SESK: Stuff Everyone Should Know · sesk.info/ai-agent-vs-workflow
What separates an AI agent from an AI workflow, in Anthropic's definition?
An agent directs its own steps and tool use; a workflow follows predefined code paths.
- Agents are always bigger models
- Workflows cannot use tools
- Agents choose their own steps and tools ✔
Why: In a workflow, programmers fix the order of steps in code. An agent is an LLM using tools in a loop, deciding what to do next based on feedback from its environment.
Huh, didn't know that: Anthropic's guide says agents are typically just LLMs using tools based on environmental feedback in a loop.
A workflow is a recipe. An agent is a chef who opens the fridge and improvises.
Like this card?
References
Answer: Agents choose their own steps and tools. In a workflow, programmers fix the order of steps in code. An agent is an LLM using tools in a loop, deciding what to do next based on feedback from its environment.
- Anthropic Engineering: Building effective agents www.anthropic.com/engineering/building-effective-agents
Agents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage
Checked 2026-10-10.
Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.
More stuff everyone should know
Artificial IntelligenceIn reinforcement learning, what tells the agent how well an action went?Artificial IntelligenceToolformer taught a language model to call tools. Which weak spots of LMs did that target?Artificial IntelligenceWith function calling, who actually runs a tool that the developer defined?
That's stuff everyone should know.