Durable AI Knowledge
The AI product principles I expect to keep using even as models, tools, and headlines change.
This is the material I want to retain after the weekly news moves on. · Updated September 2026
For the changing landscape, techniques, and vocabulary I am actively tracking, see AI Professional Edge →
The system matters more than the demo
The model is only one part of the product
A stronger model can improve an AI product, but reliability still depends on context, retrieval, tools, permissions, state, application logic, checks, and recovery paths.
Durable question: Where does the model end and the system begin?
Flexible reasoning belongs inside firm boundaries
AI is useful when the right path cannot be fully written as rules. Important limits should still be enforced outside the model when possible.
Budgets, permissions, approval requirements, access scopes, and irreversible actions should not depend on the model remembering them.
Evidence matters more than confidence
Grounding beats polished wording
AI can sound certain while using incomplete, stale, or wrong information. Real work needs clear source quality, provenance, and a way to distinguish authoritative information from everything else.
Durable question: What is authoritative, and how does the AI know?
Preserve uncertainty
Unknown, inferred, proposed, and confirmed information are not interchangeable. Products should keep those distinctions visible when they affect a decision.
Economic authority is still authority
Agents consume resources, not just tokens
Agents may use model calls, retrieval, compute, human review, paid APIs, or machine payments to complete a goal. Once money becomes another tool, spending behavior becomes part of product quality.
A task can succeed and still be badly designed if it costs far more than necessary.
Durable question: What does one successful outcome cost?
Machine payments need the same governance as other consequential tools
Useful controls include total budgets, per-action limits, approved services, human approval thresholds, and transaction logs. The agent can optimize inside those constraints without receiving unlimited financial authority.
Quality needs repeatable evidence
Evals turn failures into learning
One impressive answer proves very little. Representative scenarios, known failures, edge cases, and expected behaviors make AI quality repeatable enough to improve.
Product habit: Save the failure. Find where it started. Change one thing. Run it again.
Human review should be intentional
Human-in-the-loop is not automatically safe or useful. Review belongs where judgment or consequences justify the interruption. Too much review creates fatigue; too little gives the system authority it has not earned.
State and observability keep agents trustworthy
Memory is not automatically a source of truth
Conversation history, retrieved facts, inferred state, and authoritative state are different things. Important facts may need explicit ownership, validation, timestamps, history, or human authorization.
AI can fail without a software error
An agent can choose the wrong tool, misunderstand the goal, retrieve the wrong evidence, or stop too early while every service remains technically healthy.
Durable question: What can we observe directly instead of trusting the model to explain itself?
Questions I keep coming back to
- What job are we actually trying to improve?
- What information is authoritative?
- What should the AI reason about, and what should software enforce?
- What can the AI see, decide, and do?
- What happens when it is uncertain or wrong?
- How will we notice and recover?
- What does one successful outcome cost?
- What evidence would justify giving the system more autonomy?
The point
Models and products will keep changing. The durable skill is learning how to make good decisions about evidence, authority, reliability, cost, and value while they do.