设计复杂工作流
为复杂任务设计包含多个智能体、工具和决策点的精密自主工作流
设计复杂工作流 是 CoddyKit 上的免费 AI Agents with LangChain & Autonomous Workflows 课时。 这是第 1 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 AI Agents with LangChain & Autonomous Workflows 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 AI Agents with LangChain & Autonomous Workflows 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
Beyond Simple Linear Chains
So far, we've built agents that follow a straightforward path. But real-world tasks are rarely simple!
Complex workflows allow your AI agents to handle intricate problems by combining multiple steps, making decisions, and coordinating different AI capabilities.
The Workflow Conductor
Think of a complex task like writing a research paper. It involves many steps:
- Researching topics
- Finding relevant sources
- Summarizing information
- Drafting sections
- Reviewing and editing
Each step might need different tools or even different specialized agents. Orchestration is about making these steps work together seamlessly.
Building Blocks for Intricate Tasks
Designing complex workflows means thinking about how to combine:
- Agents: Specialized for different sub-tasks.
- Tools: External actions agents can perform.
- LLMs: The brain for reasoning and generation.
- Decision Points: Logic to choose the next step or agent.
- Memory/State: How information flows between steps.
These elements are combined to create powerful, multi-stage processes.
Guiding the Workflow Path with Routers
A crucial part of complex workflows is the decision point, often implemented using a router.
A router analyzes the current input or intermediate result and decides which path the workflow should take next. This allows for dynamic, adaptive behavior.
For example, if a user asks for 'weather,' route to a weather tool. If they ask for 'news,' route to a news agent.
Router in Action: A Simple Example
A router directs your workflow by making decisions based on the input. Here's a simple Python function that acts as a conceptual router, directing queries to different 'handlers' based on keywords.
Try changing the input query to see how it routes!
def route_query_to_handler(query: str) -> str:
"""
Simulates a router that directs a query to a specific handler
based on its content.
"""
query_lower = query.lower()
if "weather" in query_lower:
return f"Routing to Weather Tool for: '{query}'"
elif "news" in query_lower:
return f"Routing to News Agent for: '{query}'"
elif "calculate" in query_lower or "math" in query_lower:
return f"Routing to Calculator Tool for: '{query}'"
else:
return f"Routing to General LLM for: '{query}'"
# Main entry point for demonstration
if __name__ == "__main__":
print(route_query_to_handler("What's the weather like today?"))
print(route_query_to_handler("Tell me the latest tech news."))
print(route_query_to_handler("Can you calculate 5 + 7?"))
print(route_query_to_handler("Hello, how are you?"))Keeping Context Across Steps
In a complex workflow, you often need to carry information from one step to the next. This is called managing state or context.
For example, an agent might extract key entities from a document, and then a subsequent step uses those entities to perform a web search.
LangChain helps by allowing you to define how outputs of one runnable become inputs for the next, often through dictionaries or specific input/output schemas.
Agents Working Together
Complex problems can be broken down into smaller tasks, each handled by a specialized agent.
- An "Editor Agent" might refine text.
- A "Data Agent" might retrieve information.
- A "Planner Agent" might decide the overall sequence.
The workflow orchestrator ensures these agents receive the correct inputs and their outputs are correctly processed for the next stage.
Case Study: Research & Report Workflow
Let's design a workflow to generate a report on a given topic:
- Input: User provides a topic.
- Step 1 (Research Agent): Gathers relevant articles.
- Step 2 (Summarizer Agent): Processes findings, identifies key points.
- Step 3 (Drafting Agent): Writes an initial report draft.
- Step 4 (Reviewer Agent): Critiques the draft.
- Step 5 (Editor Agent): Applies improvements, finalizes report.
- Output: A polished report.
Mapping Out the Orchestration
When designing, it's helpful to visualize the flow. Imagine arrows connecting steps:
- User Query → Research Agent
- Research Agent Output → Summarizer Agent
- Summarizer Agent Output → Drafting Agent
- Drafting Agent Output → Reviewer Agent
- Reviewer Agent Feedback + Drafting Agent Output → Editor Agent
- Editor Agent Output → Final Report
Each arrow represents data flow and a potential decision point (implicitly, 'next step').
Workflow Decision Time
Consider a complex workflow designed to assist with customer support. It needs to either answer common FAQs or escalate to a human agent for complex issues.
Orchestrating Intelligence
You've learned how to think about designing complex AI agent workflows!
We covered the importance of orchestration, key components like routers for decision-making, managing state, and how multiple agents can collaborate on sophisticated tasks.
The ability to architect these intricate flows is key to building truly intelligent and autonomous applications.
常见问题解答
「设计复杂工作流」课时是免费的吗？
是的 — 「设计复杂工作流」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 AI Agents with LangChain & Autonomous Workflows 课程的其余内容，请升级到 CoddyKit PRO。 AI Agents with LangChain & Autonomous Workflows 课程共包含 4 节课。
「设计复杂工作流」这节课中我会学到什么？
为复杂任务设计包含多个智能体、工具和决策点的精密自主工作流 你通过在浏览器中直接运行的动手代码来练习 AI Agents with LangChain & Autonomous Workflows，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 AI Agents with LangChain & Autonomous Workflows 需要有经验吗？
无需任何先前经验。CoddyKit 上的 AI Agents with LangChain & Autonomous Workflows 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 1 节课，共 4 节。
「设计复杂工作流」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 AI Agents with LangChain & Autonomous Workflows 课中编写并运行代码吗？
能。每节 AI Agents with LangChain & Autonomous Workflows 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。