对话式智能体

The Conversational Agent node runs an LLM-driven turn in a chat conversation, looping through reasoning and tool-calls and streaming them to the chat.

操作

Runs a single turn of a conversational AI agent that you author in the canvas. You configure a model, instructions, and tools, then pass in the conversation context (which includes the chat history) emitted from a Wait for Message node. The agent performs a loop of reasoning and tool-calls, streaming them to the chat.

备注：

The agent can only reply within an exchange that a user has initiated, which means the user must send a message first before a conversational agent node can run. Flow-initiated exchanges — sending a message without a prior user turn — are not yet supported.

何时使用此选项

情况	使用
You need an LLM-driven, streamed conversational response, with possible tool-calls.	对话式智能体
You need a deterministic reply in the conversation (no LLM).	发送消息
You need an LLM-driven execution with possible tool-calls, but without streaming to the conversation.	自主式智能体

备注：

Since the Conversational Agent node streams and appends its response to the chat automatically, you do not need to use Send Message to emit the agent's response to the conversation.

Visit build a chat agent workflow for a step-by-step example that combines Conversational Agent nodes with the other Chat nodes.

添加智能体

添加节点，然后在属性面板中对其进行配置。

1. 选择输出句柄上的+按钮，或从底部工具栏中打开节点面板。
2. Select the Agent category, then Conversational Agent. Flow adds the node and opens its properties panel.
3. Configure the model, system prompt, and the conversation context binding, as described below.

Result: The Conversational Agent node is added to the canvas with its properties panel open, ready to configure.

配置参考

字段	必填	默认	描述
模型	否	组织默认智能体模型	智能体使用的大型语言模型 (LLM)。从选取器中选择一个模型，该选取器列出了您组织可用的模型。
系统提示	是	无	The agent's role and standing instructions: who it is and how it should behave. Applies to every turn of the conversation, so write durable guidance — e.g. persona, tone, goals, and when to call tools.
温度	否	0	采样随机性，从0到1 。值越低，响应的确定性越高；值越高，响应就越多样化或更具创意。
每个响应的最大令牌数量	否	8192	Maximum length of each model response within a turn. The ceiling depends on the selected model.
Conversation context	是	无	The conversation context object — containing the chat history — from an upstream Wait for Message, e.g. $vars.waitForMessage1.output.conversationContext

输出变量

In addition to the agent's conversational response, you may optionally configure structured output variables in the Outputs section of the properties panel.

These outputs are not seen by the user in the chat — instead, they are useful for setting goal-oriented or routing variables to use in downstream nodes within the Flow.

Each output variable you declare becomes a field on the agent's output object, referenced as $vars.<agentName>.output.<name>. Give each one a name and a type, then instruct the agent in the variable's Description field how to populate it.

重要提示：

Generation of the agent's conversational responses is driven by only its system prompt, while generation of the agent's outputs are driven by a combination of its system prompt and the output variable descriptions. To ensure the agent doesn't emit structured output data into the chat, use the system prompt to tell the agent how to respond in the chat, while using the output descriptions to instruct the agent how to fill in the outputs.

例如：

System prompt: "Thank the user when they would like to end the conversation."

Output variable: endConversation (boolean). Description: "Set to true when the user intends to end the conversation."

根据结果创建分支

Follow the agent with a Decision or Switch to route on a structured output field. For example:

Wait for Message → Conversational Agent (supervisor) → Switch on $vars.agent.output.intent
  → 'intent-a':  Route to a loop with specialist conversational agent A
  → 'intent-b':  Route to a loop with specialist conversational agent B
  → 'off-topic': Send Message ("Message is off-topic") → back to first Wait for Message.

资源

A Conversational Agent composes with resource nodes you connect to its handles. The node has three resource handles, each with its own label in the canvas: Tools, Context, and Escalations. Connect a resource to a handle, then configure that resource in its own properties panel. The resources travel with the flow.

每个句柄仅接受其匹配的资源类型。画布会阻止无法容纳的连接，因此您无法将工具连接到上下文句柄。

工具

将工具连接到工具句柄，为智能体提供在推理时可以调用的功能。智能体在其循环中决定是否以及何时调用每个已连接的工具。每个工具都带有描述，告诉智能体该工具的用途，因此请在工具公开时编写清晰的描述。

您可以连接的工具类型包括：

• 内置工具，三个现成的工具，如下所述。
• 连接器工具，使智能体可以调用 Integration Service 操作，例如发送电子邮件或在下游系统中创建记录。
• RPA 工作流和API 函数工具，使智能体可以将已发布的 RPA 流程或 API 工作流作为工具调用。
• 模型上下文协议 (MCP) 服务器工具，公开在 MCP 服务器上发布的工具。

内置工具

Flow 附带三个内置工具。每个都是独立的资源，您可以连接到工具句柄，并在其自己的面板中进行配置。

• 分析文件：使用 LLM 分析一个或多个文件，以提取、合成或回答有关其内容的问题。描述智能体将传递的文件以及要对这些文件运行的分析任务。
• 批量转换：逐行处理和转换 CSV 文件。提供源文件，描述每行的任务，并定义该工具添加的输出列。您可以为转换启用或禁用网页搜索锚定。
• 汇总：生成带有引文的跨文档合成（最多 1,000 页）。提供来源，描述要合成的内容，然后选择文件扩展名。当来源是 PDF 时，您可以打开或关闭引文。

MCP 服务器工具

连接模型上下文协议 (MCP) 服务器，以将其工具公开给智能体。从服务器中选择一个或多个工具时，会在工具选取器下方添加一个“工具配置”部分，每个工具都有一个可展开面板。在该面板中，您可以编辑每个参数的描述，查看工具的完整输入和输出架构，并选择参数获取其值的方式：由智能体在运行时决定；将值绑定到作用域内的智能体变量；或者将值绑定已修复（也可以选择将其标记为敏感）。

MCP 服务器的工具列表可以来自两种发现模式：

• 已缓存: 连接服务器后生成服务器工具的快照。使用服务器上的“刷新”工具按需拉取更新的快照。
  • 默认情况下，工具配置面板中的“调用前刷新架构”切换开关会在每次调用前重新检查服务器中的工具当前架构，因此，无需再更改服务器上的架构（例如，重命名或添加参数）。手动刷新。禁用后，该工具将始终使用上一个快照中的架构。
• 动态：每次调用时在 Runtime 发现工具，包括在配置节点后添加到服务器的工具。

对于远程 MCP 服务器，刷新会轮询服务器的发现端点，以获取异步完成情况。对于平台 MCP 服务器（UiPath 原生服务，例如 Document Understanding），工具列表将来自 UiPath Platform 服务目录。

If no MCP server is connected yet, add one from the node palette's MCP server entry. The Create new options group server creation by subtype — Platform, Remote, Command, Coded, and UiPath. Selecting Platform opens a dialog to create the server within the current solution, when supported by your environment; the other subtypes open the corresponding creation page in Orchestrator. For more details, see About MCP Servers.

备注：

The inline Conversational Agent node does not yet support personal connections, client-side tools, or tool-call confirmations. To use these, build the agent in Agent Builder and import it as a node in your Flow.

Context

将上下文资源连接到上下文句柄，使智能体基于您的数据。智能体在推理时会利用这些基础数据，而不是仅依赖模型。上下文资源指向组织中的上下文索引。

配置智能体从索引中检索的方式，包括检索模式（语义、结构化、DeepRAG 或批量转换）、查询、要返回的结果数量、相关性阈值以及是否包含引文。要创建新的上下文索引，请使用句柄的“添加”面板上的“新建上下文”操作，该操作将在新选项卡中打开索引创建内容。

升级

连接升级句柄，以便在智能体遇到不应该单独决策的案例时路由到人员。智能体暂停，人工处理升级，智能体得出结果继续。您可以附加以下两个升级资源中的任何一个：

• 升级: 路由到 Action 应用任务。配置操作应用程序、收件人、通知、传递给应用程序的输入以及应用程序的结果如何映射回智能体。
• Action 应用升级：路由到编码 Action 应用程序，具有相同的收件人、通知、输入和结果映射配置。

Both escalation resources are configured the same way. Choose Action App Escalation when your escalation target is a coded action app rather than a standard action app.

重要提示：

An escalation from a Conversational Agent blocks the conversation turn — the user is left waiting on the chat surface until the human acts. For long-running approvals or hand-offs where the conversation should keep moving, run a Human Task from a parallel branch instead, so the chat can continue while the approval happens in the background.

常见问题

An input validation error appears before you can debug. The Model, System prompt, and Conversation Context are all required. The node reports a validation error until each one is set.

The chat blocks for a long time after the agent triggers an escalation. Escalations attached directly to the agent pause the entire turn until the human acts. For long-running approvals, move the human step to a parallel Human Task branch that runs alongside the conversation instead.

连接的批量转换工具报告验证错误。批量转换需要至少一个输出列。定义工具在调试流程之前应添加的列。

相关页面

• Wait for Message — provides the conversation context this node consumes.
• Send Message — deterministic (non-LLM) response alternative.
• Chat — full palette of chat conversational nodes.
• Build a chat agent workflow — end-to-end walkthrough that combines a supervisor and specialists.
• Chat deployment — publish and expose the Flow through various channels.
• Autonomous Agent — task-executing LLM-driven loop without streaming to the conversation.