Frequently asked questions about thinking, epistemology, and cognitive tools. 1287 answers
Optimizing before you understand the system is the root of much wasted effort.
Design systems that surface errors early when they are easiest and cheapest to correct.
Small uncorrected errors can trigger chains of increasingly large errors.
Optimization is not something you do once — it is an ongoing relationship with your systems.
Accept that some error rate is normal and define how much error is tolerable.
Accept that some error rate is normal and define how much error is tolerable.
Your set of agents is an ecosystem — it needs balance and periodic assessment.
Physical cues in your environment trigger more reliably than mental intentions.
When an agent fails to fire or produces bad results you learn how to improve it.
Agents for how to structure emails presentations and difficult conversations.
A complete set of well-tuned triggers means you respond appropriately to everything that matters.
Record decisions, their reasoning, and their outcomes to improve future decision-making.
Know which decisions you must make yourself and which can be delegated.
Choose the option you would least regret in five years.
Accept that some error rate is normal and define how much error is tolerable.
Asking why five times in succession usually reaches the root cause of a problem.
For every important process have a documented way to recover from common failures.
When your agents work together smoothly the result looks like natural ability to others.
Delegation without verification is abdication. Build lightweight checks to ensure delegated work meets your standards.
A well-written document delegates explanation, alignment, and decision context to the future.
Delegation ranges from "do exactly this" to "handle it entirely" — know which level you are using.
Delegation ranges from "do exactly this" to "handle it entirely" — know which level you are using.
Written reflection is the oldest and most versatile form of self-monitoring.
Compare agents against each other and against baselines to identify relative performance.