THE THATWARE AI STACK

Turn Your Website Into an AI-Ready Data Stack

Transform your existing website content into five coordinated, machine-readable assets designed to help AI crawlers, large language models, enterprise retrieval systems, and intelligent agents understand your digital presence more clearly.

ai.txt llms.txt ai-manifesto.json vector-feed.xml semantic-sitemap.xml
Generate Your AI Stack Explore the Five Files
Built from your existing website content. No separate content repository required.
AI Readiness Overview
Live generation metrics
Last generated: 2 hours ago
90% AI Stack Complete
Total URLs Analyzed 12,458
AI Files Generated 11,230
LLMS Files Generated 10,840
Manifesto Files 9,620
File Generation Status
5 Assets
ai.txt
11,230 90%
llms.txt
10,840 87%
ai-manifesto.json
9,620 77%
vector-feed.xml
9,180 74%
semantic-sitemap.xml
8,740 70%
BUILT FOR THE NEW MACHINE-READABLE WEB
AI Crawlers
LLMs
RAG Systems
Enterprise Search
AI Agents
WHY AI READINESS MATTERS

Your Website Was Built for Browsers.
AI Systems Need a Clearer Data Layer.

Traditional websites distribute important information across pages, navigation structures, metadata, sitemaps, and structured markup. That can make it difficult for automated systems to identify your most authoritative content, understand relationships between pages, and retrieve the right information efficiently.

The ThatWare AI platform converts your existing website into a coordinated set of machine-readable resources, giving AI systems a clearer path to your content, entities, priorities, and source relationships.

Learn more about AI readiness
Without an AI Stack
  • Critical content distributed across individual pages
  • Important sources difficult to prioritize
  • Semantic relationships remain implicit
  • Enterprise ingestion requires custom extraction
  • AI-facing agents maintained separately
With ThatWare AI
  • Five coordinated machine-readable assets
  • Priority sources organized for retrieval
  • Entities and content relationships mapped
  • Structured feeds prepared for AI workflows
  • One centralized generation process
FIVE FILES. ONE CONNECTED SYSTEM.

Every Layer Your Website Needs to Become AI-Ready

ai.txt

Establish Your Website’s AI Guidance Layer

ai.txt acts as the foundational entry point within the ThatWare AI Stack. It provides a concise, machine-readable reference that helps organize how your website presents its AI-facing resources.

Recommended information

  • Website and organization identity
  • Preferred source locations
  • Important content sections
  • Links to additional AI Stack assets
  • Content-use or access guidance
  • File version and update information

Primary benefits

A clear Starting Point

Give automated systems one location from which to identify your website’s AI-ready resources.

Centralized Guidance

Organize website-level instructions and important source references in one file.

Simple Deployment

Start improving machine readability without deploying the complete five-file stack.

Best suited for: Individual websites and organizations beginning their AI-readiness journey.
ai.txt Preview 
# Example: ThatWare AI
                                        # AI Guidance File

                                        site: https://www.example.com
                                        name: Example Company
                                        description: Example website description
                                        for AI readiness and digital growth.

                                        resources:
                                        - llms.txt: https://www.example.com/llms.txt
                                        - ai-manifesto.json: https://www.example.com/ai-manifesto.json
                                        - vector-feed.xml: https://www.example.com/vector-feed.xml
                                        - semantic-sitemap.xml: https://www.example.com/semantic-sitemap.xml

                                        version: 1.0
                                        last_updated: 2025-05-20

llms.txt

Curate the Content LLMs Should Understand First

llms.txt provides a structured, Markdown-based overview of a website and its most important resources. It can present priority URLs with descriptions that explain what each resource contains and why it matters.

The proposed llms.txt specification is intended to provide curated LLM context and coexist with existing web standards such as sitemaps and robots.txt. Adoption may vary between AI platforms.

Recommended information

  • Brand or project summary
  • Key products and services
  • Priority documentation
  • Authoritative content URLs
  • Descriptions of important resources
  • Optional secondary content

Primary Benefits

Curated LLM context

Highlight the pages and resources that best represent your organization.

Reduced source ambiguity

Explain what important URLs contain rather than presenting an unannotated URL list.

Better documentation discovery

Guide retrieval systems toward primary product, service, or knowledge resources.

Best suited for: Growing websites, SaaS platforms, knowledge bases, publishers, and documentation portals.
llms.txt Preview 
# Example: llms.txt

                                        site: https://www.example.com

                                        content:
                                        - homepage
                                        - products
                                        - services
                                        - documentation

                                        priority: high
                                        format: machine-readable
                                        version: 1.0

ai-manifesto.json

Define Your Brand, Content, and Governance in Structured JSON

ai-manifesto.json provides a structured representation of the organization behind the website, its primary entities, its content architecture, and its preferred source hierarchy.

This should be presented as a ThatWare AI structured asset, not as a universally adopted web standard.

Recommended information

  • Organization identity
  • Brand and product entities
  • Official domains and profiles
  • Content categories
  • Canonical source hierarchy
  • Ownership and authorship signals
  • Usage or governance policies
  • Version and modification timestamps

Primary benefits

Consistent entity definition

Present your organization, products, services, and content categories in a standardized structure.

Machine-readable governance

Communicate source ownership, preferred references, and content policies.

Integration-friendly output

Provide JSON-formatted information that can be processed by enterprise applications and data pipelines

Best suited for: Brands with multiple products, complex content ecosystems, compliance requirements, or enterprise integrations
ai-manifesto.json Preview 
{
                                    "name": "Example Company",
                                    "type": "Organization",
                                    "description": "Example AI-ready
                                    organization",

                                    "entities": [
                                        "Example Product",
                                        "Example Service"
                                    ],

                                    "ai_ready": true,
                                    "version": "1.0"
                                    }

vector-feed.xml

Prepare Website Content for Retrieval and Vector Workflows

vector-feed.xml organizes website content and metadata into a structured feed designed to support ingestion, chunking, embedding, retrieval, and enterprise RAG workflows.

It should be positioned as a preparation and interoperability asset—not as a guarantee that external AI providers will ingest the feed.

Recommended information

  • Stable content identifiers
  • Canonical source URLs
  • Page and section titles
  • Content segments
  • Content types
  • Topic and entity tags
  • Language information
  • Publication and modification dates
  • Parent-child relationships

Primary benefits

Structured AI ingestion

Reduce the amount of custom extraction needed before website content enters a retrieval pipeline.

Source traceability

Connect each content segment to its canonical page and stable identifier.

Freshness management

Help downstream systems identify content that has changed and may require reprocessing

Best suited for: Enterprise search, internal copilots, RAG systems, knowledge assistants, and large content repositories
vector-feed.xml Preview 
<vector-feed>
                                            <site>https://www.example.com</site>

                                            <document>
                                                <url>/about</url>
                                                <title>About Us</title>
                                                <priority>high</priority>
                                            </document>

                                            <document>
                                                <url>/services</url>
                                                <title>Services</title>
                                            </document>
                                        </vector-feed>

semantic-sitemap.xml

Map What Your Content Means—not Only Where It Lives

A traditional sitemap primarily helps systems discover website URLs and updates. semantic-sitemap.xml extends that concept by describing content types, topics, entities, and relationships within the website.

It should complement the standard sitemap.xml, not replace it. Google describes conventional sitemaps as a mechanism for informing search systems about new or updated website pages.

Recommended information

  • Canonical URLs
  • Content classifications
  • Topic clusters
  • Primary entities
  • Parent and child relationships
  • Related content
  • Language and region
  • Publication and modification dates
  • Priority source indicators

Primary benefits

Semantic site mapping

Show how pages, entities, topics, and content clusters relate to one another.

Stronger information architecture

Expose relationships that may otherwise remain hidden inside navigation or internal links.

Scalable content discovery

Help machines explore large websites by meaning, content type, and hierarchy.

Best suited for: Enterprise sites, publishers, ecommerce catalogs, multi-region websites, and large knowledge ecosystems.
semantic-sitemap.xml Preview 
<semantic-sitemap>
                                            <entity id="company">
                                                <name>Example Company</name>
                                            </entity>

                                            <relationship>
                                                <source>company</source>
                                                <target>services</target>
                                                <type>provides</type>
                                            </relationship>

                                            <relationship>
                                                <source>services</source>
                                                <target>products</target>
                                                <type>includes</type>
                                            </relationship>
                                        </semantic-sitemap>
FROM FILE GENERATION TO BUSINESS VALUE

Build a Website AI Systems Can Work With

Improve Machine Discoverability

Create clear, centralized resources through which automated systems can locate your most important content and AI-facing assets.

Strengthen Brand and Entity Consistency

Define your organization, products, services, content categories, and canonical sources in coordinated machine-readable formats.

Accelerate Enterprise AI Projects

Prepare website content for retrieval, vectorization, internal search, assistants, and RAG applications without beginning every project with a custom scraping pipeline.

Reduce Manual Technical Work

Generate coordinated website assets from a centralized platform instead of manually authoring and maintaining each file.

Improve Content Governance

Connect content records with source URLs, ownership information, modification dates, and preferred references.

Scale Across Larger Websites

Apply one coordinated AI-readiness architecture across extensive content libraries and multi-site environments

ONE WORKFLOW

From Website URL to Complete AI Stack

1

Analyze Your Website

ThatWare AI discovers accessible pages, content types, metadata, internal relationships, and important entities.

2

Structure the Information

The platform organizes website content into source records, topic groups, entities, hierarchy, and machine-readable metadata.

3

Generate Your Assets

ThatWare AI produces the files included in your selected plan using one coordinated content model.

4

Review and Validate

Inspect coverage, file health, excluded URLs, missing information, and structural issues before deployment.

5

Deploy and Regenerate

Publish the generated assets to the appropriate root locations and regenerate them when your website content changes.

Start With Your Website URL
CHOOSE YOUR AI-READINESS DEPTH

Start With One File or Deploy the Complete Stack

Freemium

ai.txt
1 Website
Start building your website's AI readiness for free.
Start Free

Boost

2 Websites
  • ai.txt
  • llms.txt
Essential files to help LLMs understand and work with your content.
Choose Boost
Most Popular

Hyper-Intelligence

3 Websites
  • ai.txt
  • llms.txt
  • ai-manifesto.json
  • vector-feed.xml
  • semantic-sitemap.xml
The complete AI Stack for maximum AI readiness.
Unlock the Complete Stack

Bespoke Enterprise

Custom
Custom websites, agents, integrations, and implementation support tailored to your needs.
Contact Enterprise Sales
Enterprise AI Readiness
ENTERPRISE AI READINESS

Build a Machine-Readable Infrastructure
Across Your Digital Estate

Deploy a coordinated AI-readiness architecture across large websites, mobile brands, regional domains, product portfolios, and enterprise knowledge environments.

Request an Enterprise Consultation View Enterprise Architecture
Multi-domain workspace
Custom generation rules
Agent version history
Role-based access
Validation & approval workflows
API & webhook access
Audit logs
Custom schemas
Managed implementation
Priority technical support
FREQUENTLY ASKED QUESTIONS

No. The files are designed to improve machine readability, organization, and technical readiness. Visibility and citations also depend on content quality, authority, accessibility, relevance, platform policies, and each AI system’s retrieval processes.

No. It should complement established crawling, indexing, structured-data, and SEO practices rather than replace them

ai.txt is ThatWare AI’s foundational site-guidance asset. llms.txt is a proposed Markdown format for presenting a curated overview and list of important resources to language models.

No. It remains a proposed convention, and implementation or adoption can vary between platforms.

It is a ThatWare AI structured JSON asset designed to describe an organization, its primary entities, its content categories, source hierarchy, and AI-facing governance information.

It prepares website content and metadata for structured ingestion into retrieval, embedding, enterprise search, or RAG workflows.

No. It extends the website’s machine-readable architecture with semantic classifications and relationships while the standard sitemap continues to support URL discovery.

The Hyper-Intelligence Plan includes the complete five-file AI Stack. Bespoke Enterprise plans can be configured around larger or more specialized requirements.

Your Website Already Contains the Knowledge.
Make It Ready for AI.

Organize the machine-readable layer that helps crawlers, LLMs, retrieval systems, and agentic AI understand what your site contains, where it matters, and how it relates.

Generate Your AI Stack Speak With an AI-Readiness Specialist