Posts about ai-architecture
-
Local-First Embeddings for Regulated Industries
24MB download, <100ms per batch, nothing leaves the machine. For banks with air-gapped environments, this changes the conversation.
-
Model Routing Is a Design Decision
Your AI budget question isn't which model — it's which phase of the workflow needs depth, and which just needs speed.
-
Progressive Disclosure for AI Agents
Search returns summaries. Get returns detail. The model decides what to expand. 75% context savings.
-
The Four Layers of Every AI Agent
Interaction, inference, orchestration, tooling. The boundaries between them must be enforcement points, not design principles.
-
When the Platform Is Mature, the Architect's Job Changes
The hardest phase of AI architecture isn't building the stack. It's the moment after the stack is built and eighteen teams start making independent decisions on top of it.