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 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 finds that configuring agents via markdown skills and allowing them to self-modify their environment scales further than hand-coded harnesses, and that organizing context for the mode…

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…