A Meta ads operator had Claude build each client an internal dashboard with four parts. 1) Main KPIs, costs and creative win rate, which shows whether the process works or you're getting lucky. 2) A Kanban pipeline from concept to copy to production to live, paused or winner, so bottlenecks are obvious. 3) A batch view: each idea becomes 5 or 6 creatives with different hooks or visuals, so you can tell if the idea won or only one hook did. 4) Landing page performance with a map of which ads send traffic to which page, because "half of bad ads" are an ad-to-page mismatch. It started in Airtable, but Claude's permissions there were limited, so they had Claude convert it to HTML and host it on Vercel behind a password.
← All agent use cases · Creative use cases
A per-client creative ops dashboard built with Claude: idea pipeline, batch results, win rate and ad-to-page map
ClaudeVercel
AdShift lists real agent workflows people have shared publicly. We summarize them and link to the original; check the source before you copy a setup.
More Creative use cases All →
- Seven Claude skills turn 3–5 competitors' live Meta ads into winners, word-for-word hooks, market gaps and a brief for your next ad Nov 11
- A Claude Code operator folder plus MCPs: scan competitors' top ads and landing pages, then generate on-brand statics with Higgsfield Nov 9
- Rip a competitor's best-performing ad format, rewrite it with your own customer research, and have Claude generate the UGC video Nov 6
- An agent that writes ad scripts from your winners and losers, diagnoses dying ads from hook and hold rate, and pulls every ad's funnel metrics each Monday Nov 2
Monday brief
One new agent use case every Monday, alongside the platform changes that matter.