Redis and AI Agent Memory with Andrew Brookins

A key challenge with designing AI agents is that large language models are stateless and have limited context windows. This requires careful engineering to maintain continuity and reliability across sequential LLM interactions. To perform well, agents need fast systems for storing and retrieving short term conversations, summaries, and long term facts. Redis is an open source, in memory data store widely used for high performance caching, analytics, and message brokering. Recent advances have extended Redis' capabilities to vector search and semantic caching, which has made it an increasingly popular part of the Adjantic application stack. Andrew Brookins is a principal applied AI engineer at Redis. He joins the show with Sean Falconer to discuss the challenges of building AI agents, the role of memory in agents, hybrid search versus vector only search, the concept of world models, and more. This episode is hosted by Sean Falconer. Check the show notes for more information on Sean's work and where to find him. Andrew, welcome to the show. Thank you. Thanks for having me. I'm a big fan, so this is fun. Nice. Yeah. Well, I'm glad glad you could be here, glad we could work it out. Always good to have a fan on the show as well. Absolutely. So I wanted to kinda start with the big picture or a big quick picture question. You know, a lot of people are saying that 2025 is gonna be this breakout year for AI agents. It's, you know, the year of the agent. There's a lot of hype going on in the market right now. We're moving beyond just basic chat. So from your perspective, what makes building these more autonomous agentic systems like hard and why does memory or other components kinda play such a central role here? Yeah. Well, I think I've been thinking a lot about this, of course. And, and one of the reasons I think it's so difficult is that, you know, many of the tasks that we can put into a POC to show off what an agent can do, you know, backed by an LM, They satisfy the the weaknesses of the LM. Right? They draw on information and training. They use that generative ability plus, you know, context engineering to produce information effectively. And elements can do that really well, and we've we've done a lot of work now to make agents be able to do that as well. Right? But the tricky part is, I think, when the agent has to integrate in any kind of environment and do something, actually change something and, crucially, be able to predict, like, the outcome of the change. And that's the part that, you know, LLMs just don't don't model, actually. They don't they don't model state transitions like that for environments. That's where they tend to break down, where agents tend to break down. And you think that is it primarily that, you know, companies get stuck in sort of that, you know, demo POC …