A reading path
Designing the agent
A suggested route through persistent agents, inherited knowledge, latent intelligence, and self-regulation.
This is a suggested reading order through related essays, rather than a claim that they were published as a numbered series.
Read in this order
4 essaysThe Agent, Not the Task
A case for designing persistent, bounded, adaptive agents rather than organising everything around a task and a score.
The Mapmaker's Alphabet
An agent inherits a conceptual vocabulary from human expression. What can it do with maps it did not make?
Intelligence Beyond the Next Token
The useful structure inside a model can be richer than the output channel through which we ask it to speak.
The Regulator's Mirror
Metacognition as a governing layer: how an agent might monitor and regulate its own operation.