Skip to content
J·BJon BishopFractional growth marketer

Data platforms · llms.txt file breakdown

Hex llms.txt

A directly retrieved Markdown index for Hex's documentation, with 35 links across 8 detected headings.

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Open saved text ↗

Complete saved Markdown shown below.

# Hex

> Hex is an AI analytics platform for trusted data exploration, agentic notebooks, conversational self-serve analytics, and interactive data apps, with shared context and governance managed by data teams.

Context Studio brings together business definitions, models, and analytical work for agents to use across Hex, Slack, MCP-connected tools, and the CLI. Data teams can inspect agent activity, evaluate context changes, and address gaps in answers.

For research, follow the relevant links below. Public content pages on hex.tech and learn.hex.tech support `Accept: text/markdown`; use the canonical URLs rather than assuming a `.md` suffix. Consult the linked pricing and API documentation for current plans, limits, and permissions.

Hex workspace data is private. Product API calls require a bearer token; MCP access requires the user to authorize an OAuth connection.

## Start here

- [Hex](https://hex.tech/): Platform overview and common questions.
- [AI analytics platform](https://hex.tech/capability/ai/): How agents, analytics, and shared context work together.
- [Documentation](https://learn.hex.tech/docs): Product guides, administration, and implementation details.

## Choose a workflow

- [Business intelligence](https://hex.tech/product/bi/): Combine governed reporting with conversational self-service.
- [Context Studio](https://hex.tech/product/context-studio/): Manage business context, inspect agent activity, and improve answers.
- [Threads](https://hex.tech/product/threads/): Ask data questions in plain language and review the analysis behind answers.
- [Generative data apps](https://hex.tech/product/data-apps/): Turn analytical work and prompts into shareable dashboards and interactive apps.
- [Agentic notebooks](https://hex.tech/product/notebooks/): Analyze data with SQL, Python, no-code tools, and AI assistance.
- [Evals](https://hex.tech/blog/evals/): Compare models, effort levels, and context changes for quality and cost.
- [Integrations](https://hex.tech/product/integrations/): Connect warehouses, semantic layers, catalogs, and orchestration tools.
- [Exploratory analysis](https://hex.tech/capability/exploratory-analysis/): Investigate complex questions beyond existing reports.

## Evaluate and get started

- [Switching to Hex](https://hex.tech/product/switching-to-hex/): Evaluate fit, run a proof of concept, and plan migration.
- [Comparisons](https://hex.tech/compare/): Compare Hex with BI and analytics platforms.
- [Pricing](https://hex.tech/pricing/): Current plans, packaging, and usage considerations.
- [Start a Hex trial](https://app.hex.tech/signup): Create a workspace.
- [Request a demo](https://hex.tech/request-a-demo/): Discuss enterprise requirements or arrange a walkthrough.

## Agent and developer access

- [Hex MCP server](https://learn.hex.tech/docs/api-integrations/mcp-server): Connect an authorized assistant for data questions, project search, and Threads; includes client setup and tools.
- [Hex CLI](https://learn.hex.tech/docs/api-integrations/cli): Work with projects, context, and workspace resources from the terminal.
- [API overview and authentication](https://learn.hex.tech/docs/api-integrations/api/overview): Execute projects and automate administration; check token scopes, workspace URLs, and plan requirements.
- [API reference](https://learn.hex.tech/docs/api-integrations/api/reference): Supported operations, parameters, and request and response schemas.
- [Product OpenAPI specification](https://static.hex.site/openapi.json): Machine-readable contract for the authenticated Hex API.
- [API limits](https://learn.hex.tech/docs/api-integrations/api/overview#kernel-and-rate-limits): Current request limits and project execution constraints.

## Trust and governance

- [Enterprise analytics](https://hex.tech/enterprise/): Enterprise governance, administration, deployment, and support.
- [Security](https://hex.tech/security/): Security controls, compliance, and data protection.
- [Trust Center](https://trust.hex.tech/): Security documentation, certifications, and compliance details.
- [Privacy policy](https://learn.hex.tech/docs/legal/privacy): Data handling, privacy rights, and contact information.
- [Service status](https://status.hex.tech/): Current availability and incident history.

## Customer evidence

- [Customer stories](https://hex.tech/customers/): Examples across industries and analytical workflows.
- [LangChain](https://hex.tech/customers/langchain/): Modernizing BI and expanding self-service.
- [Notion](https://hex.tech/customers/notion/): Helping more teams answer their own data questions.
- [StubHub](https://hex.tech/customers/stubhub/): Supporting business analysts and self-serve exploration.

## Optional

- [Sitemap](https://hex.tech/sitemap.xml): Broader index of public marketing pages.
- [Robots](https://hex.tech/robots.txt): Crawl directives for automated clients.
- [Blog](https://hex.tech/blog/): Product announcements and analytics articles.
- [About Hex](https://hex.tech/about/): Company background, leadership, and newsroom links.

Measured from the saved file

Linked document

UTF-8 text size
5.0 KB5082 bytes
Token count
1067o200k_base encoding
Markdown links
3535 distinct URLs
Fenced code blocks
065 lines in the file

Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.

Project H1
Hex

Opening blockquote

Hex is an AI analytics platform for trusted data exploration, agentic notebooks, conversational self-serve analytics, and interactive data apps, with shared context and governance managed by data teams.

Context architecture

How the content is divided

7 H2 sections organize 35 parsed Markdown links. 0 links point to .md or .markdown paths; 11 link occurrences use another hostname. Linked destinations have not been recursively validated.

H2 sectionLinksUTF-8 bytesTokens
Start hereLine 11329565
Choose a workflowLine 1781022221
Evaluate and get startedLine 285491117
Agent and developer accessLine 366962192
Trust and governanceLine 455531107
Customer evidenceLine 53441093
OptionalLine 60 · Optional433879

Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.

Embedded material

Code, installation and API examples

Fenced blocks
0 closed
Declared languages
No fenced blocks detected
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
0 fenced lines match request-method patterns
Authentication links
0 links have authentication-related labels

Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.

Publisher prioritization

The Optional section

1 H2 section named “Optional” contain 4 parsed links. 31 links sit outside those sections. That puts 11.4% of the file’s parsed links under Optional.

The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.

Machine-readable routes

MCP references and configuration text

MCP-related text was detected in the captured file. 1 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.

These are text and link observations. No MCP server connection, authentication or tool call was tested.

Index and bundle

llms-full.txt companion

Not found at checked URLs

A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.

Change evidence

What can be said about freshness

This capture establishes a baseline. Update frequency cannot be determined from one observation.

File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.

Capture identity and measurement method
Requested endpoint
https://hex.tech/llms.txt
Final endpoint
https://hex.tech/llms.txt
HTTP status
200
Content type
text/plain; charset=UTF-8
Text retrieval
Firecrawl literal text capture
Tokenizer
tiktoken 0.14.0 · o200k_base
SHA-256 of saved UTF-8 text
3de8cceed9fd3dfb730a25a0d8df574f8f2af0244c14f9946c2c7d6a2d51e8da

Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.

Related tools and resources

Contact Jon