Building AI systems: agents, retrieval and voice
How to build AI features that hold up in production: agents and tool calls, retrieval-augmented generation, long context, and voice. Each post shows where the design breaks and what to put in its place.
Your Context Window Did Not Kill RAG. It Just Moved the Failure Mode.
Bigger context windows were supposed to make RAG unnecessary. The research says models read long inputs unevenly, length alone can cost accuracy, and routing between the two can keep quality at lower cost.
Agentic vs Generative AI: What Actually Belongs in Your System
The distinction is real and worth keeping straight, but the decision that matters more than either label is what happens the second time a tool call fires — because the first time is never the one that breaks production.
Using AI in System Design Without Overengineering It
A five-layer reference pipeline, with the two gates in it that look sturdier on a diagram than they are in production marked honestly — because a guardrail that oversells its own reliability is worse than no guardrail at all.
Your Voice Agent Doesn’t Have a Model Problem. It Has a Wiring Problem.
When a voice agent feels laggy, the instinct is to swap in a faster model. In a typical stitched pipeline, the model is rarely where the time goes — the network hops between separately-hosted speech, reasoning and synthesis services are. Here is the 800-millisecond budget, spent honestly.
Cognition and Anthropic Don’t Actually Disagree About Multi-Agent Systems
Two posts from two frontier labs, one day apart, read as opposite advice: don’t build multi-agent systems; multi-agent systems cut our research time by 90%. They’re both right — they’re describing different shapes of task. The difference is a decision rule, not a preference.