> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aiparlance.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> AI-first intermediate representation for AI-assisted software generation

# AI Parlance

<Note>
  **v0.1 is specification-only.** Parser, validator, and transpilers are not published yet. This documentation defines the language; code generation is planned.
</Note>

AI Parlance is an AI-first language for **intermediate representation (IR)** in AI-assisted software generation — focused on data-oriented applications, APIs, authorization, and declarative automations.

Humans, agents, and LLMs describe systems in `.aip`; transpilers turn the spec into concrete implementations.

```txt theme={null}
Human or AI
↓
AI Parlance (.aip)
↓
AST + validation
↓
Transpilers
↓
Go, TypeScript, SQL, OpenAPI, …
```

Normative details: [Specification](/en/specification).

***

## Why it exists

When models generate code directly in general-purpose languages, they face:

* large amounts of boilerplate (CRUD, routes, validation, migrations)
* inconsistency across stacks
* large context → more tokens and more hallucination
* business rules and permissions scattered in generated code

AI Parlance concentrates **intent** in a compact semantic layer before implementation.

***

## What it describes (and what it does not)

| Describes                   | Does not describe                      |
| --------------------------- | -------------------------------------- |
| entities, types, relations  | custom UI                              |
| CRUD, indexes, migrations   | complex algorithms                     |
| auth, policies              | integrations without a dedicated block |
| domain workflows and events | hand-written imperative SQL            |

***

## Minimal example

```aip theme={null}
app Demo @0.1 {
  database postgres
}

entity User {
  name: string required
  email: email required unique
}

crud User
```

See [examples/minimal.aip](https://github.com/eudameron/aiparlance/blob/main/examples/minimal.aip). Every v0.1 spec requires one `app` block ([Specification](/en/specification)).

One definition can feed multiple generators (see [transpiler matrix](/en/specification#transpiler-matrix)).

***

## AI-first principles

The language prioritizes, in order:

1. domain intent and semantics
2. predictable structure for LLMs
3. static validation before generation
4. multi-target implementation via transpilers

***

## Documentation map

| Page                               | Content                                |
| ---------------------------------- | -------------------------------------- |
| [Specification](/en/specification) | Grammar, builtins, policies, stability |
| [Cost impact](/en/cost-impact)     | Tokens, honest comparisons             |
| [Syntax](/en/syntax)               | Core + Infra blocks                    |
| [Database](/en/database)           | Migrations, indexes, naming            |
| [Security](/en/security)           | Auth, policies, rate limit             |
| [Workflows](/en/workflows)         | Events, jobs, queues                   |
| [Agents](/en/agents)               | Prompts, `ai_context`, best practices  |

Reference spec: [examples/crm-reference.aip](https://github.com/eudameron/aiparlance/blob/main/examples/crm-reference.aip).