Multifunction Calling using Slack AI Agent > Introduction to Multifunction Calling using Slack AI Agent recipe

Introduction to Multifunction Calling using Slack AI Agent recipe

The Multifunction Calling using Slack AI Agent recipe is based on REST API. Use the recipe to receive user queries from Slack. These queries are then sent to Google Vertex for function calling, which directs the request to the appropriate AI agent. The AI agent analyzes the request, performs the required actions, and returns the result to the Slack channel.

The process begins by receiving user input from Slack and skipping messages if they are bot responses.

The process sends a request to Google Vertex AI with the specified function declaration and user prompt. Google Vertex AI interprets the query, extracts key variables and values, and returns them in the appropriate format. Using the response received from the function calling, a request is then made to the Large Language Model (LLM) to summarize and explain the extracted parameters, and sends the result in the Slack channel.

The process sends a request to the Application Integration process with parameters obtained from the function calling response. The LLM generated response is returned to the user in the same channel, where it appears as a bot or app response.