tokens agents
Reference Glossary Timeline

The same terms, in order

Forty terms with a placed date, read as a chronology instead of an index. From the variable in 1591 to the thesis itself.

1591

Variable (the abstraction)

Francois Viete

Representing a known or unknown quantity with a letter so you can compute with it as if it were the value.

1984

Literate programming

Donald Knuth, Stanford

Writing a program as one document that interleaves the explanation, ordered for a human, with the code the compiler extracts.

1994

Separation of structure and style

Hakon Wium Lie (CSS), proven by Dave Shea (CSS Zen Garden)

Keeping content separate from how it looks, so one structure can wear many styles and a value can change in one place.

c. 2001

JSON

Douglas Crockford

A lightweight, language-neutral data format of key-value pairs and arrays.

Model-driven architecture (MDA)

Object Management Group

An older approach making formal models the primary artifact and generating code from them.

2004
2009

EARS notation

Alistair Mavin and team, Rolls-Royce

The Easy Approach to Requirements Syntax: five sentence patterns that make requirements testable and unambiguous.

c. 2010

JSON Schema

Community, early drafts by Kris Zyp

A vocabulary for declaring the shape of JSON so it can be validated.

2013

Atomic design

Brad Frost

A mental model that builds interfaces from small composable parts, atoms to molecules to organisms, up to pages.

c. 2014
c. 2015

CSS custom properties

W3C

Native variables in the browser (--name: value) that made tokens practical on the web.

2016

Token tiers

Nathan Curtis, EightShapes

The layered naming model where raw values (primitives) are aliased to purpose (semantic) and then to component-level tokens.

2017

Transformer architecture

Vaswani et al., Google

The neural network architecture, built on self-attention, under every large language model in the stack.

2019

Design Tokens Community Group (DTCG)

Kaelig Deloumeau-Prigent, W3C

The vendor-neutral W3C body that standardizes the token format.

2020

Prompt engineering

No clean single coiner, emerged with GPT-3

Crafting the input to steer a model's output.

Retrieval-augmented generation (RAG)

Patrick Lewis et al., Meta (FAIR)

Grounding a model's output in documents retrieved at query time instead of relying only on what it memorized.

2023

Figma Variables

Figma

Token-like variables native to Figma, with aliasing and modes.

Function calling, tool use

OpenAI

Letting a model return a structured call to a defined function or tool.

2024

Tessl

Guy Podjarny

Spec-centric, AI-native development tooling oriented toward spec-as-source.

llms.txt

Jeremy Howard, Answer.AI

A Markdown file at a site root giving agents a curated map of what to read; llms-full.txt inlines the content.

2025

DESIGN.md

Emerging convention

A file pairing machine-readable tokens with the prose that explains the visual identity.

Spec-driven development (SDD)

Modern framing via GitHub Spec Kit

Making a written, version-controlled spec the source of truth and treating generated code as a regenerable artifact.

Spec-first, spec-anchored, spec-as-source

Birgitta Böckeler, Thoughtworks

Three maturity levels: write-then-discard the spec, keep it governing, or only ever edit the spec.

The structure-not-size finding

Diana Wolosin and Tony Rucker, Indeed

Structured JSON beat prose-heavy docs for feeding components to an agent.

Context engineering

Tobi Lutke, amplified by Karpathy

Deciding what goes into the model's working memory at each step and what stays out.

AGENTS.md

OpenAI

A simple Markdown file giving coding agents consistent project-specific guidance.

2026

The four layers

Ryan Payne

The chain that hands context down: values (tokens), meaning (machine-readable logic), intent (spec-driven development), delivery (runtime context).

Tokens to agents

Ryan Payne

The argument that a design system is no longer documentation a human reads but infrastructure an agent executes against.

Return to The map