Jun 24, 2024 · How does function calling create a "plan"? At its simplest, function calling is merely a way for an AI to invoke a function with the right parameters. Take for example a user wants to turn on a light bulb. Assuming the AI has the right plugin, it can call the …

Jul 13, 2024 · Function Calling belongs to chat completions and lets a model call external tools, functions or APIs based on user input. Doing this optimises the model output and increases the probability of generating more accurate responses.

Jul 23, 2024 · In Semantic Kernel, it’s possible to implement planning logic using FunctionCallingStepwisePlanner class. Today we want to introduce a new way how to achieve the same results by using Automatic Function Calling. This approach produces the results more reliably and uses fewer tokens comparing to FunctionCallingStepwisePlanner.

Dec 22, 2023 · The main difference is that, with function calling, we must call the function on our own, while with the planner, Semantic Kernel was taking care of calling function on our behalf.

May 29, 2024 · You will receive a response from LLM which functions to call (basically a plan), and then you can edit it based on your needs and execute it on your side. The concepts of planner and function calling are very similar. In planner, we ask LLM to generate plan string with functions to execute.

Apr 15, 2024 · You don't necessarily need a plan to make this work, you can add your plugins like you do already and just provide a prompt. With that the LLM will make the proper function calling interactions automatically. Ensure you use the latest OpenAI models that support function calling (after NOV-2023)

May 19, 2024 · In this entry I look at using the Handlebars Planner to accomplish the same functionality. Then I’ll show the request and response JSON for both using a saved plan as well as having the LLM create a plan and end with a token usage comparison. The code for this entry is the HelloWorld.Planner1.Console project in my GitHub repo.

Feb 19, 2025 · Both function calling and tools play crucial roles in enhancing the capabilities of AI agents. Function calling is ideal for scenarios where tasks are specific and well-defined, while tools...

Jul 23, 2024 · In this blog post we’ll cover our current experimental planners and what comes next for the function calling stepwise planner and the Handlebars planner. We’ll answer: How do they work? What are they good at? And how do we plan to make them even better.

Mar 13, 2025 · In short, LLM Agents are modular AI systems capable of complex, multi-step reasoning with memory and planning, while Function Calling is a simpler approach enabling structured interactions between LLMs and predefined external functions or APIs.