Pedro argues that all successful AI products reduce to agentic loops with tools, and that controlling LLMs like 'Foxconn factories' fails; instead, harnesses should give agents autonomy wit…

Drawing an electricity analogy, Pedro argues inference scaling will make token costs the biggest line item, but companies that push usage now gain compounding advantages despite current ROI…

Instead of automating existing KYC, Brex redesigned onboarding end-to-end, enabling KYC at lead qualification which changed targeting and credit decisions—illustrating how AI-native process…

Brex built Crab Trap, an HTTP proxy that analyzes agent traffic and uses an LLM judge to enforce policy, leveraging models' native understanding of web traffic for security without restrict…

Pedro identifies three adoption tiers—token maxers, average engineers, and the rest using chatbots—and argues companies must build OpenClaw-style harnesses to give non-technical teams virtu…

Pedro describes a system where production conversations that flag issues automatically become eval cases, triggering agents to fix code and prompts, creating a self-learning loop that compo…

Pedro uses voice memos to OpenClaw as his primary developer UI, arguing that fighting the instinct to build UI and instead making agents smarter unlocks higher leverage, and that token maxi…

Pedro notes decent Chinese models and hobbyists running local GPU clusters show that token costs can be bypassed via local inference, suggesting API dependency isn't the only path for heavy…