Sebastian Cochinescu

Developer of agentmarkup

Builder of developer tools for machine-readable websites. Developer of agentmarkup. Founder of Anima Felix.

About

Sebastian is a product builder and developer with over 25 years in technology. He created agentmarkup to solve a problem he encountered on his own projects: making websites machine-readable for LLMs and AI agents required juggling separate tools for llms.txt, JSON-LD, robots.txt, markdown mirrors, headers, and validation. agentmarkup combines that build-time surface into one toolkit for Vite, Astro, and Next.js.

He is also the founder of Anima Felix, an anxiety support app that uses agentmarkup in production.

Articles

Guides

Is your website ready for AI? Free LLM discoverability checker

Audit your website for llms.txt, JSON-LD, robots.txt, markdown mirrors, and sitemap. Free tool for e-commerce and brand websites.

BeginnerWebsite ownersAI discoverabilityMarch 20, 2026 · 8 min read

How to make your brand appear in AI conversations

Organization schema, llms.txt, and FAQ markup make your brand visible in ChatGPT, Claude, and Perplexity answers.

BeginnerWebsite ownersBusiness visibilityMarch 20, 2026 · 7 min read

Why LLM-optimized e-commerce websites sell more

Product JSON-LD, llms.txt, and AI crawler access make your store visible in AI product recommendations.

BeginnerWebsite ownersBusiness visibilityMarch 20, 2026 · 8 min read

What is GEO? Generative Engine Optimization explained for developers

What is real, what is hype, and what you can do today to make your site citeable by AI.

BeginnerWebsite ownersAI discoverabilityMarch 20, 2026 · 7 min read

Why llms.txt matters: making your website discoverable by AI

LLMs answer questions by synthesizing web content. llms.txt gives them a structured overview of your site.

BeginnerWebsite ownersAI discoverabilityMarch 20, 2026 · 6 min read

Research

We ran 500 of America's biggest companies through an AI-crawler audit

We fetched 500 corporate homepages the way ChatGPT, Claude, and Perplexity do. Most serve readable HTML, but 46% have no usable structured data, 86% have no llms.txt, and seven serve crawlers a blank page. Built for Google, not yet for AI agents.

IntermediateResearchAI accessJuly 2, 2026 · 4 min read

Implementation

I built AgentMarkup Studio with WebMCP

AgentMarkup Studio uses WebMCP so a browser agent can edit a visible draft of a site's machine-readable surface while rules catch cross-surface contradictions.

AdvancedPeople who build websitesImplementationAugust 27, 2026 · 9 min read

agentmarkup is now a plugin for ChatGPT, Codex and Claude Code

The agentmarkup plugin is now published for ChatGPT and Codex, with a guided workflow for installing, building and validating machine-readable website output.

BeginnerPeople who build websitesImplementationAugust 23, 2026 · 8 min read

agentmarkup.dev served a soft-404. Our own tooling missed it.

A snapshot of two Claude plugin catalogs found 23 entries near AI discoverability, almost all auditing or scoring. agentmarkup instead emits the artifacts at build time and can gate CI.

IntermediatePeople who build websitesImplementationAugust 23, 2026 · 5 min read

See your website the way AI crawlers do

Use @agentmarkup/audit to fetch any live URL as GPTBot, ClaudeBot, PerplexityBot, and other AI crawlers, diff each response against a browser, and catch machine-readability issues in CI.

AdvancedPeople who build websitesAI accessJuly 2, 2026 · 6 min read

How to add llms.txt, JSON-LD, and AI crawler controls to Nuxt

Use @agentmarkup/nuxt to generate llms.txt, inject JSON-LD, create markdown mirrors, and manage AI crawler rules from prerendered Nuxt output.

IntermediatePeople who build websitesImplementationJune 21, 2026 · 7 min read

Run agentmarkup on any static site with the CLI

Use @agentmarkup/cli to run llms.txt, JSON-LD, markdown mirrors, and AI crawler controls over any built static output, with a CI check command.

IntermediatePeople who build websitesImplementationJune 21, 2026 · 6 min read

How to add llms.txt, JSON-LD, and AI crawler controls to Next.js

Use @agentmarkup/next to generate llms.txt, inject JSON-LD, manage AI crawler rules, and understand the dynamic SSR boundary in Next.js.

IntermediatePeople who build websitesImplementationMarch 23, 2026 · 8 min read

When markdown mirrors help, and when they do not

A practical guide to when generated markdown mirrors add signal, when HTML is already enough, and how to avoid unnecessary downsides.

IntermediatePeople who build websitesAI discoverabilityMarch 20, 2026 · 7 min read

Build-time markdown mirrors for agent readability: Cloudflare comparison

Build-time markdown generation for AI readability, including when it helps and how it compares to Cloudflare runtime extraction.

AdvancedPeople who build websitesImplementationMarch 20, 2026 · 7 min read

Every AI crawler indexing your website in 2026

Complete list: GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot, and more. What each does and how to control access.

IntermediatePeople who build websitesAI accessMarch 20, 2026 · 8 min read

JSON-LD structured data: the complete guide for web developers

Schema types, JSON-LD vs microdata, common mistakes, and build-time validation.

IntermediatePeople who build websitesStructured informationMarch 20, 2026 · 10 min read