> For the complete documentation index, see [llms.txt](https://docs.wem.io/platform/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.wem.io/platform/wemmodeler/agentic-ai/ai-flowchart-nodes.md).

# AI Flowchart Nodes

## The AI agent conversation node ![](https://1449034948-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-L_NpOsk0sjotPXNy29Q%2Fuploads%2FAJNXS5kJVKgQRdp4XFnt%2Fimage.png?alt=media\&token=0b557730-2573-4745-8691-22a928d7d743)

The actions that let a flowchart talk to an AI Agent: Create conversation, Invoke agent, and Send message, live under a single **AI agent conversation** node. Dragging this node from the Nodes palette, or dragging an AI Agent directly from the AI agents hub onto the flowchart, both place the same node and give you the same choice of action.

When the **AI agent conversation** node is dropped onto a flowchart, it gives three options:

* **Create conversation:** required the first time a user interacts with an Agent. Sets up the conversation between user and Agent.
* **Invoke agent:** triggers the AI agent to act on a prompt without requiring a user-facing chat box, allowing flowcharts to drive agent activity directly. Useful for back-end processing, data analysis, or automated decision-making.
* **Send message:** sends a prompt or message to an Agent without the user's interaction. This can also be used to invoke an Agent's function.

### Create conversation (Start Agent)![](https://1449034948-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-L_NpOsk0sjotPXNy29Q%2Fuploads%2FCBJLHbDVpl2EKXrokxuJ%2Fimage.png?alt=media\&token=d5eb95d8-9db4-4bed-a173-e5cf307b2620)

Creating a conversation is essential the first time a user interacts with an Agent. This conversation establishes the conversational context using the context fields from the Agent's properties, which can be set as part of the Create conversation node. Each time a conversation is created, it is specific to that user when the user returns, the conversation needs to be started up again, but it reuses the same context.

**Properties**

<table><thead><tr><th width="220">Name</th><th>Description</th></tr></thead><tbody><tr><td><code>Conversation ID</code></td><td>Stores the created conversation's ID, so it can be used to return to this conversation or referenced in the other AI nodes and components.</td></tr><tr><td><code>Assign Context</code></td><td>Opens the Assign context overlay, where you set the values of the Agent's conversational context fields. Use it to pass in the record, user, or session-specific data this conversation needs; for example a customer ID or case number, instead of hardcoding it into the Agent's or sending it through the agent chat. </td></tr></tbody></table>

**Exits**

* **Default:** used when the conversation is successfully created.
* **Error:** used when issues arise during creation.

### Invoke agent ![](https://1449034948-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-L_NpOsk0sjotPXNy29Q%2Fuploads%2FsXlLLQ9PsRpWgF19vkgo%2Fimage.png?alt=media\&token=da691d4a-b700-48d6-bb5b-89ec424bf246)

The Invoke agent option sends a prompt to an AI agent and triggers it to act on that prompt, without needing a chat box or any direct user interaction. Where Send message is typically tied to a user-driven conversation, Invoke agent is used by the application itself to drive the agent: useful for processing data in the background, asking the agent to summarise or classify content, calling agent functions on demand, or chaining agent activity into longer workflows.

The node can run both synchronously, waiting for the agent's response and mapping it back to fields in the data model before the user can interact again. Or asynchronously, firing the prompt and continuing the flowchart immediately, where the execution of an agent function flow is the response.

**Properties**

<table><thead><tr><th width="220">Name</th><th>Description</th></tr></thead><tbody><tr><td><code>Conversation ID</code></td><td>The conversation the prompt should be sent to. Either an <strong>AI agent conversation</strong> field or a text field containing a conversation ID.</td></tr><tr><td><code>Prompt</code></td><td>The text instruction sent to the agent. Static text describing what you want the agent to do (e.g. "Summarise the case notes and assign a priority") and how to behave in answers. Because this is static text, it protects the conversation from prompt injection through user input.</td></tr><tr><td><code>Edit payload</code></td><td>Attaches structured data to the prompt as JSON, using the same overlay as the import/export JSON wizard. Useful when the agent needs to act on specific records or values without embedding them in the prompt text.</td></tr><tr><td><code>Attach files</code></td><td>Attaches files from the application (uploaded documents, generated PDFs) to the invocation. The agent can read or reference these in addition to any persistent file sources configured on the agent.<br>This will only be visible for agents that support file processing. </td></tr><tr><td><code>Wait for response</code></td><td>When enabled, the application pauses on this node until the agent responds, and the response can be used immediately by the rest of the flow. When disabled, the prompt is sent asynchronously and the flow continues without waiting. Keep this toggled off for fire-and-forget tasks where the user shouldn't have to wait.<br>When this is enabled make sure the user knows it is working and waiting for a response. </td></tr></tbody></table>

**Exits**

* **Default:** used when the message is successfully sent and a response is received.
* **Error:** used when issues arise during the message sending process.

### Send message ![](https://1449034948-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-L_NpOsk0sjotPXNy29Q%2Fuploads%2FZ0kjBTDUcDhQT4YLY7f4%2Fimage.png?alt=media\&token=86904bd2-d678-4c36-bede-15e69670d582)

Send message is used when the application needs to send a message to the Agent, or invoke a function on the Agent, without requiring user interaction. This option interacts with the Agent within an already-established conversation. This means this node can only be used after a create conversation node, as it always needs a active conversation to work.&#x20;

**Properties**

<table><thead><tr><th width="220">Name</th><th>Description</th></tr></thead><tbody><tr><td><code>Conversation ID</code></td><td>The conversation the message should be sent to. Either an <strong>AI agent conversation</strong> field or a text field containing a conversation ID.</td></tr><tr><td><code>Message</code></td><td>The text of the message to be sent to the Agent. This can be a text string or a function resulting in a text. </td></tr><tr><td><code>Attach files</code></td><td>Attaches files from the application (uploaded documents, generated PDFs) to the invocation. The agent can read or reference these in addition to any persistent file sources configured on the agent.</td></tr><tr><td><code>Wait for response</code></td><td>When enabled, the application pauses on this node until the agent responds, and the response can be used immediately by the rest of the flow. When disabled, the prompt is sent asynchronously and the flow continues without waiting. Use this for fire-and-forget tasks where the user shouldn't have to wait.</td></tr><tr><td><code>Response Message</code></td><td>The data model field that captures the Agent's response, so it can be processed in the rest of the flowchart.</td></tr></tbody></table>

**Exits**

* **Default:** used when the message is successfully sent and a response is received.
* **Error:** used when issues arise during the message sending process.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.wem.io/platform/wemmodeler/agentic-ai/ai-flowchart-nodes.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
Name	Description
`Conversation ID`	Stores the created conversation's ID, so it can be used to return to this conversation or referenced in the other AI nodes and components.
`Assign Context`	Opens the Assign context overlay, where you set the values of the Agent's conversational context fields. Use it to pass in the record, user, or session-specific data this conversation needs; for example a customer ID or case number, instead of hardcoding it into the Agent's or sending it through the agent chat.
Name	Description
`Conversation ID`	The conversation the prompt should be sent to. Either an AI agent conversation field or a text field containing a conversation ID.
`Prompt`	The text instruction sent to the agent. Static text describing what you want the agent to do (e.g. "Summarise the case notes and assign a priority") and how to behave in answers. Because this is static text, it protects the conversation from prompt injection through user input.
`Edit payload`	Attaches structured data to the prompt as JSON, using the same overlay as the import/export JSON wizard. Useful when the agent needs to act on specific records or values without embedding them in the prompt text.
`Attach files`	Attaches files from the application (uploaded documents, generated PDFs) to the invocation. The agent can read or reference these in addition to any persistent file sources configured on the agent. This will only be visible for agents that support file processing.
`Wait for response`	When enabled, the application pauses on this node until the agent responds, and the response can be used immediately by the rest of the flow. When disabled, the prompt is sent asynchronously and the flow continues without waiting. Keep this toggled off for fire-and-forget tasks where the user shouldn't have to wait. When this is enabled make sure the user knows it is working and waiting for a response.
Name	Description
`Conversation ID`	The conversation the message should be sent to. Either an AI agent conversation field or a text field containing a conversation ID.
`Message`	The text of the message to be sent to the Agent. This can be a text string or a function resulting in a text.
`Attach files`	Attaches files from the application (uploaded documents, generated PDFs) to the invocation. The agent can read or reference these in addition to any persistent file sources configured on the agent.
`Wait for response`	When enabled, the application pauses on this node until the agent responds, and the response can be used immediately by the rest of the flow. When disabled, the prompt is sent asynchronously and the flow continues without waiting. Use this for fire-and-forget tasks where the user shouldn't have to wait.
`Response Message`	The data model field that captures the Agent's response, so it can be processed in the rest of the flowchart.