Part of Content Studio
ARD Generator
A reference document so AI agents understand your business
What are LLMs and why do they matter for your business?
LLM stands for Large Language Model. These are the artificial intelligence systems behind tools like ChatGPT, Google Gemini, Claude, and Perplexity. They work by processing enormous amounts of text to learn human language patterns, which enables them to answer questions, generate content, and hold natural conversations.
When a user asks ChatGPT "what's the best project management tool?" or asks Perplexity "which laptop should I buy for graphic design?", the LLM analyzes everything it learned from the web and selects the sources it considers most trustworthy to build its response. If your brand, product, or website doesn't have the right signals, the model simply won't include you in that answer, and your competition will take that spot.
Google AI Overviews is Google's version of this technology: instead of showing just a list of links, it now generates a direct AI-powered answer at the top of search results. This means the first result many users see is no longer a link to your site, but an AI-generated response that may or may not mention you.
In short: LLMs are the new intermediaries between your business and your potential customers. More and more people use these tools to research, compare, and decide what to buy. AuraMetrics helps you ensure that when AI answers questions about your industry, your brand is part of the answer.
What it does
ARD Generator creates a ready-to-publish ai-catalog.json (Agentic Resource Discovery) from your real site. ARD is the agentic counterpart to llms.txt: a manifest at /.well-known/ai-catalog.json that lets AI agents discover your MCP and A2A servers. It detects the agent servers you already expose, validates any catalog you have published, and builds the ARD 1.0 structure with the correct did:web identity. It is fully deterministic: no AI model calls, and it never invents servers or capabilities that do not exist.
Why it matters
As AI agents start to act on your behalf (not just read), they need to discover which servers and tools your domain exposes. ARD is that entry point, just as llms.txt is for content. The spec is new (announced June 2026) with near-zero adoption, so publishing your catalog today positions you as an early adopter. It does not replace UCP or llms.txt: it complements them.
How it works
You enter your site URL and the module detects agent servers deterministically: it probes /.well-known/mcp.json, /.well-known/agent.json, and MCP endpoint references in your llms.txt, all with SSRF protection. It generates the ai-catalog.json with host did:web:yourdomain, correct urn:air identifiers, and one entry per detected server. When none is detected, it leaves a clearly-marked template entry with recommendations on what to fill in. It also validates any catalog you already publish. The result is ready to copy or download.
Metrics you get
Recommended use cases
Frequently asked questions
What is ARD?
Agentic Resource Discovery: a standard for AI agents to discover the MCP/A2A servers and tools a domain exposes, via a manifest at /.well-known/ai-catalog.json. It is the agentic counterpart to llms.txt.
Is ARD only for ecommerce?
No. Any site that exposes agent-consumable resources (SaaS, docs, APIs, media) can publish it. It is not tied to commerce.
Does the generator invent my tools?
No. It detects the servers you actually expose and leaves the capabilities for you to fill in; it never fabricates tools that do not exist.