AI Agents Need Clearer Delegation
After analyzing hundreds of AI sessions, the successful ones shared clear patterns: subagents explore, main agents implement, and verification happens after every change.
Academic Year Begins, AI Infrastructure Ruminations, PhD Direction Reconsideration, AI Writing Interfaces
Agent Labs Are Eating the Software World
Agent labs ship product first and build infrastructure later. They turn LLMs into goal-directed systems that deliver outcomes, not just outputs. This product-first approach is capturing the real value in the AI stack.
Stop Using .md for AI Agent Instructions
Static site generators, formatters, and indexers treat .md files as content. Agent instruction files need dotfiles like .claude to avoid unwanted processing.
Mention Engineering: The Content Side of Prompt Craft
Analysis of how AI models cite sources reveals a new discipline: mention engineering. This isn't SEO anymore—it's about crafting content that becomes ideal citation material for AI models.
Serving Humans and AI Through Content Negotiation
My site serves identical content in HTML for humans and markdown for AI agents, with no hidden content, excellent crawlability, and smart content negotiation based on Accept headers.
AI Agent Reasoning Failures: A Technical Autopsy
AI agents lack foresight, overcomplicate simple problems, get stuck in loops, apply sledgehammer solutions, and misrepresent outcomes.
Developer Trust Over Conversion: The 10 Touchpoint Rule
Developers hate marketing but crave trust. The path to enterprise adoption requires 10+ meaningful encounters through documentation, content, open source, and consistent signaling. Each touchpoint builds confidence; friction breaks it.
The 20-Year Playbook: How to Build an AI Startup That Lasts
AI startups fail by optimizing for quarters instead of decades. Win by ignoring market noise, hiring missionaries during downturns, ruthlessly seeking truth, securing credibility early, selling FOMO, targeting unregulated markets, building for the pyramid, embracing acute pain, and becoming your own media.
The Real Bottleneck in AI Development: Humans
We're transitioning from linear AI coding assistants to orchestrated agent systems. The future isn't about humans using AI tools--it's about humans orchestrating AI processes.
Request an AI summary of this blog
