When should we build an AI agent vs a direct LLM call?

“Build an agent when the task requires multi-step reasoning, tool use (databases, APIs, code execution), conversation state across turns or routing between specialized capabilities. Use a direct LLM call (OpenAI/Anthropic SDK) for single-shot tasks: classification, summarization, structured extraction, single-question Q&A. Most "AI features" are actually direct calls. Agents are for workflows, not features.”