{"slug": "stop-building-chatbots-and-start-building-agentic-workflows", "title": "Stop Building Chatbots and Start Building Agentic Workflows", "summary": "A developer argues that building simple chatbot wrappers around LLMs is a dead end and advocates for agentic workflows instead. By breaking tasks into iterative loops with planning, execution, critique, and refinement, developers can achieve higher quality results, especially for complex tasks like coding. The post provides practical patterns such as self-critique, tool use, multi-agent systems, and structured state management.", "body_md": "Most developers start their AI journey by building a 'wrapper'. You take a user input, wrap it in a system prompt, send it to an LLM, and return the result. If the result is wrong, you try to 'prompt engineer' your way out of it by adding more instructions to that single prompt.\n\nThis is a dead end. No matter how good your prompt is, LLMs struggle with complex tasks in a single pass. They hallucinate, they skip steps, and they fail to double check their own work.\n\nAgentic workflows are different. Instead of one long prompt, you break the task into a loop of smaller, specialized steps where the LLM can reason, act, and correct itself.\n\nIn a standard chatbot, the flow is: User -> Prompt -> LLM -> Output.\n\nIn an agentic workflow, the flow looks more like: User -> Planner -> Executor -> Critic -> Refiner -> Output.\n\nThink of it like a professional software project. You do not just write 1,000 lines of code in one go and push to production. You write a draft, you run tests, you find bugs, and you fix them. That is exactly how you should structure your LLM calls.\n\nThis is the simplest agentic move. You ask the LLM to generate a response, and then you send that response back to the LLM (or a different model) with a prompt like: \"Review the response above for technical errors or missing requirements. List the flaws.\"\n\nOnce you have the critique, you send both the original response and the critique back to the model to generate a final version. This almost always produces a higher quality result than a single prompt, especially for coding tasks.\n\nInstead of hoping the LLM knows the answer, give it tools. A tool is just a function the LLM can choose to call.\n\nThe pattern works like this:\n\nThis prevents the model from guessing. If it needs a current stock price or a specific database record, it fetches it rather than hallucinating a plausible-looking number.\n\nWhen a task is too large, a single agent gets confused. The context window gets cluttered with irrelevant details. The solution is to split the roles.\n\nCreate a 'Manager' agent that breaks the goal into sub-tasks. Then, assign those tasks to 'Worker' agents. For example, one agent handles API documentation, another handles implementation, and a third handles testing. The Manager collects the outputs and ensures they align.\n\nMoving to agentic workflows introduces a new problem: state. You are no longer managing a single request, but a conversation history that includes thoughts, tool outputs, and critiques.\n\nIf you do not manage this carefully, your token costs will explode, or the model will lose the original goal. I recommend using a structured state object (like a JSON store) rather than just appending everything to a chat history string. Keep track of:\n\nStop trying to write the 'perfect prompt'. It does not exist.\n\nIf your LLM is failing at a task, do not add more adjectives to the prompt. Instead, split the task into two steps: one to generate a draft and one to critique it. Then, feed that critique back in for a second pass.\n\nMoving from a linear pipeline to an iterative loop is the single biggest jump in quality you can make in AI development.", "url": "https://wpnews.pro/news/stop-building-chatbots-and-start-building-agentic-workflows", "canonical_source": "https://dev.to/ntty/stop-building-chatbots-and-start-building-agentic-workflows-5be5", "published_at": "2026-07-09 11:00:56+00:00", "updated_at": "2026-07-09 11:11:44.238487+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-tools", "developer-tools"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/stop-building-chatbots-and-start-building-agentic-workflows", "markdown": "https://wpnews.pro/news/stop-building-chatbots-and-start-building-agentic-workflows.md", "text": "https://wpnews.pro/news/stop-building-chatbots-and-start-building-agentic-workflows.txt", "jsonld": "https://wpnews.pro/news/stop-building-chatbots-and-start-building-agentic-workflows.jsonld"}}