# aityx docs

> aityx is a decision API for AI applications and agents. Turn questions or a policy into a model you own, submit it with each case, and receive decisions, computed amounts and dates, and an execution receipt.

## Docs

- [Introduction](https://aityx.ai/docs): Create rules you can inspect. Send your model with each case and receive an answer you can trace.
- [Run your first policy](https://aityx.ai/docs/quickstart): Create invoice payment rules, keep the model, check the cutoff and test a revised discount.

## Concepts

- [System One and System Two](https://aityx.ai/docs/concepts/system-one-and-two): Start with questions or a policy. Keep the model and send it with each execution.
- [State](https://aityx.ai/docs/concepts/state): Supply matching JSON or let the reader extract facts. Inspect given and read inputs in the receipt.
- [Questions](https://aityx.ai/docs/concepts/questions): The five question types, their criteria, and the answer each returns.
- [Models](https://aityx.ai/docs/concepts/models): Keep the complete model file: executable content and the questions that define its answers.
- [Receipts](https://aityx.ai/docs/concepts/receipts): Trace an answer to established inputs and executed rules. Keep the model, original case and receipt together.
- [Determinism and confidence](https://aityx.ai/docs/concepts/determinism-and-confidence): What is deterministic, what is probabilistic, and how to use confidence here versus in Jev.

## Guides

- [Call it from JavaScript and Python](https://aityx.ai/docs/guides/call-from-code): Submit the complete model, keep the returned receipt and handle missing facts.
- [Build a model from a prompt or a document](https://aityx.ai/docs/guides/build-from-a-prompt): System Two from a task description, a policy PDF, or both. Portable definitions, question contracts and sample inputs.
- [Define a model by hand](https://aityx.ai/docs/guides/define-by-hand): Write and validate the compact JSON yourself, then submit it with each execution.
- [Compare revised rules](https://aityx.ai/docs/guides/revise-and-replay): Keep both definitions and compare the same inputs before changing your application.
- [The console](https://aityx.ai/docs/guides/console): Inspect and run models in a session, download your work, and track the balance shared with API calls.

## Resources

- [Model format](https://aityx.ai/docs/resources/model-format): The compact JSON a model is written in. Types, inputs, decisions, tables, functions and the expression language.
- [Errors](https://aityx.ai/docs/resources/errors): Problem details, stable codes, and what to do about each.
- [Pricing and limits](https://aityx.ai/docs/resources/pricing-and-limits): Which request uses each rate, how caching is billed, and how your credit balance works.

## Coming from Jev

- [Coming from Jev](https://aityx.ai/docs/coming-from-jev): Change the base URL, keep the request. What is the same, what is extra, what to watch.

## Reference

- [aityx API](https://aityx.ai/docs/reference)

### Operations

- [Create, revise or check a portable model](https://aityx.ai/docs/reference/operations/author-decision)
- [Execute questions or a portable model](https://aityx.ai/docs/reference/operations/execute-decision)

## Agent skills

- [aityx-docs](https://aityx.ai/docs/.well-known/agent-skills/aityx-docs/SKILL.md): Read the aityx docs instead of answering from memory. aityx is a decision API for AI applications and agents. Turn questions or a policy into a model you own, submit it with each case, and receive decisions, computed amounts and dates, and an execution receipt. Use when a task involves aityx docs: how it works, how to set it up or configure it, or its API.

## Agent resources

- [llms-full.txt](https://aityx.ai/docs/llms-full.txt): The full Markdown of every page in one file.
- [Page Markdown](https://aityx.ai/docs/index.md): Append `.md` to any page URL to fetch that page as raw Markdown.
- [JSON API](https://aityx.ai/docs/api/docs/pages.json): Page index of the JSON docs API; each entry links the page's JSON and Markdown forms. Described by the OpenAPI document at https://aityx.ai/docs/openapi.json.
- [Agent skills](https://aityx.ai/docs/.well-known/agent-skills/index.json): Agent Skills discovery index of the skills this site publishes.
- [API catalog](https://aityx.ai/docs/.well-known/api-catalog): RFC 9727 linkset of the APIs documented here.
- [AI catalog](https://aityx.ai/docs/.well-known/ai-catalog.json): ARD manifest of the agent-facing resources on this site (MCP server, skills, APIs).
- [agent-readability.json](https://aityx.ai/docs/agent-readability.json): Manifest of every agent-facing artifact on this site.
- [Sitemap](https://aityx.ai/docs/sitemap.xml): Every indexable page URL with its last-modified date.