Lagos · WAT (UTC+1)

Newton Ayomipo Emmanuel

Full-Stack Software Engineer Portfolio & Record Vol. IX

SaaS architecture, UI engineering, AI integration

Google Tag Manager, without the tag manager pain

Built TagRabbit, a drag-and-drop and LLM-driven Google Tag Manager configurator.

The problem

Configuring GTM means wiring variables, triggers and tags by hand — error-prone work that marketers depend on engineers for.

What I did

  1. SvelteKit drag-and-drop editor that maps visual blocks onto a GTM configuration model.
  2. A translation layer that compiles that model into variables, triggers and tags.
  3. Stape.io integration for server-side tracking.
  4. An LLM path (Gemini, OpenAI, OpenRouter) that produces the same model from plain language, orchestrated with Mastra and FastMCP on a Django + RabbitMQ backend.

What changed

  • Shipped as a production SaaS with two input modes — visual and natural language.