About

AI isn’t slowing down, and the Nordics are accelerating.

Discover how to evolve your AI stack from simple caching to a real-time context engine. We’ll explore how Redis enables semantic caching and agent memory - and how these patterns apply to teams building AI systems across the Nordics.

Semantic Caching for AI Apps

LLMs are powerful, but slow and expensive. Traditional caching doesn’t help when users ask the same question in different ways. Semantic caching changes that by matching on meaning rather than exact text, reusing previous responses.

We’ll cover:

• How Redis powers semantic caching in production
• Up to 15× faster responses and 30%+ lower costs
• Live demo

Agent Memory Server for AI Apps

AI agents quickly show limitations: they forget context and repeat themselves. Adding more context isn’t the solution - it’s slow and expensive. Agents need real memory across conversations and sessions.

We’ll cover:

• Why stateless LLM calls fall short
• Durable, low-latency memory with Redis
• Live demo