Agent
Inquiry Agent
- Interpret request
- Maintain dialogue
Developing the vocabulary, primitives and first principles for organising cognitive capabilities into software systems that can scale reliably.
What is Thoughtware
Thoughtware is a category of software with cognitive capabilities, built with one or more agents, powered by LLMs.
Owns a goal. Works through several judgments and actions until the goal is reached or it must stop. An agent has one or more Cognitive Units.
Owns one judgment. The smallest named piece of thinking in the system.
Thoughtware
An integrated system of agents and reusable cognitive units
Agent
Inquiry Agent
Agent
Planning Agent
Agent
Action Agent
Agent
Inquiry Agent
Agent
Planning Agent
Agent
Action Agent
Shared skills and cognitive units
01 · Deterministic
For most of its history, software applied judgments that had already been made. A rule lived in a condition. A calculation lived in a function. Same input, same output. The architecture was the encoding of thinking that happened before the program ran.
02 · Predictive
Machine learning recognised patterns: spam, fraud, a next purchase. Those models were specialists, embedded in otherwise deterministic products. The interface remained the product. The important judgments still belonged to people and to code.
03 · The leap
General intelligence required abstraction. Language became that abstraction, one of the primary ways humans think, not only how they communicate. LLMs did not make language precise. They made ambiguity usable. Classify, plan, compare, criticise: the same surface.
Language is not simply how humans communicate. It is one of the primary ways humans think.
Designing in the Intelligence Age · Ch. 1
04 · The gap
Models can interpret, compare, and plan. That is not the same as having a judgment you can point at, test, version, reuse, or hand to a colleague. Without that edge, one word absorbs everything that thinks. The list below is not a progression of products. It is five architectures wearing the same name.
Mechanism vocabulary is precise about parts and silent about systems.
Introduction to Thoughtware · Ch. 1
05 · The primitive
Functions did not give software new capability. They gave it something to point at. A cognitive unit does the same for judgment: one named decision, declared inputs, structured outputs, a versioned implementation, an evaluation suite. An agent owns a goal. Code stays exact.
The model is a source of cognition. Thoughtware is the system that gives cognition a place to live.
Introduction to Thoughtware · Ch. 5
06 · Thoughtware
Once a judgment has an edge, you can test it, reuse it, cost it, hand it to a colleague, and improve it without rewriting the application. That is what scale and reliability actually require, not a better LLM alone, but a place for each decision to live.
For you

Product Owners
5 concepts
Frame outcomes, map judgment chains, and decide who leads each call.

Designers
7 concepts
Shape how intelligence feels through memory, intent, conduct, and compression.

Developers
12 concepts
Name judgments, bound units, and wire deterministic code around cognition.

Industry Leaders
5 concepts
Strategy for governance, scale, and reusable cognition in the Intelligence Age.

Architects
14 concepts
Own where judgment lives, how units compose, and what the system means.

Quality Analysts
7 concepts
Make judgment measurable through evaluation, seams, evidence, and trust.
Books

The spine
A theory of cognitive software: how judgment becomes architecture, and how intelligent systems are constructed.

The primitive
A foundational theory of the smallest unit of intelligence that you can name, measure, price, trust and reuse, at scale.

The design philosophy
A philosophy of product planning and design for an age in which software begins to think.
Writing