Agentic Systems
Open Source AI in Mid-2026: The Convergence Is Real — And So Are the Divides
By mid-2026 the gap between the best open-weight models and closed frontier systems has narrowed dramatically on benchmarks and many real workloads. But production reality — especially for reliable agentic systems, regulated environments, and long-horizon reasoning — still reveals meaningful differences. Here's where things stand and what it means for teams building actual platforms.
Expert Vision: Cognitive Foundations for Human-AI Collaboration
What fifteen years of studying how experts perceive, decide, and perform under pressure — from eye-tracking systems to competitive gaming to enterprise AI platforms — teaches us about building agents that genuinely extend expertise rather than merely automate tasks.
Reliability Engineering for Generative AI Platforms
Fifteen years of distributed systems, real-time pipelines, and incident command applied to LLM platforms. How to build agentic systems that degrade gracefully, contain failures, and remain auditable when everything is on fire at 2 a.m.
Context Engineering for Production Agentic Systems
Beyond prompt engineering lies context engineering — the systematic design of memory, state, retrieval contracts, and compression layers that turn brittle LLM workflows into reliable, observable, enterprise-grade agentic platforms.