PromptSharpPrompt LibraryCPG › Search-term harvest → campaign structure

Digital Marketing & Retail MediaFREE

Search-term harvest → campaign structure

A messy search-term report needs to become campaign structure: groups, match types, negatives, and a naming convention.

The prompt — copy and run it

You are a retail search-advertising planner restructuring campaigns from a search-term report. I will paste the report rows (term, impressions, clicks, spend, sales where available). Produce:

A) A GROUPING TABLE assigning every meaningful term to branded / category / competitor-adjacent / long-tail, with a match-type suggestion per group and a NEGATIVE-KEYWORD list (terms burning spend without sales in my data).
B) BUDGET-SPLIT logic across the groups tied to the performance numbers I gave — where a group's data is too thin to judge, say so instead of guessing.
C) A NAMING CONVENTION for the restructured campaigns that makes next quarter's report self-explanatory.

Report rows: [PASTE: search-term report with performance columns]

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.

How to use this prompt

  1. Copy the full prompt above with the Copy button.
  2. Fill in your inputs. Replace each bracketed placeholder with your specifics: [PASTE: search-term report with performance columns]
  3. Paste into ChatGPT, Claude, or Gemini and run. Read the reality guardrail below before you act on the output.

Why this prompt works

Search-term reports are where budget quietly leaks — everyone means to restructure and nobody does. Having the model do the tedious grouping and negatives pass in minutes removes the excuse, and the naming convention is the gift to whoever inherits the account.

Get a prompt like this every day

The PromptSharp CPG Brief ships one desk-ready prompt every weekday — free on the web today. Free forever. Today's CPG issue is live on the web right now — subscribe and we email you the sample issue immediately, then the CPG daily every weekday as its email edition ships. Unsubscribe anytime.

Subscribe free → Read a sample issue
Reality guardrail: this prompt makes the model reason from data you paste — it does not source or verify facts for you. Check every claim, keep confidential data out of consumer AI tools, and follow your employer's AI-use policy.

Frequently asked

When should I use this prompt?

A messy search-term report needs to become campaign structure: groups, match types, negatives, and a naming convention.

Why does this prompt work?

Search-term reports are where budget quietly leaks — everyone means to restructure and nobody does. Having the model do the tedious grouping and negatives pass in minutes removes the excuse, and the naming convention is the gift to whoever inherits the account.

Related CPG prompts

CPG

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 increm…

CPG

PDP rewrite: title, bullets, and search terms that convert

A product page is underperforming in retailer search. Rewrite it inside the style rules — with every claim flagged for substantiat…

CPG

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.…

CPG

Budget allocation across retail media networks

One budget, several networks. Build the allocation argument from last period's results — and name what you would need to reallocat…

CPG

Trade calendar × media sync: find the orphaned weeks

The trade calendar and the media plan were built by different teams. Find the promo weeks with no media and the media weeks with n…

CPG

Creator brief for a CPG item: claims-safe and actually usable

You need creators briefed for a launch — with the claims language locked down before content gets made, not after.…

CPG

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.…

All CPG free prompts

The PromptSharp CPG Brief page — five full free prompts plus today's issue.

PromptSharp Daily — free

The cross-vertical sampler: one sharp, copy-paste prompt each day, rotating across the roster. Two things in one brief: you get better at AI and prompting, and you see the sharpest prompts from across the network.

Double-opt-in. Unsubscribe anytime. No spam, ever.

Better together
Make prompts remember you: Brainfile

Even a sharp prompt starts from zero unless your AI knows you. Brainfile is persistent context — your work, voice, and priorities loaded into every session. Brainfile is the memory; PromptSharp is the playbook. Together they compound — the same prompt gets sharper because it runs on YOUR context.

Set up your brainfile →

Want both? The All-Access + Brainfile annual bundle covers the pair.

PromptSharp prompts are drafted with AI assistance and human-reviewed. They structure how a model reasons over data you provide — they do not source or verify facts for you, and you own every output. Nothing here is financial, legal, tax, or investment advice. Never paste confidential, client, or material non-public information into consumer AI tools; follow your employer's AI-use policy. © 2026 PromptSharp.