Topic
Redis
3 episodes
-
Context architecture is replacing RAG in AI
Justy and Cody dissect the claim that context architecture is supplanting RAG for enterprise AI agents, weighing Redis Iris as a concrete example and debating its practical relevance for product teams.
-
ScyllaDB cut Sprig's read latency 4X after Redis and ClickHouse hit a wall
Sprig, a fintech platform, hit latency walls with Redis and ClickHouse as their user base grew. By migrating to ScyllaDB—a high-performance NoSQL database built on Cassandra—they cut read latency by 4x and solved throughput bottlenecks. The episode explores why a specialized database sometimes beats general-purpose tools, the trade-offs of that choice, and when you'd actually reach for ScyllaDB in your own stack.
-
RAG precision tuning can quietly cut retrieval accuracy by 40%, putting agentic pipelines at risk
Justy and Cody dig into new Redis research showing that fine-tuning RAG embeddings for sentence-level precision can quietly hurt general retrieval, sometimes by a lot. They unpack why that matters more in agent pipelines, where one bad retrieval can snowball into bad downstream actions, and why common fixes like hybrid search, MaxSim reranking, or bigger models don't really solve the structural problem. The episode lands on a practical takeaway: keep recall fast, add a separate verification step when correctness actually matters.