automation

A blog pipeline that researches, writes, verifies, and publishes on its own, plus the four gates that make it trustworthy.

TL;DR: The author's blog publishes articles fully automatically via a 2-hour cron pipeline that researches, drafts, verifies, and posts without human touch. Safety comes from strong brakes: verification gates that reject bad content, automatic rollback after publishing, and escalation to humans for taste calls. Full-auto is trusted only for mechanical tasks; editorial judgment stays human.

Free Qwen chat via Playwright is now the primary draft engine for my article cron, with a local router9 fallback wired like a circuit breaker.

TL;DR: The author scrapes Qwen's free web chat via Playwright, copying answers from the clipboard since virtualized DOM rendering hides long replies. Knowing free tiers die without notice, a circuit breaker routes to local router9 after two failures, giving genuinely separate failure domains. The bet isn't that scraping lasts, just that the pipeline keeps running when it doesn't.

Two-layer API key rotation, provider fallback, and DoH for lying ISP DNS: lessons from building a research script that refuses to die quietly.

TL;DR: Firecrawl's keyless search endpoint died with permanent 403s mid-research, so the author pivoted to keyed APIs. The result is web-direct.py, 125 lines doing search, scrape, and extract with two-layer rotation: next key first, then next provider. A DoH health check catches lying ISP DNS, falling back to curl --resolve.

How to build an article research workflow on AI agent skills: three core capabilities, editorial patterns to adopt, and a 2026 security audit.

How to wire the avoid-ai-writing skill into an article pipeline as a detect-only gate, plus a lesson from the Stanford study on AI-detector bias.

My content security gate auto-rolled back the very article announcing it. False positive, cheap fix, and the best proof the fail-closed design works.

We deleted the daily 6+6 article cap and went event-driven: per-entry cursor, cycle budgets, and a local bge-m3 embedding dedup.

Two Hermes containers with network_mode: host fought over port 8642. Fix: a single gateway run container with HERMES_DASHBOARD=1, dashboard in-process.

Cloudflare blocks Python's default urllib User-Agent with a 403, even when the API key is correct. Set a custom UA on every agent request to get through.