AI Agent Architecture: Tools, State, Approvals, and Safe Execution
A practical architecture for agents that call real tools: narrow capabilities, durable state, explicit approvals, idempotent execution, and measurable outcomes.
Read articleBlog · Tags
#Ai agents
Engineering guides, platform notes, and honest lessons from running modern applications. Ai agents.
2 articles
RAG vs AI Agents: When Do You Need Each?
RAG retrieves relevant knowledge for an answer, while an agent can choose tools and take steps. Use retrieval alone when answering is the full job.
Read article