Manually emitting messages - Copilotkit

While most agent interactions happen automatically through shared state updates as the agent runs, you can also manually send messages from within your agent code to provide immediate feedback to users.

<video src="https://cdn.copilotkit.ai/docs/copilotkit/images/coagents/emit-messages.mp4" className="rounded-lg shadow-xl" loop playsInline controls autoPlay muted /> <Callout> This video shows the result of npx copilotkit@latest init with the implementation section applied to it! </Callout>

What is this?

In CrewAI, messages are only emitted when a function is completed. CopilotKit allows you to manually emit messages in the middle of a function's execution to provide immediate feedback to the user.

When should I use this?

Manually emitted messages are great for when you don't want to wait for the function to complete and you:

Have a long running task that you want to provide feedback on
Want to provide a status update to the user
Want to provide a warning or error message

Implementation

<Steps> <Step> ### Run and Connect Your Agent to CopilotKit <RunAndConnectSnippet /> </Step> <Step> ### Install the CopilotKit SDK <InstallSDKSnippet/> </Step> <Step> ### Manually emit a message The `copilotkit_emit_message` method allows you to emit messages early in a functions's execution to communicate status updates to the user. This is particularly useful for long running tasks.

    <Tabs groupId="language_crewai-flows_agent" items={['Python']} default="Python" persist>
        <Tab value="Python">
            ```python
            from litellm import completion
            from crewai.flow.flow import start
            from copilotkit.crewai import copilotkit_emit_message # [!code highlight]
            # ...

            @start()
            async def start(self):
                # [!code highlight:2]
                intermediate_message = "Thinking really hard..."
                await copilotkit_emit_message(intermediate_message)

                # simulate a long running task
                await asyncio.sleep(2)

                response = copilotkit_stream(
                    completion(
                        model="openai/gpt-5.4",
                        messages=[
                            {"role": "system", "content": "You are a helpful assistant."},
                            *self.state["messages"]
                        ],
                        stream=True
                    )
                )
                 message = response.choices[0]["message"]

                self.state["messages"].append(message)
            ```
        </Tab>
    </Tabs>
</Step>
<Step>
    ### Give it a try!
    Now when you talk to your agent you'll notice that it immediately responds with the message "Thinking really hard..."
    before giving you a response 2 seconds later.
</Step>

</Steps>