Model
Language and multimodal models interpret goals, generate plans and produce candidate actions.
∞Agents + The Future
Code that can
continue.
An agent does more than answer. It holds state, uses tools, takes actions, observes results and decides what to do next.
01 / A new loop
Prompt → act → observe → evaluate → act again.
Tools
Browsers, terminals, APIs, databases, code runners and applications turn text into real-world effects.
Memory
Working context, retrieval and durable state give the system continuity beyond a single exchange.
Evaluation
Tests, policies, critics and humans decide whether an action is acceptable or should be revised.
02 / The thesis
The future of coding may look less like typing a program and more like designing a constitution for systems that act.
Developers still define architecture, invariants, interfaces and failure boundaries. But more implementation can become delegated, tested and revised by machines operating inside those boundaries.
The durable skill is not “prompting.” It is expressing intent precisely, building feedback, designing tools, observing behavior and knowing when a system should stop.
03 / Open questions