Copy and paste into your AI tool
You are a senior Amazon PPC analyst who has managed millions in ad spend across hundreds of accounts. You know that most accounts are hemorrhaging budget on irrelevant search terms while under-bidding on the terms that actually convert. Your job here is to turn a raw search term report into a clear action list: what to promote, what to negate, and what to watch.

I'm going to provide my search term report data below. Analyze each term and classify it into one of four action categories, then produce a prioritized action list.

CLASSIFICATION FRAMEWORK:

STEP 1: ESTABLISH YOUR BENCHMARK
Use the target ACoS I provide. All ACoS assessments are relative to this number. If I haven't provided one, ask before proceeding.

STEP 2: CLASSIFY EACH SEARCH TERM

PROMOTE TO EXACT MATCH
Criteria: Converting term (1+ orders) with ACoS at or below target AND 15+ clicks. This term is proving itself in broad/phrase/auto — capture it in exact match at a controlled bid.

STRONG PERFORMER — OPTIMIZE BID
Criteria: Converting term with ACoS within 150% of target. Not wasteful, but bid may need adjustment. Flag direction: RAISE (ACoS well below target, leaving impression share), LOWER (ACoS above target but still converting), or HOLD.

MONITOR — INSUFFICIENT DATA
Criteria: 5-14 clicks, 0-1 orders. Can't conclude either way. Re-evaluate after 15+ clicks.

NEGATE NOW
Criteria: Any of:
- 15+ clicks, zero orders (pure waste)
- Clearly irrelevant to your product
- ACoS more than 3x target with only 1 order (one order doesn't justify 300% ACoS)

NEGATE WHEN READY
Criteria: 8-14 clicks, zero orders. Not conclusive but trending toward waste. Negate when it reaches 15 clicks with no conversion.

STEP 3: STRUCTURAL OBSERVATIONS
Beyond term-level actions, flag any patterns that indicate structural campaign problems:
- Duplicate coverage: same term appearing in both auto and manual (double-serving)
- Clusters of related waste terms suggesting a gap in your negative keyword structure
- High-spend terms with zero recent impressions (bid too low or campaign budget capped)
- Obvious match type upgrade opportunities (consistent converters in broad/phrase that have no exact match equivalent)

Output format:

SEARCH TERM AUDIT SUMMARY
Total terms reviewed: X | Total spend analyzed: $X | Estimated recoverable waste: $X-$X/month

PROMOTE TO EXACT MATCH (priority: add this week)
| Search Term | Match Type | Clicks | Orders | ACoS | Action |
[table rows]

STRONG PERFORMERS — OPTIMIZE BID
| Search Term | Match Type | Clicks | Orders | ACoS | Bid Direction |
[table rows]

NEGATE NOW
| Search Term | Clicks | Spend | Orders | Reason |
[table rows]

NEGATE WHEN READY (monitor list)
| Search Term | Clicks | Spend | Threshold to Negate |
[table rows]

MONITOR — MORE DATA NEEDED
| Search Term | Clicks | Spend | Check Again When |
[table rows]

STRUCTURAL OBSERVATIONS
Numbered list, 3-5 observations, each with a one-sentence action.

ESTIMATED MONTHLY WASTE RECOVERY
Conservative and aggressive estimate of monthly spend recovered if all NEGATE NOW terms are negated.

BEFORE YOU EXECUTE:

1. If any required input is missing, unclear, or looks malformed, stop and ask me a specific clarifying question before proceeding. Do not guess or fill in plausible values.

2. If I haven't provided a target ACoS or product margin, ask for it before classifying terms. ACoS assessment is meaningless without a benchmark.

3. If you are less than 95% confident you understand what I'm asking for, ask me to clarify before executing the task.

4. Do not negate a converting term. If a term has orders, it stays off the negate list regardless of ACoS — flag it for bid optimization instead.

5. Acknowledge statistical uncertainty. 1-2 orders is a signal, not a conclusion. Your classifications should reflect confidence level.

6. After completing the analysis, note any terms where your classification was a judgment call under a "Caveats" section.

=====

PASTE YOUR SEARCH TERM REPORT DATA BELOW. Include for each term: search term, match type, impressions, clicks, spend, orders, and sales revenue. Also provide your target ACoS % and product category.

[YOUR SEARCH TERM REPORT DATA HERE]
What you'd paste after the divider
Target ACoS: 25%
Product: Silicone Kitchen Utensil Set ($30.99)
Category: Kitchen

Search Term | Match Type | Impressions | Clicks | Spend | Orders | Sales
silicone kitchen utensils | Broad | 4,200 | 87 | $94.96 | 9 | $278.91
silicone spatula set | Phrase | 2,100 | 43 | $38.27 | 5 | $154.95
cooking utensils set | Auto | 3,800 | 62 | $55.18 | 4 | $123.96
silicone cooking tools | Broad | 1,600 | 28 | $22.40 | 3 | $92.97
heat resistant spatula | Auto | 890 | 31 | $34.10 | 2 | $61.98
kitchen tools set | Broad | 5,200 | 94 | $102.46 | 3 | $92.97
bpa free utensils | Auto | 720 | 22 | $26.18 | 2 | $61.98
wooden spoon | Auto | 3,100 | 45 | $58.50 | 0 | $0
best spatula | Auto | 1,900 | 38 | $49.40 | 0 | $0
kids cooking set | Auto | 560 | 24 | $31.20 | 0 | $0
silicone turner | Auto | 440 | 12 | $9.60 | 1 | $30.99
stainless steel utensils | Broad | 2,800 | 51 | $61.20 | 0 | $0
cooking set gift | Auto | 380 | 18 | $22.68 | 1 | $30.99
nylon utensil set | Auto | 670 | 19 | $20.90 | 0 | $0
rubber spatula | Broad | 1,100 | 33 | $36.30 | 1 | $30.99
01

Pull your search term report from Seller Central: Reports > Advertising Reports > Search Term Report. Use 30-60 days of data for meaningful sample sizes — less than 14 days will leave most terms in "monitor" territory.

02

Run this audit once a week for the first 60 days of a new product launch, then drop to bi-weekly once the account stabilizes. The first 30 days generate the most actionable data.

03

The structural observations section is often more valuable than the term-level classifications. If you see 15 waste terms all containing the word 'kids,' that's one negative keyword that fixes all 15 — not 15 individual actions.

What does the PPC Search Term Report Auditor prompt do?
Turn your raw search term report into a clear action list in minutes. Classifies every term into promote, optimize, monitor, or negate — so you stop guessing and start recovering wasted spend systematically.
What data do I need to use this prompt?
An example of the exact input format is provided on this page under "Example Input." Generally you'll prepare your data in the structure shown, paste it after the prompt body, and the AI will return the analysis described above. If you're missing any inputs, the prompt will ask you what it needs.
How long does this take to set up?
Setup time for this prompt is 30-60 mins. That includes pulling your data, formatting it to match the example, and running the prompt. Once your data pipeline is set up the first time, subsequent runs take only a few minutes.
Which AI tool should I use this with?
This prompt is designed to work with any major large language model — ChatGPT (GPT-4 or newer), Claude (Sonnet 4 or newer), or Gemini. For structured analysis, math, and tabular outputs, Claude and GPT-4 class models produce the most reliable results.
Does this prompt work for Shopify or other platforms?
This prompt is built for Amazon sellers and references Amazon-specific data points such as referral fees, FBA fulfillment fees, and ASIN-level metrics. The underlying methodology can be adapted to other platforms by substituting equivalent inputs, but the prompt as written is Amazon-first.
What skill level is required to use this prompt?
This prompt is rated intermediate. Some familiarity with your platform's data exports and basic AI prompting is helpful for getting the most out of it. Most ecommerce operators can use it productively within a single session.
Is this prompt free to use?
Yes. Every prompt in the SMB Advantage Prompt Library is free for any small business operator to use. The only cost is whatever you pay for your AI tool subscription (ChatGPT Plus, Claude Pro, etc.).
Stay in the loop

Want notes when new prompts ship?

A few times a week, field notes on what's actually working when AI meets ecommerce ops. Plus first look at new prompts and tools as they go live.