Skip to content

Trade Spend Efficiency Analyzer

Analyze trade spend efficiency across your portfolio, after the fact.

What is the Trade Spend Efficiency Analyzer?

The Trade Spend Efficiency Analyzer is a free AI skill that analyzes how efficiently trade spend performed across a food or beverage portfolio or time period, using data you paste in after the fact. You give it your trade spend by SKU, account, or promotion type over a period, plus the incremental sales it's meant to have driven; it returns each spend category ranked by efficiency, the biggest waste and win identified from the data, an account-by-account comparison where possible, and reallocation recommendations for where trade dollars would work harder next period. It is built for sales and revenue teams who commit trade budgets in advance but rarely grade how that spend performed once the period closes. Because it works strictly from the data provided, not assumed benchmarks, every efficiency ranking is defensible in a budget conversation. Comparing spend efficiency against live food and beverage demand data helps show whether a low-return period reflects poor execution or a category-wide demand dip no spend level could have overcome.

Who it's for

  • Sales and revenue managers reviewing trade spend after a period closes
  • National account directors comparing trade efficiency across retail accounts
  • Finance-aligned sales teams building the case for next year's trade budget
  • Category and insights teams analyzing spend efficiency across a portfolio

What you get

  • Trade spend ranked by efficiency across SKUs, accounts or promo types
  • The biggest waste and biggest win identified from your data
  • An account-by-account efficiency comparison where the data allows
  • Reallocation recommendations for next period's trade budget
  • What the data cannot yet explain about a low-return category
  • A leadership-ready summary of trade spend efficiency for the period

How to use it

  1. 1Drop the prompt into ChatGPT, Claude or Gemini.
  2. 2Paste your trade spend and sales data for the period.
  3. 3Answer its clarifying questions about how spend and results were tracked.
  4. 4Ask it to build next period's reallocation plan from the findings.

See it in action

Example input

Reviewing 2 quarters of trade spend across our fictional 'Grovepoint Beverages' RTD tea range (5 SKUs) at 3 retail accounts. Total spend: $340,000 — $120,000 on secondary displays (drove an estimated 48,000 incremental cases), $95,000 on feature ads (drove an estimated 22,000 incremental cases), and $125,000 on off-invoice discounts (drove an estimated 14,000 incremental cases, though we're not fully sure how much was just cases that would have sold anyway). Want to know where the money worked hardest and where to cut.

Example output

Trade spend efficiency analysis — Grovepoint Beverages, 2 quarters, $340,000 total spend

Efficiency ranked by spend type, cost per incremental case
- Secondary displays: $120,000 ÷ 48,000 incremental cases = $2.50 per incremental case. The most efficient spend type by a wide margin.
- Feature ads: $95,000 ÷ 22,000 incremental cases = $4.32 per incremental case. Moderately efficient, roughly 1.7x the cost per case of displays.
- Off-invoice discounts: $125,000 ÷ 14,000 incremental cases = $8.93 per incremental case, and this is likely the optimistic read. Off-invoice discounts have no built-in mechanism to confirm the 14,000 cases are genuinely incremental rather than cases that would have sold anyway at regular price, you flagged this uncertainty yourself, and it's the right instinct. Treat $8.93 as a floor, not a confirmed number; the true cost per incremental case may be meaningfully higher.

Biggest win
Secondary displays, at $2.50 per incremental case, returned roughly 3.6x more efficiently than off-invoice discounts on the numbers provided. This is the program to protect and likely expand first.

Biggest waste
Off-invoice discounts. At $125,000, this was the largest single spend category by dollars, but the least efficient and the least verifiable, combining the highest cost per case with the lowest confidence that the case counted actually needed the discount to happen. This is the first place to cut before touching displays or feature ads.

Account-by-account comparison
The figures above are blended across all 3 retail accounts. That's the biggest limitation of this analysis: the same $2.50-per-case display efficiency could be driven entirely by your strongest account while masking a weak performer elsewhere, or it could be consistent across all three. [Insert per-account spend and case data — breaking this out by account is the single highest-value next step, since reallocating spend requires knowing which account earns it, not just which spend type does in aggregate.]

What the data cannot yet explain
Whether the off-invoice discount's low efficiency is a structural problem with that spend type, or specific to how it was executed this period, for example whether any of the three retailers agreed to pass the discount through to shelf price versus simply pocketing it. Also unclear: whether feature ad timing lined up with genuine seasonal demand peaks or ran during flatter weeks, which would understate its true efficiency.

Reallocation recommendation for next period
1. Cut off-invoice discount spend by at least a third and reallocate it toward secondary displays, prioritizing the account(s) where display data is strongest once broken out.
2. Before renewing any off-invoice program, require retailer confirmation that the discount reaches shelf price, spend with no compliance visibility should not continue at $125,000 a year unexamined.
3. Track incremental cases by account starting next period, not just by spend type, so the next review can rank accounts as well as programs.

Leadership-ready summary
Over 2 quarters and $340,000 in trade spend, secondary displays delivered incremental cases at $2.50 each, by far the most efficient program, while off-invoice discounts, the single largest spend category at $125,000, delivered the weakest and least verifiable return at roughly $8.93 per incremental case. Recommend cutting off-invoice spend by at least a third next period, reallocating toward displays, and adding account-level tracking so future reviews can identify not just which program works, but which retail relationship earns the investment.

Want this rebuilt with account-level detail once you have that breakout, so the reallocation plan can name specific accounts?

The prompt

Here's the start of the prompt. Download the free bundle for the full, ready-to-paste version — plus the installable Claude Skill and Custom-GPT instructions.

# Role
You are a CPG revenue and trade strategy analyst who grades trade spend efficiency after a period closes, using only the data provided. You separate spend that's genuinely incremental from spend that just discounted sales that would have happened anyway.

# Context I'll provide
- Trade spend data, pasted as text: [SPEND DATA — by SKU, account, or spend type, with incremental sales if tracked]
- Time period: [PERIOD]
- Spend categories covered: [CATEGORIES e.g. feature ads, displays, off-invoice discounts]
- What you already suspect: [HYPOTHESES — optional]
- Audience this analysis is for: [AUDIENCE]

# Your task
1. If the spend data, period, or categories are missing or vague, ask up to 3 clarifying questions BEFORE writing anything.

Frequently asked questions

What is trade spend efficiency analysis?
Trade spend efficiency analysis compares how much incremental sales or cases a dollar of trade investment actually generated, across different spend types like displays, feature ads, and off-invoice discounts, using the data from a period that's already closed. Unlike planning a promotion in advance, it's a retrospective, evidence-based grade on money already spent, so future budgets can shift toward what's actually working. This skill ranks your spend categories by efficiency and flags which figures are less certain.
How is this different from the Trade Promotion & ROI Planner skill?
The Trade Promotion & ROI Planner plans a single promotion's expected ROI before it runs, projecting what a specific upcoming promo should deliver. This skill works in the opposite direction and at a wider scope: it analyzes actual trade spend efficiency after the fact, across a whole portfolio or time period rather than one promotion, using real results you paste in. Plan a single promo's ROI with that skill; grade a whole period's trade spend efficiency with this one.
Which AI models can run this prompt?
Any capable chat model — ChatGPT, Claude, or Google Gemini. The prompt is model-agnostic and works well with pasted spreadsheet-style data; paste your trade spend and sales figures directly into the conversation, or save the prompt as a Custom GPT or reusable skill for a recurring end-of-period trade review.
What if my incremental sales data isn't very reliable?
Say so in your inputs, the skill will flag which efficiency figures depend on uncertain incrementality assumptions, particularly for off-invoice discounts, rather than presenting every number with equal confidence. It will not invent more reliable figures than what you actually have; the output is only as precise as the data behind it, and a rough analysis with honest confidence flags is more useful than a falsely precise one.

Related skills

Want the live data behind sharper outputs?

These skills get better with real-time F&B intelligence. See what Tastewise can do for your team.