Frequently asked questions about thinking, epistemology, and cognitive tools. 6402 answers
Inventory your existing agents both designed and default to understand what is running.
Each agent should handle one specific situation — multi-purpose agents are fragile.
When an agent fails to fire or produces bad results you learn how to improve it.
Every agent embeds assumptions about the world — the schema it uses must be accurate.
Agents for recurring decision types like buy-versus-build or accept-versus-decline.
Agents for spending saving and investment decisions.
Linking an agent to a specific event like arriving at work or opening your laptop.
Too sensitive and the agent fires too often — too insensitive and it never fires.
When a trigger fires in the wrong context you need to add qualifying conditions.
Position trigger cues where you will encounter them at the right moment.
One-way doors deserve careful analysis — two-way doors should be walked through quickly.
Define good defaults so that the do-nothing option is acceptable.
Know which decisions you must make yourself and which can be delegated.
Know which decisions you must make yourself and which can be delegated.
Different frameworks for decisions made alone versus with others.
Define in advance what evidence would cause you to abandon a course of action.
Sometimes deciding fast is more important than deciding optimally.
Your emotions create self-reinforcing cycles — anxiety begets more anxiety.
What you read shapes what you think which shapes what you seek out to read.
Resistance to certain feedback signals it touches an important blind spot.
The ability to build and tune feedback loops is the ability to continuously improve.
You cannot fix what you cannot detect — invest in error detection mechanisms.
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.