Linear Thinking, Nonlinear Costs
The Missing Optimization Layer in Agent Systems
All Articles
Who Owns the Code Claude Wrote?
AI-generated code copyright explained for builders.
This Week in AI: The Next-Gen Recommendation Experience
Plus responsible AI and why a conversational agent doesn’t count as a true sales agent
When Context Collapses: Teaching Agents to Detect and Recover from Lost Memory
Or, how I learned to stop worrying about compaction and love the file system
The PM’s Playbook for Shipping AI Features That Actually Work in Production
The Subsidy Ended: What Tool-Using Agents Actually Cost
Usage-based billing didn’t make agents expensive. It made their existing costs visible, and visibility turns agent economics into a governance problem.
Long-Running Agents
The AI Agents Stack (2026 Edition)
Six layers between your LLM and a production agent
This Week in AI: Production Viability
Metacognition, what OpenAI’s finance move is really about, and why tokenmaxxing is a trap
I Let an AI Agent Run 40 Experiments While I Slept
A linter ruined half of them.
The Tidy House
DJ Patil on why the hardest part of AI adoption is organizational, not technical
Predict, Don’t Enumerate
An AI lab just endorsed a predictive model for defense.
Context as Code
Build-time governance in the era of infinite syntax
Radar Trends to Watch: June 2026
Developments in policy and governance, infrastructure and ops, AI models, and more