Simon Hearne
Simon is a Solutions Architect at Zilliz, working on vector search architecture, migration and performance for production retrieval systems. Previously at Elastic and Akamai, with an MEng in AI and an MSc in Data Science. Simon has a background in web performance and observability which shapes how he thinks about search: balancing accuracy, latency and cost whilst measuring the outcome.
Sessions
The RAG Cost Curve: When an index beats live search
Talk
16. September 2026, 13:30 - 14:15
Main Stage
"Just let the agent search live" has a cost curve, so does a compressed index. The curves cross but most teams pick a side before doing the maths. We'll use open benchmarks on quantisation and refinement to prove what compression really costs you in recall, in answer quality, and in dollars against live search.