the claims and attributes present in the category, and my current portfolio. Produce:

A) A MATRIX of segments × price tiers showing occupancy from my data: where my portfolio plays, where competitors are, and which cells are empty — with every empty cell verified against the data I gave, not assumed.
B) FIVE white-space candidates ranked by size-of-prize logic using only my numbers (segment size × growth direction), with gaps in the sizing marked 'not provided' rather than filled in.
C) For the top TWO candidates: the 'what must be true' list (shopper need evidence, margin structure, route to shelf) and the cheapest validation test for each.

My data: [PASTE: segment sizes and trends, price tiers, attribute/claims landscape, your item list]

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in the data I give you, write "not provided" and flag it. Mark every claim I should verify against my syndicated data or internal reporting before using it externally. Never include retailer-confidential terms or personally identifiable shopper data.

Why it works: Innovation funnels fill with ideas that ignore the category's actual structure. A verified occupancy matrix grounds the brainstorm in where demand and price architecture already leave room — and the 'what must be true' discipline kills zombie concepts before they eat a stage-gate cycle.

Useful? 👍 Yes👎 No

Retail Media & Digital

Digital Marketing & Retail Media

For: Brand marketers, commerce media managers, and e-commerce content owners

Retail media readout: platform ROAS vs what you can actually claim

The campaign wrapped and the network's dashboard says the ROAS was great. Write the readout that separates attribution from incrementality.

Copy & paste into your own LLM · open in archive →

You are a retail media analyst writing an honest post-campaign readout. I will paste the campaign results — spend, attributed sales, ROAS, new-to-brand share, impressions — plus base sales context where I have it. Produce:

A) A READOUT that separates PLATFORM-ATTRIBUTED results from what is PLAUSIBLY INCREMENTAL, listing exactly which numbers are missing to make an incrementality claim (holdout results, base-sales counterfactual, halo measurement) — and refusing to fill those gaps with assumptions.
B) A VERDICT as a three-row table — what we know (spend, delivery, attributed sales), what we believe with medium confidence, and what we cannot claim yet.
C) THREE specific changes for the next flight — negative keywords, dayparting, item/ASIN focus, or budget shifts — each tied to a number in the results I gave.

Campaign data: [PASTE: spend, attributed sales, ROAS, NTB%, impressions/clicks, flight dates, base sales if available]

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in the data I give you, write "not provided" and flag it. Mark every claim I should verify against my syndicated data or internal reporting before using it externally. Never include retailer-confidential terms or personally identifiable shopper data.

Why it works: Retail media budgets keep growing while most readouts recycle the network's own attribution as proof. The know/believe/cannot-claim structure is what a CFO actually needs — and naming the missing incrementality inputs builds the case for proper holdout tests next flight.

Useful? 👍 Yes👎 No

Sell the Insight

Presentations & Sales Story

For: Sales leads, national account managers, and insights teams who present to retailers and leadership

So-what skeleton: slide titles that carry the argument

The analysis is finished and the deck is due. Build the skeleton where the titles alone tell the story.

Copy & paste into your own LLM · open in archive →

You are a presentation coach for insights teams, trained on assertion-evidence structure. I will paste my analysis summary, the audience, and the decision I am asking for. Produce:

A) A SLIDE-BY-SLIDE SKELETON where every TITLE is a full-sentence assertion (the 'so what' — never a topic label like 'Category Overview'), and the body spec is the ONE exhibit that proves that sentence, named precisely (which chart, which cut, which comparison).
B) The 30-SECOND VERSION: if the meeting collapses, the three sentences I say in the hallway.
C) A CUT LIST: everything in my summary that belongs in the appendix — with the rule used to demote it (does not advance the decision).

My analysis: [PASTE: findings summary, audience, the decision you want made]

Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in the data I give you, write "not provided" and flag it. Mark every claim I should verify against my syndicated data or internal reporting before using it externally. Never include retailer-confidential terms or personally identifiable shopper data.

Why it works: Read only the titles of most CPG decks and you learn nothing — they are labels, not arguments. Assertion-evidence structure is the highest-value presentation habit in the industry, and drafting it as a skeleton first means the story gets fixed before hours go into formatting.

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 'due-to bridge builder' that turns your quarterly volume decomposition into a one-slide bridge-chart spec with every driver ranked, annotated, and labeled structural vs temporary. Pro members get the full prompt in the archive.

Your searchable archive

Every prompt we’ve shipped, organized by section and task.