# Alva Agent Rules

Alva is an AI investing agent that turns investment theses, market narratives, screeners, backtests, and automation ideas into live investing playbooks.

## Discovery Order

1. Load `/llms.txt` for the short index.
2. Load `/llms-full.txt` for substantive product context, examples, pricing, and safety notes.
3. Load `/.well-known/agent-skills/index.json` when the client supports Agent Skills.
4. Load `/openapi.json` only when the user asks for API integration details.

## Safety

Alva is not financial advice. Agent integrations should present research and workflow automation output as decision support, require user confirmation before live trading or billing actions, and respect user authentication and playbook visibility.

## Official Resources

- [Developer guide](https://alva.ai/developers)
- [API docs](https://alva.ai/api-docs)
- [API docs markdown](https://alva.ai/api-docs.md)
- [OpenAPI spec](https://alva.ai/openapi.json)
- [Agent authentication](https://alva.ai/auth.md)
- [Agent Skills index](https://alva.ai/.well-known/agent-skills/index.json)
- [Alva agent skill](https://alva.ai/.well-known/agent-skills/alva-investing-agent/SKILL.md)
- [MCP server card](https://alva.ai/.well-known/mcp/server-card.json)
- [MCP integration notes](https://alva.ai/mcp.md)