The process begins with receiving user input from Microsoft Teams and returns a pre-configured answer in the same channel.

The process sends a request to Azure OpenAI containing the specified function declaration and user prompt. Azure OpenAI interprets the query, extracts key variables and values, and returns them in the appropriate format. Based on the function calling response, a request is made to the Large Language Model (LLM) to summarize and explain the extracted parameters, with the result sent back to the Microsoft Teams channel.

The process also sends a request to the Application Integration process with parameters obtained from the function calling response, and calls the appropriate AI agent.

The Agent uses an LLM to generate the initial API request based on the user’s query. After executing the service API call, the Agent evaluates the response received. If additional information is required, the Agent formulates and executes a subsequent service API request, leveraging the previous response as context. This process repeats until the Agent determines that sufficient data has been gathered to address the original query.

Finally, the Agent compiles the accumulated context and uses the LLM to generate a comprehensive final response to the user’s query. This LLM generated response is returned to the user in the same Microsoft Teams channel.