{"id":3228,"date":"2026-06-28T08:57:49","date_gmt":"2026-06-28T08:57:49","guid":{"rendered":"https:\/\/tucumandevelopers.com\/index.php\/2026\/06\/28\/how-to-write-design-md-prose-that-ai-agents-actually-follow\/"},"modified":"2026-06-28T08:57:49","modified_gmt":"2026-06-28T08:57:49","slug":"how-to-write-design-md-prose-that-ai-agents-actually-follow","status":"publish","type":"post","link":"https:\/\/tucumandevelopers.com\/index.php\/2026\/06\/28\/how-to-write-design-md-prose-that-ai-agents-actually-follow\/","title":{"rendered":"How to Write DESIGN.md Prose That AI Agents Actually Follow"},"content":{"rendered":"
\n
<\/header>\n
\n

To write DESIGN.md prose agents follow, describe intent and rules, not just values.<\/strong> A token says a color is a hex; good prose says it is for the primary action only. Reasoning is what lets an agent generalise to cases you did not explicitly cover.<\/p>\n

<\/a> Weak vs strong prose <\/h2>\n
\n
## Colors # WEAK - restates the tokens: Primary is #1A1C1E. Secondary is #6C7278. # STRONG - explains intent: High-contrast neutrals with one warm accent. Use the accent only for the single most important action. Never decoratively. <\/code><\/pre>\n
\n<\/p><\/div>\n<\/p><\/div>\n
The strong version gives the agent a rule it can apply to situations you never listed.<\/p>\n
  <\/a> Why prose works on agents <\/h2>\n
LLMs read markdown with very high fidelity – most of their training is structured this way. That makes prose an ideal channel for design intent. The value tells the model what a color is; only prose tells it the rules.<\/p>\n
  <\/a> Cover the canonical sections <\/h2>\n
Each section answers a question the agent would otherwise guess at: <\/p>\n
\n
## Overview -> the personality ## Colors -> roles and rules ## Typography -> the job of each style ## Layout -> grid and spacing ## Do's and Don'ts -> hard guardrails <\/code><\/pre>\n
\n<\/p><\/div>\n<\/p><\/div>\n
  <\/a> Do’s and Don’ts is where the value is <\/h2>\n
\n
## Do's and Don'ts<\/span> -<\/span> Do use the accent for one primary action per screen -<\/span> Don't mix rounded and sharp corners in the same view -<\/span> Do maintain WCAG AA contrast (4.5:1 for normal text) -<\/span> Don't use more than two font weights on a screen <\/code><\/pre>\n
\n<\/p><\/div>\n<\/p><\/div>\n
Each line removes a whole category of off-brand output.<\/p>\n
  <\/a> How much is enough? <\/h2>\n
A good test: would the prose let a designer who had never seen your product apply your system correctly? Write what prevents a mistake, and stop there.<\/p>\n
  <\/a> FAQ <\/h2>\n
Descriptive color names?<\/strong> Yes – tie them to the token name so the agent can map rationale onto values.
 Most important section?<\/strong> Do’s and Don’ts – it directly prevents agent mistakes.<\/p>\n
  <\/a> Bottom line <\/h2>\n
Tokens are easy; the rationale is the work. Spend your time on the prose that turns values into your identity.<\/p>\n
\n
Free starter:<\/strong> The format, a complete annotated example, and the core idea are on a free cheat sheet: DESIGN.md Quick-Start Cheat Sheet<\/a><\/p>\n
Go deeper:<\/strong> The full guide covers the entire format \u2014 the token schema, the CLI in depth, accessibility, Tailwind and DTCG export, agent integration, and a complete walkthrough: DESIGN.md: The Complete Guide to Design Systems for AI Agents<\/a><\/p>\n
What is the one design rule you wish your agent would stop breaking? Drop it below – it probably belongs in your Do’s and Don’ts.<\/p>\n<\/p><\/div>\n<\/article>\n
  <\/div>\n
 <\/main> <\/div>\n<\/div>\n<\/div>\n<\/div>\n
Fuente: Art\u00edculo original<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"
To write DESIGN.md prose agents follow, describe intent and rules, not just values. A token says a color is a hex; good prose says it is for the primary action only. Reasoning is what lets an agent generalise to cases you did not explicitly cover. Weak vs strong prose ## Colors # WEAK – restates […]<\/p>\n","protected":false},"author":1,"featured_media":2648,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[41],"tags":[],"class_list":["post-3228","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-devto"],"jetpack_publicize_connections":[],"_links":{"self":[{"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/posts\/3228","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/comments?post=3228"}],"version-history":[{"count":0,"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/posts\/3228\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/media\/2648"}],"wp:attachment":[{"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/media?parent=3228"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/categories?post=3228"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/tucumandevelopers.com\/index.php\/wp-json\/wp\/v2\/tags?post=3228"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}