AI Tinkerers x Redis: Built for Speed
Details
Most AI agents do not fail because the model is weak. They fail because the context is stale, scattered, slow to retrieve, or forgotten the moment a session ends.
Join us for a hands-on Redis Demo Night exploring Redis Iris — Redis’s real-time context engine for building agents that can act on fresh business data, retain useful memory, and respond within a real production latency budget.
We’ll go beyond slides and show what it takes to make an agent genuinely context-aware:
- Fresh, navigable data: turn operational information—customers, orders, tickets, policies—into structured context that agents can discover and use.
- Memory that compounds: carry important facts, preferences, and decisions across conversations, sessions, and agents.
- Fast, cost-aware retrieval: use Redis Search and semantic caching to surface the right context quickly and avoid repeating equivalent LLM work.
Expect live demos, technical walkthroughs, and an honest discussion of the hard part of agentic AI: not picking a model, but giving it the right information at the right moment.
Whether you are building an AI assistant, a support copilot, a workflow agent, or a production RAG system, come see how Redis Iris helps move agents from impressive demos to dependable systems.
Some important notes:
- Please make sure you RSVP at the official Luma page of AI Tinkerers SG. Meetup.com RSVP is not sufficient.
Who should come: AI engineers, platform teams, founders, data builders, and anyone wrestling with agent memory, retrieval, or real-time context.
Food will be provided.