Using AI tools — OpenAI, Claude, Gemini — inside n8n to automate content creation, keyword clustering, and on-page optimization.
An internal linking agent closes the loop a suggestion engine leaves open: it perceives your link graph, decides which links are justified, and applies them itself — inside guardrails, a review queue, and full rollback. Here’s how to build one responsibly.
llms.txt promised to make sites AI-readable. Eighteen months in, does anything actually fetch it? We check the log evidence, run the cost-benefit math, and build a Python generator that keeps yours current automatically.
A Python pipeline to isolate AI crawler hits in your server logs, verify authenticity against vendor IP ranges (20-35% are impostors), and turn measured behavior into a defensible robots.txt and CDN policy.
A production Python pipeline that pulls images from the WordPress REST API, generates context-aware alt text with a vision LLM, and writes it back — with guardrails so you never overwrite good human-written descriptions.
A repeatable Python pipeline that turns the live SERP into a structured editorial brief — heading consensus, entity checklist, question targets and word-count band — with guardrails against scaled-content abuse.
Position-only tracking is blind to AI Overviews, featured snippets, and PAA. Build a Python pipeline that monitors which SERP features appear for your keywords, who owns them, and what changes over time.
I handed a real technical-SEO backlog to a constrained Claude Code agent wired to the Search Console API. A teardown of what it got right, where it hallucinated, and the guardrails that made it useful.
A content refresh pipeline is the action layer on top of decay detection: score decaying pages by recoverable opportunity, diff them against SERP consensus, and generate specific LLM update briefs.
A code-first Python + n8n pipeline that tracks whether ChatGPT, Perplexity, and Google AI Overviews cite your site, so you can trend AI visibility like keyword rankings.
A production Python + LLM pipeline that generates, validates, and deploys JSON-LD structured data at scale — with a hard validation gate so you never ship markup Google rejects.