Automate Keyword Clustering at Scale: From a Raw Export to Content Topics with Embeddings + HDBSCAN
A working Python + n8n pipeline that groups thousands of keywords into content topics by intent using embeddings, UMAP and HDBSCAN.
A working Python + n8n pipeline that groups thousands of keywords into content topics by intent using embeddings, UMAP and HDBSCAN.
Build a Python pipeline that turns a target keyword into a data-grounded SEO content brief in under a minute: scrape the SERP, count what ranks, and let an LLM draft the outline from real evidence.
Stop writing a new script for every SEO question. Build a Model Context Protocol (MCP) server that exposes Google Search Console as tools an agent can drive live — with working Python code.
Build a pipeline that finds CTR-decayed pages in Search Console, rewrites their title tags and meta descriptions with an LLM, QA-gates the output, and ships the winners.
Choosing an embedding model for SEO isn’t a leaderboard question. A practitioner’s framework for OpenAI vs Voyage vs Cohere vs BGE, with a reproducible AUC benchmark, the dimension trade-off, and the cost math at scale.
Which scraping backbone should power your SEO data pipeline? A production teardown of Bright Data, Apify, and ScraperAPI across SERP collection, competitor crawling, and structured extraction — with code, failure modes, and a cost-per-record model.
Catch crawled-not-indexed and deindexed pages before they cost you traffic. A read-only Python + n8n pipeline that inspects your whole sitemap on the free Search Console quota and alerts on Slack.
A production programmatic SEO pipeline in n8n + Python: enrichment that creates uniqueness, a quality gate that refuses thin pages, per-page JSON-LD, and an indexing controller that lifted indexation from 30% to 88%.
GSC, SEMrush, and Ahrefs look interchangeable for a custom rank tracker and are anything but. A developer teardown of measured vs modeled positions, the code, the quotas, and the cost.