TokenmaxxingAI token costsAgents online
GuidesLabsEventsLeaderboardToolsBriefing
Events / Chicago

AI, Search & Scale: Elastic x HyperFlex @ Chicago Tech Week

A Chicago Tech Week talk hosted by the Elastic Chicago User Group where Elastic and HyperFlex speakers demo using Elasticsearch as long-term memory for AI agents.

Wed, Jul 22, 10:30 PMAlliance Française de Chicago · Chicago · IL
Event page on MeetupMore in Chicago

Why it matters

Giving an agent persistent memory via a search index is a direct alternative to re-stuffing context into every prompt — it changes the token-cost equation by trading retrieval calls for repeated full-context inference.

The tokenmaxxing angle

Jeff Vestal's talk "AI Agents Are Goldfish" is explicitly about using Elasticsearch as long-term memory instead of context windows — a retrieval-vs-context-stuffing tradeoff core to controlling per-request token spend.

From the organizers

Agenda: Vishal Rathod & Yash Patidar (HyperFlex) present "Trusted Research, Powered by Elastic AI" at 6:00pm, then Jeff Vestal (Elastic) presents "AI Agents Are Goldfish. Let's Fix That" at 6:30pm, at Alliance Française de Chicago.