AI may generate an insight, but people must still evaluate its significance and plausibility.

determine when to delegate execution to Codex versus when human oversight is most valuable

Security engineers reviewed every finding before it reached a maintainer... While frontier AI models are highly capable of finding vulnerabilities and patching them, they also produce a high volume of false positives

We now spend much more of our time delegating tasks to many Claudes in parallel.

people make about 70% of the planning decisions but only 20% of the execution decisions

people make about 70% of the planning decisions but only 20% of the execution decisions

Even this result was very much a human-AI collaboration. While the AI system found the proof on its own, human mathematicians verified the result. Other humans came up with better-written proofs that extended the AI's initial ideas.

KPMG and UT Austin's research helps clarify what that human should be doing

For the next decade or so, we should think about AI as this amazing tool to help scientists

A DESIGN.md file combines machine-readable design tokens (YAML front matter) with human-readable design rationale (markdown prose). Tokens give agents exact values. Prose tells them _why_ those values exist and how to apply them.

Open Loop + Infinite Demand = Creative Amplifiers.

The organizations that get this right won't be the ones that just automated the most tasks. They'll be the ones that figured out when the human should act, when the agent should act, and how the handoff between them works.

Each run creates a new session alongside your other sessions, where you can see what Claude did, review changes, and create a pull request.

Forward Deployed Engineers tune Relvy for your stack

The boundary between AI judgment and human judgment is explicit and written in code.

McClary took the process from there, contacting the supplier himself to discuss the revised design. Within a month, the new version of the Guardian flashlight was back up for sale on Amazon and on his brand's website.

An agent cannot be held accountable. I think about this principle most. The instinct to put a human in the loop is understandable, but taken literally, it can mean a person approving every step before anything moves forward. The human becomes a bottleneck, rubber-stamping work rather than directing it, and you lose much of what makes agents valuable in the first place.