# Aethis - [Introduction](https://docs.aethis.ai/getting-started/introduction.md): Compile source documents into deterministic eligibility rules. Decide in under 1ms, explain why, and guide users through the shortest path to a determination — no LLM at decision time. - [Your first decision](https://docs.aethis.ai/getting-started/first-decision.md): Run a real, audited eligibility decision against the live API. No signup, no Aethis key, no model-provider key. - [Try it](https://docs.aethis.ai/getting-started/try-it.md): Live rulesets you can curl right now. No signup, no key. - [How Aethis works](https://docs.aethis.ai/concepts/how-it-works.md): Source text in. Deterministic decisions out. No LLM at runtime. - [When to use Aethis](https://docs.aethis.ai/concepts/when-to-use.md): Good fit domains, DSL capabilities, known limits, and workarounds. - [Nomenclature](https://docs.aethis.ai/concepts/nomenclature.md): What a rulebook and a ruleset are — and how the aethis/* namespace works. - [Worked examples](https://docs.aethis.ai/getting-started/examples.md): Worked examples you can run with no key, plus what the invite-only authoring workflow produced for each. - [AI coding agents](https://docs.aethis.ai/agents/index.md): Connect Aethis to Claude Code, Cursor, Windsurf, or another MCP-compatible coding agent. - [Your first 20 minutes with an AI coding agent](https://docs.aethis.ai/agents/onboarding.md): Connect Claude Code or Codex, discover Aethis tools and skills, and explain your first decision. Then author a reviewed policy and explore versioned replay. - [Versions, regression and pinned replay](https://docs.aethis.ai/agents/versions-and-replay.md): Compare reviewed cases, inspect a composed rulebook and replay an exact publication before integrating decisions into your application. - [Which interface?](https://docs.aethis.ai/interfaces/which-to-use.md): MCP server, CLI, Python SDK, or REST API — pick the right tool for your workflow. - [MCP server overview](https://docs.aethis.ai/mcp-server/overview.md): Install and configure aethis-mcp for Claude Code, Codex, Claude Desktop, Cursor, and Windsurf. - [Tools reference](https://docs.aethis.ai/mcp-server/tools.md): Every aethis-mcp tool — parameters, examples, and response shapes. - [CLI](https://docs.aethis.ai/interfaces/cli.md): File-based rule authoring and eligibility evaluation from the terminal. - [Python SDK](https://docs.aethis.ai/interfaces/python-sdk.md): Typed Python client for the Aethis decision API — sync and async clients, stateful decision sessions, ergonomic Pydantic models. - [REST API](https://docs.aethis.ai/interfaces/rest-api.md): Integrate eligibility evaluation and rule authoring directly into your application. - [Evaluate a case](https://docs.aethis.ai/recipes/evaluate-a-case.md): Agent recipe: schema → collect fields → decide → explain. End-to-end, copy-pasteable. - [Author a rule from legislation](https://docs.aethis.ai/recipes/author-a-rule.md): Agent recipe: create project → upload sources → three-phase generate-and-test → publish. - [Debug a failing decide](https://docs.aethis.ai/recipes/debug-a-decide.md): Agent recipe: when /decide returns the wrong answer, or an error, or undetermined — what to check and in what order. - [LangGraph integration](https://docs.aethis.ai/recipes/langgraph-integration.md): Drop Aethis into a LangGraph flow as a deterministic decision node. ~10 lines via langchain-mcp-adapters. - [Author your first ruleset](https://docs.aethis.ai/getting-started/author-first-ruleset.md): Create, review, generate, test, publish and decide a small private ruleset through the Aethis authoring API. - [Phase 1 — Section discovery](https://docs.aethis.ai/authoring/section-discovery.md): Split complex legislation into independently testable sections before authoring begins. - [Phase 2 — Field vocabulary](https://docs.aethis.ai/authoring/field-vocabulary.md): Establish and validate the input field names before writing test cases. - [Phase 3 — Rule generation](https://docs.aethis.ai/authoring/rule-generation.md): Generate rules from source text, run tests, iterate with guidance until all tests pass, then publish. - [Provenance and citations](https://docs.aethis.ai/authoring/provenance.md): Bind each criterion to the document it comes from, verified verbatim against retained bytes at publish time. - [Review checks](https://docs.aethis.ai/authoring/review-checks.md): The Authoring Coach rubric — what each check measures, how it's scored, and the one lever that fixes it. - [Capabilities and access](https://docs.aethis.ai/reference/capabilities.md): What Aethis does without a key, what needs an invite, and the generated inventory of tools and published package versions. - [Deployed contract status](https://docs.aethis.ai/reference/deployed-contract.md): What api.aethis.ai serves today, and how to confirm which engine build answered you. - [API Reference](https://docs.aethis.ai/api-reference/introduction.md): REST API for evaluating eligibility and authoring rule rulesets. - [Authentication & API keys](https://docs.aethis.ai/reference/authentication.md): When you need a key, what a key can do, and how to diagnose a 403 before you hit one. - [Decision envelope](https://docs.aethis.ai/concepts/decision-envelope.md): Every /decide response carries a reproducibility envelope for audit and replay. - [Ruleset & rulebook graphs](https://docs.aethis.ai/reference/graph.md): The visual map of a compiled ruleset — fields, criteria, groups, and the outcome, as structured data and as Mermaid. - [Errors reference](https://docs.aethis.ai/reference/errors.md): Every reason_code the Aethis public API emits, plus recovery actions. - [Troubleshooting](https://docs.aethis.ai/getting-started/troubleshooting.md): Common problems and how to resolve them. - [Changelog](https://docs.aethis.ai/changelog/index.md): Changes across the Aethis platform — the engine, CLI, MCP server, and Python SDK. ## OpenAPI Specs - [openapi](/api-reference/openapi.json) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.