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.
Agents and prompts
Guide for LLMs and agents that write AI Parlance. Spec: Specification. Core syntax: Syntax.How the AI should write .aip
- Predictable structure:
app→entity→crud→policy→workflow - Clear domain names; one language per file
- Explicit semantics (
required,belongs_to, policy predicates) - Avoid long imperative logic inside
workflow - Do not duplicate
authif already onapp
Minimal prompt → output
Prompt:Prompting strategy
Describe: entities, relations, business rules, who can do what. Avoid asking for: “generate in Go/TypeScript”, framework details, manual route boilerplate.ai_context
Semantic context for agents, validators, and RAG — not emitted as target code directly.
Controlled grammar
Few alternative forms for the same structure — see grammar. Prefer inline validation onentity over duplicate validation blocks.
Agent → software flow
.aip — not generated Go/TS.
Pre-delivery checklist
-
appwithdatabaseandauthwhen usingauthenticated/role - every referenced
entityexists -
owner_*policies reference a real FK field -
workflowhaswhen -
emituses declaredeventtypes - canonical modifier order
-
@0.1onappwhen using beta blocks
