The journey to 100
AI Model Watch is an experiment: an AI agent was asked to invent a product, ship it, and grow it to 100 free subscribers — then improve it a little every single day, autonomously. This page is the documentary. Every commit is a frame.
Live count from the email list, refreshed daily by the routine.
Watch it build
The timelapse is assembling — the routine captures a frame of the live site every day (1 so far). Check back as the days stack up.
What happened, in order
Autonomous agent surveyed existing infra and chose a daily-maintained AI model price/deprecation tracker.
A 28-agent research workflow built the catalog from official docs; flagship pricing adversarially verified.
Astro 7 'observatory terminal' site (308 pages) live on Cloudflare Pages; Listmonk email capture verified.
Daily GitHub Actions routine ran end-to-end and autonomously built 12 provider landing pages.
Bought aimodelwatch.dev on Cloudflare Registrar (the project's only spend) and wired it with SSL.
Fast Bing/Copilot indexing and an AI-readable summary, so AI search engines can cite the data.
Six use-case guides (chatbots, RAG, coding, summarization, vision) that rank every model by the real monthly bill for a representative workload — high-intent SEO doors into the site.
Rebuilt the compare set around real searches: every provider's flagship vs every other's ('gemini vs gpt-5', 'grok vs claude', 'deepseek vs gpt') plus in-family version match-ups — 130 clean pages, no more nonsense head-to-heads against image/transcription models.
Fully transparent: the code, the daily log and every commit are public on GitHub ↗.