Reading Notes
Links, short summaries, and notes on what is worth noticing across AI, operations, strategy, and company-building.
A concrete workflow for using coding agents while keeping humans responsible for quality. Kenn separates design, specification, implementation, verification, and merge ownership instead of treating agent output as production-ready.
Why AI application startups have to build their own model fine-tuning factories to survive in the enterprise. Decagon AI shows that selling agents to large enterprises requires custom workflows that frontier models can't handle alone.
A breakdown of the six components you need to build a reliable agent harness. The harness is the software layer between the model and the actual work.
How Wall Street is turning AI data centers into securitized assets like power plants. Nvidia signed MOUs with Apollo, BlackRock, and Blackstone to raise $500 billion for AI data centers.
See how managing your team's shared context gets better results out of AI. An AI model's output depends entirely on what you feed it.
A practical guide to structuring prompts so coding agents actually follow them. Stop dumping all your instructions into one file.
Shows how Coinbase redesigned its workflows around AI agents instead of bolting them onto human processes. Coinbase engineers paused coding for two weeks to redesign their development cycles around agents.
A look at SpaceXAI's new model and Grok Bot, which pushes AI from chatbot to autonomous coworker. SpaceXAI released Grok 4.