Semantic Clustering

Method

1. Take seed keyword (e.g. "claude code")
2. Fetch SERP for seed via WebFetch/fuse-browser (top 10 results)
3. For each related keyword (autocomplete + "People Also Ask"):
   • Fetch its SERP
   • Compute overlap with seed's SERP (Jaccard index)
4. Group keywords where SERP overlap ≥ 30% → same cluster
5. Cluster center = highest-volume keyword

Output

# Cluster: "claude code"