Upcoming talk
Building Machine Learning Workflows with Your Crawl Data
- Event
- Lumar
- Date
- Location
- Online
Why prompting alone is a dead end for repeatable SEO work, and the three-layer framework (embeddings, clustering, LLMs) that replaces it.
Resources mentioned in the webinar are linked below.
Both workflows/notebooks require a CSV crawl of your site. Start with the Rising Tide tier in either one: it runs entirely inside your own Colab session, costs nothing, and gets you a result you can look at before deciding whether the paid tiers are worth it.
The Open Water and Deep Sea tiers send your content to an LLM. Worth checking client agreements and your security team’s position on that before you run them at work. The walkthroughs included in the repo also detail cost expectations.
From this talk
colab
Competitor Content Gap Analysis
Compare your site against a competitor's using embeddings and topic clustering instead of keyword lists. Free local version, or a few dollars for the LLM write-up.
colab
Internal Link Opportunities
Find internal linking opportunities with embeddings and similarity scoring instead of page-by-page review, with an LLM writing the anchor text at higher tiers.