Erik

The md4AI plugin provides a powerful, multi-layered approach to Generative Engine Optimization (GEO).
<h3>1. Automatic AI Bot Detection (Zero-Config)</h3>
md4AI automatically detects requests from a comprehensive list of known AI agents (like GPTBot, ClaudeBot, Google-Extended, etc.) and serves them a lightweight, on-the-fly Markdown version of your content instead of the standard HTML theme. This ensures a clean, parsable data feed for LLMs right out of the box.
<h3>2. Per-Post Custom Markdown (Metabox)</h3>
The plugin adds a new metabox to your post and page editor, giving you full control over the AI-optimized version of your content. 
Serving an md version of the website is particular useful if your website has editors like Elementor / Beaver Builder / Divi Builder / other div bloated editors because bots usually skips complex and too much nested content.
<ul>
<li>Generate Custom Markdown: Convert your post’s content into Markdown with one click.</li>
<li>Manually Edit: Modify and enhance the Markdown to be exactly as you want AIs to see it.</li>
<li>(Optional) Enhance with AI: If you also use the <a href="https://wordpress.org/plugins/ai-services/" rel="ugc">AI Services</a> plugin, you can use the “Generate with AI” button to automatically add FAQs, discussion questions, or key takeaways extracted from your post.</li>
<li>Serve Enhanced Content: When an AI bot visits this specific post, it will be served your new, custom-tailored Markdown version, giving it far richer data.</li>
<li>Automatic Fallback: If you don’t create a custom version, the plugin falls back to the automatic on-the-fly conversion.</li>
</ul>
<h3>3. Site-Wide AI Instructions (llms.txt)</h3>
The plugin adds a new main page under ‘Utilities’ with dedicated tabs for configuration and insights. From here, you can create and manage a <code>llms.txt</code> file for your entire site.
<ul>
<li>What is <code>llms.txt</code>? This is a file, similar to <code>robots.txt</code>, that provides general instructions, context, and useful links to AI crawlers. It’s a new standard to help guide LLMs in understanding your site’s content and purpose.</li>
<li>Manage Content: Use the settings page to write your <code>llms.txt</code> content, which will then be served automatically to bots that look for it.</li>
<li>Learn More: You can find more details on this new standard at <a href="https://llmstxt.org/" rel="nofollow ugc">https://llmstxt.org/</a>.</li>
</ul>
This combination gives you full control, from automatic optimization to granular, AI-enhanced, per-post content and site-wide AI directives.
<h3>4. GEO/AIO Insights & Validation</h3>
The dedicated GEO/AIO Insights tab provides a unique validation mechanism for your site’s AI presence, offering measurable scores (0-100) on how well your brand is understood by Generative Engines.
<ul>
<li>The Validation Process: We ask a Large Language Model (LLM) to complete a “knowledge card” about your site (e.g., brand name, main topics, product categories).</li>
<li>Ground Truth Check: The AI response is immediately compared with real data extracted from your WordPress database (e.g., site title, author names, WooCommerce categories)</li>
<li>Final Score: Based on this cross-check, the insight provides a score for brand identity and technical relevance, highlighting exactly where the AI provided incorrect or insufficient data (hallucinations or missing data).</li>
</ul>

md4AI

Optimise content for generative engines (GEO) by serving custom Markdown and a site-wide llms.txt.

agenciaconversion

Conversion Agent Discovery helps WordPress sites expose public, read-only discovery surfaces for AI agents without pretending to support capabilities that are not implemented.
It is designed to improve measurable agent accessibility for public, read-only discovery checks without calling external scanners automatically.
Features include:
<ul>
<li>Markdown negotiation for public content with <code>Accept: text/markdown</code>.</li>
<li>Content Signals in <code>robots.txt</code>.</li>
<li>Generated <code>llms.txt</code> and <code>/.well-known/llms.txt</code>.</li>
<li>Editable AI Instructions page for official brand facts and LLM guidance, starting empty with English templates by default.</li>
<li>Runtime Front-end Placement for exact, design-safe AI Instructions link placement across matching public header, footer, or page content components.</li>
<li><code>[conversion_ai_instructions_link]</code> shortcode for manual placement.</li>
<li>Generated <code>/.well-known/api-catalog</code>.</li>
<li>Generated <code>/.well-known/agent-skills/index.json</code> and virtual <code>SKILL.md</code> files.</li>
<li>Local Agent Skills discovery schema generated by the site.</li>
<li>Read-only WebMCP tool registration with runtime diagnostics for compatible browsers.</li>
<li>Production-oriented Agentic Browsing readiness guidance for PageSpeed and Lighthouse checks.</li>
<li>Optional origin isolation headers and optional Origin-Trial header for browser WebMCP runtime support.</li>
<li>Opt-in declarative WebMCP form annotations for exact rendered form opening tags.</li>
<li>Public read-only REST endpoints for site search, recent content, single content reads, site context, and contact handoff.</li>
<li>Agentic Browsing diagnostics that separate plugin-controlled discovery surfaces from theme accessibility and layout stability checks.</li>
<li>Admin settings page with a global public switch.</li>
</ul>
Conversion Agent Discovery does not publish fake OAuth, MCP Server Card, A2A, or commerce metadata.
The AI Instructions feature was inspired by Chris Long’s public LinkedIn post and Nectiv case study showing that AI Instructions pages can be cited by ChatGPT in branded queries. It also credits the earlier Seer Interactive AI Information page by Wil Reynolds and Alisa Scharf that Chris Long identified as an important example.
References:
<ul>
<li>Chris Long’s LinkedIn post: https://www.linkedin.com/posts/chris-long-marketing_holy-moly-seos-ai-instruction-pages-influence-share-7466096236799053824-_rpb/</li>
<li>Nectiv case study: https://nectivdigital.com/blog/aeo-experiment-chatgpt-cited-an-ai-instructions-page-in-48-hours</li>
<li>Nectiv AI Instructions example: https://nectivdigital.com/ai-instructions</li>
<li>Seer Interactive AI Information example: https://www.seerinteractive.com/ai-information</li>
<li>Omniscient Digital AI Info example: https://beomniscient.com/ai-info/</li>
<li>llms.txt proposal by Jeremy Howard: https://llmstxt.org/</li>
</ul>
Important: this plugin does not guarantee LLM citations, search rankings, AI Overview visibility, or model behavior. It provides controlled public discovery surfaces for experimentation.
<h3>External Services</h3>
This plugin does not send requests to external services automatically and does not transmit visitor or site data to third parties.
The generated Agent Skills discovery document uses a local schema URL served by the WordPress site at <code>/.well-known/agent-skills/discovery-0.2.schema.json</code>; it does not depend on an external schema service.
The plugin contains optional external links that administrators or users may open manually:
<ul>
<li><code>https://conversion.ag/</code> is linked for Conversion attribution and plugin author information. The plugin does not send visitor or site data to Conversion; the link is opened only when a user clicks it manually. Conversion’s privacy policy is available at https://www.conversion.com.br/politica-de-privacidade/.</li>
<li><code>https://github.com/agencia-conversion/conversion-agent-discovery</code> is linked as the public development repository and release source. The plugin does not send visitor or site data to GitHub; the link is opened only when a user clicks it manually. GitHub’s terms are available at https://docs.github.com/en/site-policy/github-terms/github-terms-of-service and GitHub’s privacy statement is available at https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement.</li>
<li><code>https://wordpress.org/plugins/wp-graphql/</code> is linked from the admin screen when WPGraphQL is not detected, so administrators can optionally install it. The plugin does not send visitor or site data to WordPress.org; the link is opened only when an administrator clicks it manually. WordPress.org’s privacy policy is available at https://wordpress.org/about/privacy/ and terms are available at https://wordpress.org/about/terms-of-service/.</li>
<li><code>https://pagespeed.web.dev/</code> is linked from the Agentic Browsing admin screen so administrators can manually test their public site in PageSpeed Insights. The plugin does not send visitor or site data to Google automatically; the link is opened only when an administrator clicks it manually. Google’s privacy policy is available at https://policies.google.com/privacy and terms are available at https://policies.google.com/terms.</li>
</ul>
The developer-only <code>tools/run-agentic-lighthouse.sh</code> script is not run by WordPress and is never executed automatically. If a developer runs it manually, it uses <code>npx</code> to download and run Lighthouse from the npm registry and audits only the URL supplied by the developer.
The optional WebMCP Origin Trial token field is empty by default. If an administrator adds a public Chrome origin trial token, the plugin sends it as an <code>Origin-Trial</code> response header on public pages together with the opt-in WebMCP origin isolation headers. The plugin does not request or generate tokens and does not make a server-side request to Google or Chrome services.
Conversion’s privacy policy is available at https://www.conversion.com.br/politica-de-privacidade/.
<h3>Privacy</h3>
Conversion Agent Discovery does not track users and does not send site data to external services automatically. Outbound links in the admin screen and readme are plain manual links.
<h3>Development</h3>
Development happens at https://github.com/agencia-conversion/conversion-agent-discovery. The distributed plugin contains readable PHP, JavaScript, CSS, and SVG source files; no build step is required to run the plugin.
Local Agentic Browsing validation can be run by developers with:
<ul>
<li><code>tools/setup-agentic-fixture.sh</code></li>
<li><code>tools/run-agentic-lighthouse.sh http://localhost:8089/</code></li>
<li><code>node tools/assert-agentic-lighthouse.mjs .context/lighthouse-agentic.json</code></li>
<li><code>CAD_REQUIRE_WEBMCP=1 node tools/assert-agentic-lighthouse.mjs .context/lighthouse-agentic.json</code> when running a Chrome runtime that exposes real WebMCP APIs.</li>
</ul>
Public 0.4.0 launch materials are available in the repository:
<ul>
<li><code>docs/launch-0.4.0.md</code></li>
<li><code>docs/local-agentic-browsing-activation.md</code></li>
<li><code>docs/demo-checklist-0.4.0.md</code></li>
<li><code>docs/changelog-0.4.0.md</code></li>
</ul>

Conversion Agent Discovery

Read-only agent discovery for WordPress: llms.txt, Markdown, API Catalog, Agent Skills, WebMCP, and content signals.

md4AI vs Conversion Agent Discovery