Investigate Agent-Native Architecture Audit
This page is a capture in the deferred bucket of the product backlog — a pre-sprint idea, not yet pulled into a sprint as a story.
Conduct a comprehensive review of the codebase against agent-native architecture principles, launching parallel sub-agents for each principle and producing a scored report.
Core Principles to Audit:
- Action Parity - "Whatever the user can do, the agent can do"
- Tools as Primitives - "Tools provide capability, not behavior"
- Context Injection - "System prompt includes dynamic context about app state"
- Shared Workspace - "Agent and user work in the same data space"
- CRUD Completeness - "Every entity has full CRUD (Create, Read, Update, Delete)"
- UI Integration - "Agent actions immediately reflected in UI"
- Capability Discovery - "Users can discover what the agent can do"
- Prompt-Native Features - "Features are prompts defining outcomes, not code"
Links: