The second verification focus area is to use a second AI model as a critic to grade the output of the first model; think of it as a second robot librarian from a different library with a different set of books, providing insight into why the first librarian is right or wrong.

Guardrails in Claude.md are guides, not hard rules (e.g., 'Don't make up information' can be ignored by Claude); for critical tasks where errors are costly, you need to implement rule-based guardrails at the tool level, not the prompt level, so Claude literally cannot bypass them.

The robot librarian metaphor: AI systems are like librarians who can only suggest resources and answers based on books in their library; if the library doesn't have a book, the librarian can't help, and critically, the librarian doesn't know when it's missing a book, so it confidently makes something up.

The fourth step in creating proper AI environment is to create rules for what the AI can and can't work on; depending on the cost of getting something wrong, you establish different AI guardrails at different severity levels.

The more precise you are in your spec instructions, the less AI has to assume; every assumption AI makes is a chance for it to drift from the final product you want, so precision directly correlates with output fidelity.

Boris Cherney, creator of Claude code, emphasized that if Claude has a proper feedback loop, it will 2-3x the quality of the final result.

The tactical implementation of agile specking is to bias Claude toward smaller and more compartmentalized specs with tight scope, clear checkpoints, and an explicit review-adjust-repeat cycle.

You should treat your Claude.md environment as your world, and the AI should live in it; it should not feel like the other way around (where you're living in the AI's world).

The first step in creating a proper AI environment is to set up a Claude.md file that gets injected automatically every time you prompt Claude; it's the first thing Claude reads to determine how it should operate, forcing key behaviors like verification into every build rather than making them optional reminders.

By optimizing the verification lever, you play within the actual rules that AI follows, making your AI system function at higher quality levels.

The third step in creating proper AI environment is to build your skill set by creating custom skills for any task you plan to do repeatedly; think of each skill as a handbook to complete a specific task, and the more you use them, the better they become through iterative refinement.

State-of-the-art AI models will tell you to walk to a car wash 50 meters away because the distance is measurable, but they fail to understand the contextual constraint that you need a car to wash your car, revealing that AI is brilliant at what can be measured but lacks signal for context-driven reasoning.

The third verification focus area is to pull external signal where possible by bringing in additional context (data, historical examples, live system connections) that helps verify an output.

Guardrails should be bucketed into three categories: (1) Always Do (tasks AI should run on autopilot), (2) Ask First (tasks you want to double-check), (3) Never Do (critical lines that cannot be crossed).

Waterfall project completion (finishing the entire task at once before showing output) is inferior to agile completion (breaking tasks into small compartmentalized buckets with checkpoints and iterative review); people are extremely susceptible to using AI agents in waterfall manner despite agile being better.

Most people are prompting Claude wrong; specifically, they are not using the spec-verifier-environment framework that Karpathy advocates, which is why their results are suboptimal.

If Claude has a feedback loop (combining all three verification focus areas: precise evaluation criteria, second-model criticism, external signal), it will 2-3x the quality of the final result.

Precise evaluation criteria are similar to Layer 1 (specs) in that the more precise you are upfront, the less room Claude will have to make mistakes.

The way to identify where your skills need improvement is to use them repeatedly: the heuristic is 'the best way to find a leak in a hose is to run water through it'; the more you use skills, the more you'll realize where you need to fix them and where they're strong.

Because AI is a statistical system without motivation (ghost/librarian), not a motivated agent (animal), the only meaningful lever you have to improve performance is the verification lever; yelling at it, pleading, or saying 'make this better' does not work.