Sign in Subscribe

Topic

ai-architecture

A collection of 39 issues

Every AI Agent is a Liar, a Slacker, and a Thief

The industry is currently stuck in the Prototype Trap. We can build a magical AI demo in a weekend, but we spend six months failing to make it reliable in production. Why? Because we assume the model wants to help us. It doesn't. By default, every AI agent is a liar, a slacker, and a thief.

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.

Intelligence Arbitrage: The Economics of Routing Thought

The default LLM architecture is economically incoherent: one expensive model for every task. Intelligence Arbitrage treats model selection as a routing problem and turns the spread between task difficulty and model capability into operating leverage.

The Iron Triangle of Inference: You Can't Have Smart, Fast, and Cheap

In distributed systems, the CAP Theorem dictates you can only have two of Consistency, Availability, or Partition Tolerance. In AI, we face a new, equally brutal constraint: The Iron Triangle of Inference. You must choose between Quality, Latency, and Cost. You cannot have them all.

The Agentic Contract: Why a Prompt Is Not a Specification

A raw prompt can express intent, but it cannot define a real behavior contract. The Agentic Contract turns one agent capability into a typed, executable specification with explicit inputs, outputs, failure modes, and economic bounds.

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.

Software Is Digesting the World

Digitization captured the world. The next competitive layer is digestion: the stack that turns stored data into interpreted, executable, feedback-corrected decisions.

The Backlog Is a Liability. Your Real Asset Is a Map of Ignorance.

A backlog is useful for known work. Frontier work needs a different artifact: a Map of Ignorance that tracks unresolved questions, assumptions, and experiments instead of fossilized solution guesses.

Why AI Agents Should Be State Machines

A monolithic agent prompt hides routing, extraction, tool selection, formatting, and recovery inside one probabilistic call. The antidote is the formal state machine: explicit states, typed transitions, validators, and recovery paths.