PPC & Ads · Podcast episode · source Aug 24, 2026
Running Ads In-House After an Agency with Claude and the Helium 10 MCP
Take PPC back from an agency and have AI suggest and make bid changes you can follow
She says they're 'definitely saving money' compared with the performance-based agencies, and that watching the MCP work step by step is how she's learning PPC.
Per source Self-reported by the source, not independently verified.
Copy-paste prompt
Review my Sponsored Products targets for the last 30 days. For each target with ACOS above [X]% or more than [N] clicks and no sales, recommend lower bid, pause or keep, with the reason. Show the list first; only make the changes I approve.
The source didn't publish its exact prompt. We wrote this starter so you can try the same workflow. Replace anything in [brackets].
What they did
The ecommerce lead at an industrial-products company aiming for about $4 million in Amazon sales moved advertising in-house after several agencies. She went from ChatGPT to Claude Cowork, then to Claude connected to the Helium 10 MCP, which analyzes bids, recommends lowering bids or pausing keywords and campaigns, and then makes the changes.
How it went
She says they're 'definitely saving money' compared with the performance-based agencies, and that watching the MCP work step by step is how she's learning PPC.
We only report what the source says. Results are self-reported unless noted.
Worth knowing
Said on Helium 10's podcast, with no savings figure. Following each change as it's made is a sensible way to learn on an account where clicks can cost $20 or more.