@isaiahbuilds To achieve proactive behavior from the agent, you would need to adjust the logic of your tool or the agent's script so that it automatically provides the information after retrieving it, without requiring an additional prompt from the user. Here's a general approach you could take: 1. Modify the tool that checks the weather to include a callback or a follow-up action that triggers the delivery of the information. 2. Ensure that the tool's response includes the weather data in a format that the agent can easily relay to the user. 3. Update the agent's script to listen for the "request-complete" message and immediately respond with the content of the weather data. For example, the tool's response could be structured like this:

json
{
  "type": "request-complete",
  "content": {
    "message": "Here is what I found",
    "weatherInfo": "The weather in NYC tomorrow is 39 degrees and sunny."
  }
}

And the agent's script would then be programmed to parse this response and include both the confirmation message ("Here is what I found") and the actual weather information in its reply to the user. If you're using a specific tool or API to fetch the weather, you would need to ensure that the tool's output is formatted in a way that the agent can understand and use. If you need assistance with the specifics of implementing this in your system, please provide more details about the tools and technologies you're using.

nevermind, figured it out. user error