When AI Organizations Fail at the Fork, Not the Task
A task can finish correctly after an earlier classification has already sent the program down the wrong path.
Topic
principle
A fundamental, axiomatic, and timeless truth of a system. Principles are the physics of our worldview; they are statements of how things are.
Autonomy Is Prediction Accuracy
Earn agent autonomy through demonstrated prediction accuracy in a bounded decision class. Compare outcomes, correct errors, and keep permission separate.
When Validators Matter More Than Better LLMs
In a multi-step AI pipeline, the dangerous failure is not just a bad model output. It is a bad intermediate result becoming trusted state. Validators matter because they stop bad state at the boundary.
Temperature 0 Does Not Make LLM Output Deterministic
Temperature controls token selection, not the full inference path. Learn where LLM output variation enters and how to test the right reliability contract.
Durable Execution: Why Python while Loops Are Not Production Ready
A while loop is a state machine whose state lives in RAM. One pod eviction and every completed step is gone. Production agentic workflows require exactly-once semantics — a guarantee that must be encoded in the architecture, not hoped for through retry logic.
The API Is the New Command Line: A Manifesto for Agentic Design
The command line gave humans a grammar for commanding machines. The API gives agents the same grammar — at scale, in parallel, without a human in the loop. Every design decision downstream flows from whether you've internalized that shift.
Dumb Core, Smart Edge: Agentic Design
Many agentic systems I've watched fail in production had the same shape: intelligence concentrated at the center, where it was hard to test, replace, or reason about. The orchestrator was doing too much — routing requests, holding domain knowledge, managing memory, selecting tools, and shaping outputs, all at once.
The Golden Dataset: If You Lose Your Code but Keep Your Data, You Survive
Every AI system has exactly one irreplaceable artifact, and it is not the model. Your golden dataset — the curated triples of input, expected output, and ground truth — is the only thing that survives a complete rewrite. Lose it, and you are starting from zero.
The End of Determinism: Why Unit Tests Are Useless for AI Agents
Alan Turing's machine was absolute. An LLM is not. When we moved from logic to statistics, we broke every testing primitive we had — and most engineers haven't noticed yet.
Optimal Estrangement
Every field has an optimal distance from which its deepest patterns become visible. Too close and you optimize locally. Too far and you theorize vacuously. The discipline is finding -- and holding -- the gap.