How well can AI agents find, read, and verify your investor data?
Full breakdown: query topics, endpoint usage, trend over time, peer comparison
AI agents need structured, anchored data to give investors reliable answers about NATIONAL HEALTHCARE CORP. Here's what we invested to prepare it — and what an AI agent gets in return.
| SEC EDGAR extraction | 220 filings indexed |
| AI profile generation | ~$0.10 (Claude Sonnet) |
| IR site scraping | Failed — site blocks AI |
| Engineering attempts | Multiple days, no results |
| Transcript status | Cannot extract |
| Stock quote pipeline | not tracked |
| Origin chain signing | Every response anchored |
Your IR site is currently impossible for AI to access. We invested engineering time and failed. This means AI agents answering questions about your company are working from unreliable sources — web scrapes, cached pages, outdated data. This is the foundation of inaccurate AI responses about your company.
| Company identity | ~200 tokens |
| Full profile (people, products) | ~800 tokens |
| Filing index (220 filings) | ~500 tokens |
| Stock quote with provenance | ~150 tokens |
| Earnings facts | not captured |
| Topic search (cross-company) | ~300 tokens |
| Total per review | ~2,450 tokens |
| Time to answer | 2–4 seconds |
| Cost per query | < $0.01 |
| Provenance | Full chain to SEC.gov |
4-5 API calls. Structured JSON. Every response signed. Agent gets exactly what it needs — not a 200-page PDF.
When your IR site is inaccessible to AI, agents fill the gap with whatever they can find — web scrapes, cached data, secondhand sources. This is the foundation of inaccurate AI analysis. Investors using AI tools are getting unreliable information about your company right now. Origin's IR for AI program fixes this.
An AI agent doesn't fetch everything at once. It asks specific questions. Here's the real per-query cost:
| Question | Via Web Search | Via Origin | Savings |
|---|---|---|---|
| "Who is NHC?" | 10,000–50,000 tokens | ~200 tokens | 50–250x |
| "Latest stock price?" | 5,000–20,000 tokens | ~150 tokens | 33–133x |
| "Key people and products?" | 15,000–40,000 tokens | ~800 tokens | 19–50x |
| "Show me SEC filings" | 8,000–25,000 tokens | ~500 tokens | 16–50x |
Web search: agent must discover URL, render JavaScript, parse HTML, extract data, hope it's current. Origin: structured JSON, 2-4 seconds, full provenance chain.
Today, AI agents are the fastest-growing audience for investor data. But most IR sites were built for humans reading in browsers. AI agents need structured, discoverable, verifiable data. Here's your roadmap:
Add a single JSON file at investor.nhc.com/.well-known/ai that tells AI where to find your data. Think of it as robots.txt for AI — instead of telling crawlers what NOT to read, it tells AI agents what TO read and where.
Time to implement: 10 minutes. One JSON file, no code changes.
Copy this JSON to investor.nhc.com/.well-known/ai
{
"schema_version": "1.0",
"name": "NATIONAL HEALTHCARE CORP \u2014 Investor Relations",
"verified_by": "origin.rootz.global",
"investor_relations": {
"profile": "https://origin.rootz.global/api/company/NHC",
"filings": "https://origin.rootz.global/api/company/NHC/filings",
"quotes": "https://origin.rootz.global/api/company/NHC/quote",
"signals": "https://origin.rootz.global/api/signals?ticker=NHC",
"static_page": "https://origin.rootz.global/static/company/NHC.html"
},
"provenance": "All data carries an origin leaf: sha256(content + parent + timestamp). Chain traces to SEC.gov PEM signatures.",
"contact": "discover@rootz.global"
}
This tells every AI agent: "The company itself says to get investor data from Origin." One file, instant AI visibility.
AI agents struggle with PDFs, webcasts, and JavaScript-rendered pages. The highest-impact change: publish machine-readable versions of your most-requested content.
| Document | Current Format | AI-Ready Format |
|---|---|---|
| Company overview | HTML (often JS-rendered) | Markdown file or FAQ JSON — AI reads these natively |
| Earnings transcripts | Not available | Markdown + JSON with speaker tags and key metrics |
| Business description | Buried in 10-K PDF | Standalone MD file updated quarterly |
| FAQ | HTML accordion (often invisible to AI) | JSON-LD FAQ schema — search engines already support this |
| Press releases | HTML (varies by platform) | Structured with date, type, headline, summary fields |
Why Markdown? Every major AI model reads Markdown natively. It's the universal language of AI communication. A business-description.md on your IR site is instantly consumable by Claude, GPT, Gemini, Grok — no parsing needed.
AI agents are already citing your company data. The question is whether that data has a verifiable chain back to you. Origin anchoring binds your investor data to your corporate identity — so every fact carries proof of where it came from.
Data with origin is more trustworthy than data without origin. When an AI reads your anchored data, it knows the chain is real — and it carries that chain forward to everyone who reads its output.
Join our IR for AI program — we handle the setup.
Once your data is anchored with origin, you need to see who's reading it. Program members get:
No other service provides AI traffic analytics for investor relations. This data doesn't exist anywhere else.
Program members get guaranteed scanning, capture, and origin anchoring:
| Property | Finding |
|---|---|
| IR Domain | |
| AI Accessibility | impossible — no IR site found via URL pattern testing |
| Transcripts | ✗ Not found |
| Press Releases | ✗ Not found |
| IR Platform | Unknown |
| Last Scanned | Not yet scanned |
Get this AI Readiness Report for NHC delivered to your inbox — share it with your IR team.
No signup needed — your data is already partially accessible via the Origin API:
| Data | Status | Link |
|---|---|---|
| Company identity | ✓ SEC-verified | View JSON |
| AI profile | ✓ Extracted | View JSON |
| SEC filings | ✓ 220 indexed | View JSON |
| Stock quote | Not tracked | — |
| Transcripts | Not captured | — |
| Earnings calendar | Next: 2026-09-12 | View JSON |