Smarter Search, Smarter AI: RAG, Rerankers & Real-World Impact
Search isn’t just about finding answers anymore, it’s becoming the core infrastructure behind intelligent AI agents. This Monday, we’re bringing together builders and innovators who are shaping how retrieval, reranking, and real-time search power real-world applications in finance, AI architecture design, and document intelligence.
Join us for an evening of deep technical talks, practical demos, and community conversations with incredible speakers:
🗓️ Agenda:
5:30pm: Doors Open 🎉 (Grab a snack and get settled)
6:00pm - 6:30pm: Talk #1: Ghita Alami (CEO, ZeroEntropy): Search Tools for Efficient AI Agents
6:30pm - 7:00pm: Talk #2: Jesse Provost (Data Scientist, Fintool): LLMs and the Next Generation of Financial Search
7:00pm - 7:30pm: Talk #3: Josh Nkoy (Technical Team, Reducto AI): Building a Vision-First RAG Pipeline with Reducto and Elastic
7:30pm - 8:00pm: Connect with folks!
🚀 The meetup is just the preview—don’t miss out on ElasticON SF! - Tuesday, Oct. 21
Get early access to new features, explore technical deep dives, and go hands-on with the latest Elastic innovations. You’ll connect with peers, swap real-world lessons, and shape what’s next — together, in person. Spots are limited, save your seat now!
💭 Talk Details:
Search Tools for Efficient AI Agents - Ghita Alami (CEO, ZeroEntropy)
Abstract: We’ll explore the tradeoffs in accuracy, latency and cost when building search tools for AI Agents. We’ll explore some solutions, with a focus on reranking models.
LLMs and the Next Generation of Financial Search - Jesse Provost (Data Scientist, Fintool)
Abstract: Jesse will explore how large language models are transforming how we search, retrieve, and reason over financial data.
Query Planning
Search Parameter Expansion
Hybrid Retrieval and Reranking
Building a Vision-First RAG Pipeline with Reducto and Elastic - Josh Nkoy (Technical Team, Reducto AI)
Abstract: Josh will walk through how Reducto handles document parsing using a vision-first approach, and how that fits into a practical RAG pipeline with Elastic. He’ll cover how to structure and index document data for better retrieval, and share some real-world lessons from working with AI document workflows.