About

The AI landscape moves fast. It’s easy to be overwhelmed by noise, or to miss slow-moving structural shifts because no single article captures them — they only become visible when you read across weeks and topics simultaneously. Zeitgeist is a personal attempt to fix that: a curated intelligence digest that tracks a small set of topics I care about, runs an intermittent gather cycle, and presents what’s new in a form I can review from my phone in five minutes. The review step is the point — reading is passive, but marking observations as keep, dismiss, or action forces a decision and feeds back into the system.

Architecture #

The backbone is a Flask application (epistemic-rag) that runs a pipeline via /journal run. For each tracked topic — AI’s societal impact, IP and training rights, open vs. closed ecosystems, vibe coding approaches, and others — it runs web searches, filters against already-seen URLs, and asks Claude to write a dated journal entry: links with commentary, cross-topic connections, and meta-observations flagging emerging themes, keyword suggestions, and coverage gaps. A parallel set of signal journals runs analytical passes across the topic journals — symptom catalogues, five-what-if chains, causal mapping.

At the end of each run, the meta-observations are aggregated into a review document. A pre-processing script (build_zeitgeist_site.py) injects Hugo front matter into all journal and review files, builds this static site with Hugo, and deploys it to Cloudflare Pages. Cloudflare Access gates the site behind an email OTP. Verdict buttons on review pages POST to a Cloudflare Pages Function that writes to D1; those rows are drained back to the local pipeline at the start of the next gather run.