Otto The Tag Auditor checks whether Google actually got the hit
Otto The Tag Auditor walks your site, scores tag health, and names the next fix when Google never received the hit.
Writing
A chatbot question is a conversion touchpoint. Treat it like one.
Why a site chatbot is a conversion touchpoint, and why marketing should measure the path to application — not only whether the bot answered the question.
Introducing Otto: agentic AI for marketing tag audits.
First post about Otto The Tag Auditor — agentic AI for marketing tag audits. Scan, evaluate, recommend, then scan again as a health check. Very initial stage: local build still early on crawl, recommendations, and results plus dashboard.
Week-on-week is a useful signal. It is not a decision.
People asking for an AI summary of a dashboard usually want diagnosis and prescription. Week-on-week is a signal. Useful means the recommendation first, then the potential drivers — plus targeting, creative, daily budget shuffles, and the business model.
Exact match used to QA a bank chatbot. It cannot QA an LLM.
Why exact-match QA worked on a traditional bank chatbot, and why regulated industries still need a human to review every result when the tester is also an LLM.
I took an LLM course because an NLP master’s and a bank chatbot still weren’t enough.
Why I completed an LLM engineering course after an NLP master’s and enterprise chatbot work — to design AI solutions, strategy, and a roadmap that address a real business need.
A Hobbyist Can Live on Points. A Batch Project Needs a Budget.
Why I use Poe for interactive thinking and OpenRouter when an automated LLM run needs an enforceable spending limit.
In the AI Era, the Data Signal Still Comes First
What conversational AI, advertising optimization and marketing mix modeling taught me about the foundation of AI transformation.
I put the same MMM table into TabFM and Meridian. Only one answered the budget question.
A PoC comparing Google’s Tabular Foundation Model with Google Meridian on the same demo data, and what each approach can actually hand a marketing planner.
AI Adoption Is Still a Translation Problem.
Why stronger models alone cannot create the business value and professional confidence required for adoption.