We’ve come a long way in our exploration of language models. In the previous chapter, we learned how to enrich an LLM’s knowledge with virtually any kind of information. It might seem like the final frontier in maximizing the capabilities of language models. However, in this chapter, we’ll go even further, we’ll explore how to use an LLM not just as a source of knowledge but as an engine that controls the execution logic of complex applications. In the previous chapter, we answered the question: how can we enrich an LLM’s knowledge with additional information?