Load a small corpus, fire a natural-language query, and watch a real multi-hop agentic loop out-hunt a one-shot baseline on a live Cytoscape evidence graph. The comparison runs on actual fuse.js retrieval — not a fake score.
Each hop runs fuse.js over the corpus, scores the top-K, then refines the query by extracting the highest-signal terms from the retrieved snippets. Loops while composite confidence is below 0.55 or until 5 hops are spent.
conf = Σ (avg_hop_score × |unique_docs_hop|) ÷ |unique_docs_total|. Hops that add no new evidence stop contributing weight. Both panes use the same retriever — only the loop policy differs.
The one-shot pane answers part of the question. The agentic pane stitches cause → mitigation → impact into a connected evidence chain. Same retriever, same data, different search policy.