Frequently asked questions about thinking, epistemology, and cognitive tools. 3434 answers
Change one thing at a time so you can attribute improvements to specific changes.
A reliable agent works every time, not just when conditions are perfect.
A reliable agent works every time, not just when conditions are perfect.
An agent that tries to do too much does nothing well. Optimize by narrowing scope to what matters.
An agent that tries to do too much does nothing well. Optimize by narrowing scope to what matters.
Optimize how agents connect and hand off to each other, not just how each agent performs in isolation.
Record what you changed, why, and what happened — optimization without documentation is gambling.
Creating an agent is a deliberate design act — not something that just happens.
New agents are most fragile in their first month — they need extra attention and support to survive.
Track versions of your agents so you can compare, rollback, and learn from changes.
Track versions of your agents so you can compare, rollback, and learn from changes.
Periodically review and rebalance your agent portfolio — retire underperformers, invest in high-value agents.
Documentation should evolve with the agent — outdated docs are worse than no docs.
Documentation should evolve with the agent — outdated docs are worse than no docs.
The way you create, maintain, and retire agents mirrors how you learn, practice, and let go of knowledge. Recognizing this parallel turns agent management into a form of self-directed development.
You need capture tools available in every context where you think — desk, commute, shower, conversation, bed. A gap in coverage is a gap in your thinking.
You need capture tools available in every context where you think — desk, commute, shower, conversation, bed. A gap in coverage is a gap in your thinking.
When writing is impossible, speaking into a recorder preserves the thought. Your voice is a capture tool — and in high-friction moments, it is the only one fast enough.
Not all connections are equally strong — quantifying strength improves your model.
Writing does not record thinking. Writing IS thinking. The act of externalization transforms a vague internal sense into something precise enough to inspect, challenge, and build on.
Writing does not record thinking. Writing IS thinking. The act of externalization transforms a vague internal sense into something precise enough to inspect, challenge, and build on.
Writing does not record thinking. Writing IS thinking. The act of externalization transforms a vague internal sense into something precise enough to inspect, challenge, and build on.
Metacognition — the ability to observe your own thinking — is what makes self-correction possible. Without it, you cannot debug your own reasoning.
Metacognition — the ability to observe your own thinking — is what makes self-correction possible. Without it, you cannot debug your own reasoning.