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.
Keyword research is where most SEO programs quietly leak time. A mid-sized site exports 4,000 queries from Search Console, and someone spends two days dragging rows around a spreadsheet, guessing which queries belong on the same page. The output is subjective, unrepeatable, and stale the moment traffic shifts. The fix isn’t a better spreadsheet —…
Find low-CTR pages, rewrite their titles and meta descriptions with an LLM under strict guardrails, ship the changes, and measure the CTR lift — a full Python pipeline.
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.
Detect keyword cannibalization programmatically from GSC API data, score each conflict by recoverable traffic, and decide what to consolidate or differentiate.
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.
Build a scheduled Python pipeline that monitors Core Web Vitals with the CrUX and PageSpeed Insights APIs and alerts you in Slack the moment LCP, INP, or CLS go red.
A code-level teardown of the GSC, SEMrush, and Ahrefs APIs for automated rank tracking: quota math, data shape, cost at scale, and the hybrid build that wins.
Stop eyeballing the Search Console queries report. Build a Python pipeline that scores every GSC query by recoverable clicks and hands you a ranked SEO action queue.
DuckDB, BigQuery, and pandas benchmarked on the same 25M-row GSC export. Which engine wins for which SEO workload, with working code and a decision framework.