AI agent development standards using golanggraph for graph-based workflows, langchaingo for LLM calls, tool integration, MCP, and LLM best practices (context compression, prompt caching, attention raising, tool response trimming).
Go backend development standards using DDD architecture, ent ORM, fx DI, and kiwi-lib utilities. Covers project structure, domain design, API/application/infrastructure layers, database workflow, and coding requirements.
Kiwi-user authentication integration for frontend (login flows, token storage, refresh) and backend (token verification via API or public key, auth middleware, user ID extraction).