YouTube's official Test & Compare feature runs 7 days. Here's the 48-hour fast-iteration loop I use with creator clients — including when to trust the data, when not to, and the AI tools that actually shorten the cycle.
A 7-email welcome series built around the emotional arc of onboarding — not the product tour. Each email has a goal, timing, copy guidance, and an AI prompt that generates it. Long-form, copy-paste ready.
A working marketer's system for writing the first 3 seconds of a TikTok — the three jobs a hook has to do, five named patterns I actually use, and the AI workflow I run to draft 20 hooks in 15 minutes (and kill 16 of them).
A practical 4-email, 21-day re-engagement sequence for cleaning an inactive email list, with exact send timing, copy, and the post-flow suppression step most teams skip — plus where AI helps and where it ruins the breakup email.
A real content audit story: 1,200 URLs, 340 flagged, 280 deleted, 23% traffic recovery. The 7 signals I score pages on, the AI workflow that did it in two weeks, and the hard triage calls nobody talks about.
A no-code Zapier workflow that catches Shopify abandoned carts, lets AI write the recovery email, sends it through Gmail or Klaviyo, and follows up automatically. From a real client that recovered $14k in the first month on a free Zapier tier.
Forget 30-page brand books. The voice your readers actually hear lives in the posts you've already shipped. Here's the exact prompt, the 12 dimensions I measure, and the workflow to turn your archive into a one-page style guide that AI tools will actually follow.
A practical workflow for using Google's NotebookLM as a marketing research analyst — uploading competitor PDFs, G2 review dumps, and analyst reports, then querying them like a real research analyst. Includes the exact setup steps, the 6 prompts that actually return usable research, the Audio Overview trick, and the three gotchas to watch for.
Seventh Sense, Klaviyo Smart Send, and the other AI send-time tools all need thousands of engaged subscribers before they get useful. Here's what to do in the meantime — 5 practical methods that work on lists under 2,000, with the prompts and Excel formulas I use to find them.
A production-grade 4-agent content pipeline built in n8n. Each agent has a single job, a structured output, and a retry path. Includes the full workflow JSON you can paste into n8n, the prompts I use for each agent, the state schema that flows between them, and the failure modes that have actually cost me time.
A working build of a Claude Computer Use agent that browses Google like a person, scrapes People Also Ask and top results, and produces a 1,200-word content brief in 4 minutes — with the exact system prompt and Docker setup I use.
A practical walkthrough of using OpenAI Operator to crawl 20 competitor landing pages, extract positioning patterns, and turn raw screenshots into a positioning map — no code, no scraped JSON, just a browser agent and a well-built prompt.
