A practical case study of using Markdown files as shared memory so multiple AI agents can coordinate without trapping the work inside one model.
Building in Public: The Free Quick Audit Pipeline — From Order to 15-Page Audit to Discovery Call
We made Quick Audits free across every Spotlight vertical, then built an AI pipeline that runs each one at max effort and books qualified owners into a 15-minute call. Here is the entire system, published per our building-in-public principle.
The audit that sold itself: how a one-time DealCon report became our first monthly audit subscription
Matt Bodnar asked for his DealCon authority audit monthly. Here’s the agent-run delta-audit subscription that delivers it — and the first run’s receipts, including a Knowledge Panel descriptor Google rewrote in five weeks.
How a Claude Agent Imported Every Client Site into Bing
A Claude agent moved every Local Service Spotlight client site from Google Search Console into Bing Webmaster Tools, fixed a bulk-import failure, and hit 100% coverage.
How to Replace Your Video Editor with AI Agents
You don’t need a professional video editor anymore. With AI agents like Claude and tools like Descript, you can edit videos, publish to YouTube, write blog posts, and repurpose content across multiple channels without touching any of the technical work yourself. The Content Factory workflow The process is simple. You record a video, whether it’s a Zoom call, a podcast …
How a Claude Agent Verified 46 Sites in Search Console
A Claude agent worked a 46-site Google Search Console verification queue, auto-verifying sites, catching URL typos, and documenting every block.
How an AI Agent Caught a Sheet Typo and Verified 3 Sites
Three law-firm URLs in the queue would not load. A Claude agent traced the shared typo, verified all three for free, and fixed the source data.
How We Harvested Law Firm Link Equity for Law Firm Spotlight
How we found useful BlitzMetrics law firm articles, mapped white-hat internal links to Law Firm Spotlight, and fixed the site’s entity-name split — with every link verified live, not just claimed.
Stop Typing to AI: Give Agents the Context They Need
Short prompts make AI guess. Dennis Yu shows how context-rich voice briefs give AI agents the goal, evidence, constraints, and definition of done they need to deliver useful work.
- Page 2 of 2
- 1
- 2

