PPC & Ads · from a Blog post, The case study page shows no date. · Added

Adjacent Auto Terms with Claude and Intentwise

Catch budget leaking into adjacent-category search terms in auto campaigns

Scott Kennedy, VP Digital Strategy & Analytics, says: 'You go from I learned something to I did something about it very fast.'

Per source From the tool's vendor, not independently tested.

Copy-paste prompt

Copy-paste promptPrompt written by us, based on this case
Using my connected Amazon ads data, list search terms in auto campaigns from the last 30 days that belong to an adjacent category rather than our core category. For each, show spend, sales, ROAS and share of that campaign's spend. Flag terms where spend share is high and ROAS is below [target], and draft a short note to our product manager summarizing the ones worth keeping vs pausing. Don't change anything.

The source didn't publish its exact prompt. We wrote this starter so you can try the same workflow. Replace anything in [brackets].

See the original Blog post

What they did

Franklin Sports, a sports-equipment brand, used to hunt performance anomalies by digging through Excel files and bouncing between teams. With Intentwise's AI Gateway MCP feeding trusted Amazon (and other channel) data into Claude, entry-level analysts ask deep product-performance questions and bring findings to the rest of the team. Claude isolates search terms from an adjacent category that slipped into auto campaigns, shows what share of budget they take and what ROAS they return, and can draft an email to a product manager or turn off an external campaign.

How it went

Scott Kennedy, VP Digital Strategy & Analytics, says: 'You go from I learned something to I did something about it very fast.' Intentwise reports five employees upskilled as MCP users. No ACoS or dollar figures are given.

We only report what the source says. Results are self-reported unless noted.

Worth knowing

A vendor case study with no date on the page. The useful idea is measuring adjacent-category auto terms as a share of budget and ROAS before cutting them.

Original source

Blog postIntentwisePublished The case study page shows no date. · intentwise.com https://www.intentwise.com/casestudy/franklin-sportsOpen the source

Keep going

Related use cases

PPC & AdsShows real results

Agency Wasted-Spend Checks and Unit Forecasts with Claude and Intentwise

Find wasted spend across client accounts and build forecasts without gathering reports
10 minutes“a bottoms-up unit forecast for all of the agency's Amazon brands in 10 minutes” vendor claim
ToolsClaude, Intentwise AI GatewaySourceBlog post · IntentwiseSharedThe case study page shows no date.PromptWritten by us
Show promptHide prompt for Agency Wasted-Spend Checks and Unit Forecasts with Claude and Intentwise,Written by us
For each client account, list every campaign where average CPC in the last 7 days is more than double its 30-day average. For each one, check: placement bid adjustments (top of search, product pages), and any non-brand search terms showing up in campaigns named as branded. Give me a table of campaign, CPC change, likely cause and the fix.

PPC & Ads

AMC LTV Cohorts and Client Decks with Claude

Measure shopper lifetime value by ASIN and turn it into client decks ToolsClaude, Intentwise AI GatewaySourceBlog post · IntentwiseSharedThe case study page shows no date.PromptWritten by us
Show promptHide prompt for AMC LTV Cohorts and Client Decks with Claude,Written by us
From my AMC cohort data, build a 12-month matrix for [ASIN]: customers by first-purchase month, and their repeat purchases and revenue in each following month. Then compare the 12-month LTV of customers acquired in November-December with those acquired in other months, and tell me what that means for how much I should pay to acquire a holiday customer.

PPC & Ads

Ad Swing Diagnosis with Claude and Intentwise

Find out why ad performance swung and act on it without opening the ads console ToolsIntentwise AI Gateway, ClaudeSourceBlog post · IntentwiseSharedThe case study page shows no date.PromptWritten by us
Show promptHide prompt for Ad Swing Diagnosis with Claude and Intentwise,Written by us
Campaign set A is running at about 60% ACOS with flat sales and set B at about 80% ACOS with growing sales. Using the last 60 days of search term data, find the keywords and close variants whose spend or sales moved between campaigns, and show where each one is converting best. Recommend where to keep each keyword and where to add it as a negative.

PPC & AdsShows real results

80/20 PPC Audit and Exact-Match Campaign Builder Skills with Claude

Find the SKUs and search terms that drive most ad sales, then build exact and broad campaigns with break-even bids
10 hours“used to take us 10 hours” self-reported
ToolsClaudeSourceYouTube video · Dr. Travis Zigler (Profitable Pineapple)SharedNov 10, 2026PromptWritten by us
Show promptHide prompt for 80/20 PPC Audit and Exact-Match Campaign Builder Skills with Claude,Written by us
Using the attached Sponsored Products search term report and business report (child ASIN, same date range): 1) list the SKUs and search terms that make up 80% of sales and ad sales, 2) list search terms with spend and zero orders, 3) for search terms with 3+ orders, build single-keyword exact campaigns with a starting bid = (price - COGS - Amazon fees) x conversion rate, using my COGS and fees: [paste]. Output a sheet. Don't pause anything.

PPC & Ads

Daily Amazon Ad Suggestions from Claude, Reviewed by Codex

Get daily Amazon ad change suggestions, with a second AI checking them before anything changes ToolsClaude, CodexSourceX post · runthatBMCSharedNov 10, 2026PromptWritten by us
Show promptHide prompt for Daily Amazon Ad Suggestions from Claude, Reviewed by Codex,Written by us
You are reviewing another AI's proposed Amazon ad changes before they go live. Here are my rules: [paste rules, e.g. max bid, ACoS target, brand terms never negated], yesterday's report: [paste], and the proposed changes: [paste]. Approve or reject each change with a one-line reason, flag any that break a rule or rest on fewer than [10] clicks, and output only the approved list.