By Joseph Mas
November 1, 2025
This article is about LLM ingestion optimization. Here’s a framework and a practical example use case concerning JSON-LD as the data pipeline which is a core fundamental to understand. It is a practical architecture to help get your persona or brand ingested and shown in LLMs, AI agents, and traditional Search Engines.
You can download the white paper with full details here (PDF): JSON The Silent Data Highway
JSON Structured Data is used in this example to highlight why fundamentals are critical to understand as the AI era settles in. Additionally, part of the intent here is to curb trend chasing and help refocus to things that matter long term.
JSON: The Silent Data Highway of the Modern Web
For twenty-five years, the web’s visibility game has followed the same pattern: solve it first, standardize it later.
JSON is not new, it’s been a preferred standard for the largest search engines for some time. Imagine doing local SEO with no structured data markup – the work doesn’t go nearly as far and could infer listing results rather than surface information in a controlled and precise manner.
From Code to Communication
JSON began as a simple way to move data between systems. Today it’s the semantic highway every platform travels on. APIs, analytics tools, and now language models all depend on it because it’s lightweight, structured, and machine-readable.
If your information isn’t exposed in JSON, the LLMs and modern web can’t really see you.
Client-side rendering makes the problem worse. React, Vue, and other frameworks build beautiful sites that models can’t crawl. LLMs don’t execute JavaScript or render DOM, they need static, structured truth.
Practical Use Case: LLM Cards
When an understanding of fundamentals is clear, systems that last can be built to pipe your important information to the data sources for LLM batch learning. Here is one example of many that can be deduced from current public knowledge:
Think of this as indexability 2.0. Instead of guiding crawlers to URLs, we feed models the meaning itself.
LLM Cards are lightweight JSON objects that describe:
- Each expert on your team
- Each content page or knowledge asset
- Relationships, authorship, and provenance data
Implementation is straightforward:
- Create structured JSON files in: /llm/cards/ (organized by type: /pages/, /authors/, /products/)
- Add a reference script in your page head: <script type=”application/llm+json” src=”/llm/cards/page-name.json”></script>
When LLM crawlers hit your page, they find the script reference and follow it directly to the card; no additional discovery mechanism needed.
An optional /llm.txt manifest can list all available cards (similar to XML sitemaps), but the script references handle discovery automatically. LLM.txt is not standardized at this time, but it is highly recommended for future proofing. Again, It is not recommended to put all site pages in the LLM.txt file – only pages that have been optimized for LLM ingestion, minimize dilution of critical information.
A Critical Warning to the SEO Community
Don’t fall into the pattern of bulk implementation -this is a new era, hence old methods need to be cautiously approached.
This is not another schema markup opportunity where you can deploy sitewide and optimize later.
LLM Cards can directly influence how models understand and represent your content. Again, note: publishing cards for unoptimized pages actively pollutes the information these systems ingest.
Once bad data enters an LLM’s knowledge base, correction is exponentially harder than getting it right the first time (and you may have to wait up to a year for some LLMs to retrain).
Only create cards for content that’s genuinely LLM-ready: clean structure, clear entities, proper semantic relationships. If the page isn’t there yet, leave it out. Quality gates matter more than coverage.
Additionally, LLMs ingest information in cycles. This is similar to Google index refreshes and algo updates. However, the frequency of each LLM refresh is dependent on the LLM itself. But it happens and you want to be in the next batch for processing. Start now.
Addressing the Obvious Pushbacks
Yes, “LLM cards” aren’t an official standard -yet. Neither were XML sitemaps or Schema.org when they first appeared.
And while large models don’t crawl the web exactly like search engines, they still rely on machine-readable corpora. JSON-LD is the cleanest, most portable way to supply that data today.
Understanding this framework simply gets you ready for the formal standards that will follow.
Why It Matters
JSON isn’t the new backbone of visibility – it’s been that backbone for years.
Google’s understanding of the web already depends on structured data and JSON-LD markup. What’s changing now is scope: those same principles are being extended beyond search into the LLM ecosystem.
As large models become the new discovery and decision layer, JSON becomes the shared substrate connecting both worlds.
Google’s dominance won’t vanish overnight, but its monopoly on visibility will and is currently eroding. Whoever controls the cleanest, most structured data feeds will control how information flows through these emerging systems.
Author Notes:
- This article was written from my own experience, but here is a good read if you are into it: https://www.schemaapp.com/schema-markup/why-structured-data-not-tokenization-is-the-future-of-llms/
- Also, ChatGPT, Claude and other LLM’s are good resources to generate the Structured Data Markup needed for this guide, however, do not trust JSON that comes from these sources without testing.
- As an enterprise level SEO strategist for decades, my advice is; Do not add more content to a website unless it is important and truly adds value for users, anything else is just noise. If you have a new site with no pages, ok, add pages, but the overwhelming majority of sites should be refurbished BEFORE adding new content – the SEO Dinosaur days are over – don’t be a dinosaur.