---
title: stack kb agent-builder post-agent-builder-converse-async cli command
description: Send chat message (streaming) Behaviour flags: --dry-run — validate all inputs and exit without performing any action 
url: https://www.elastic.co/elastic/docs-builder/docs/4089/reference/elastic-cli/cli/stack/kb/agent-builder/post-agent-builder-converse-async
applies_to:
  - Elastic Cloud Serverless: Preview
  - Elastic Stack: Preview
---

# stack kb agent-builder post-agent-builder-converse-async cli command
<cli-modifiers>
</cli-modifiers>

```bash
elastic stack kb agent-builder post-agent-builder-converse-async [options]
```

Send chat message (streaming)
**Behaviour flags:**
`--dry-run` — validate all inputs and exit without performing any action

## Options

<definitions>
  <definition term="--execution-mode enum">
    define how to execute the agent (local execution or via task_manager)
    **Values:** local, task_manager
  </definition>
  <definition term="--access-control string">
    Optional conversation access control. Defaults to private.
  </definition>
  <definition term="--action enum">
    The action to perform. "regenerate" re-executes the last round with the original input. Requires conversation_id.
    **Values:** regenerate
  </definition>
  <definition term="--agent-id string">
    The ID of the agent to chat with. Defaults to the default Elastic AI agent.
  </definition>
  <definition term="--attachments string[]">
    Optional attachments to send with the message.
    **Repeatable:** pass `--attachments` multiple times to supply more than one value
  </definition>
  <definition term="--browser-api-tools string[]">
    Optional browser API tools to be registered as LLM tools with browser.* namespace. These tools execute on the client side.
    **Repeatable:** pass `--browser-api-tools` multiple times to supply more than one value
  </definition>
  <definition term="--configuration-overrides string">
    Runtime configuration overrides. These override the stored agent configuration for this execution only.
  </definition>
  <definition term="--connector-id string">
    Optional connector ID for the agent to use for model routing. Mutually exclusive with `inference_id`; omit or use only one.
  </definition>
  <definition term="--conversation-id string">
    Optional existing conversation ID to continue a previous conversation.
  </definition>
  <definition term="--execution-id string">
    Optional client-generated execution ID. Provide it to address this execution later (for example, to abort it). Must be unique; defaults to a server-generated ID.
  </definition>
  <definition term="--inference-id string">
    Optional inference endpoint ID for model routing (public alias for the same internal identifier as `connector_id`). Mutually exclusive with `connector_id`.
  </definition>
  <definition term="--input string">
    The user input message to send to the agent.
  </definition>
  <definition term="--project-routing string">
    Cross-project search routing expression resolved from the header project picker, applied to the run's searches. Serverless (CPS) only; ignored elsewhere.
  </definition>
  <definition term="--prompts string">
    Use this field to respond to a `confirmation`, `authorization`, or `ask_user_question` prompt. Send an `allow` boolean to answer a `confirmation` prompt, an `authorized` boolean to answer an `authorization` prompt, or an `answers` array (one entry per question) to answer an `ask_user_question` prompt.
  </definition>
  <definition term="--read-only">
    When true, the created conversation is presented as read-only in the UI: its history is shown but no message input is offered. This carries no authorization meaning — the conversation can still be continued through the API. This setting is ignored when continuing an existing conversation.
  </definition>
  <definition term="--input-file string">
    path to a JSON file to use as command input
  </definition>
  <definition term="--dry-run">
    validate all inputs and exit without performing any action (preview changes without applying them)
  </definition>
</definitions>


## Global Options

<definitions>
  <definition term="--json">
    output as JSON
  </definition>
</definitions>