EMEA: AI office hours

You may already have more of the foundation for AI in your stack than you realize. But if your agents are starting every conversation from scratch, your LLM costs are growing faster than your usage, or your RAG pipeline works in staging but not in production — the next step is understanding how to close those gaps. Join us for a live, candid session built for European engineering leaders who are building AI apps and agents today.

Join us for an exclusive customer AI office hours session with Vishal Bala, Sr. Principal Applied AI Engineer, and Kamran Yousaf, Principal Solutions Engineer at Redis. They will answer all your questions relating to AI, context, memory, and more. Whether you're building fraud detection, recommendation engines, or context-aware apps, this session is for you

Nothing is off the table. Bring any questions you might have, we’ll try to answer them all live.

• Agent memory and context: Giving agents persistent memory without bloating your prompt window or your stack.
• Keeping LLM costs in check: When semantic caching is worth it and how to size the impact.
• Simplifying the AI stack: How teams are consolidating vector search, caching, and session state into one platform.
• Real patterns from the field: What's actually working in production: fraud detection, recommendations, and context-aware apps across EMEA.
• Where the industry is heading: What's overhyped, what's real, and how to make bets you won't regret.