You've raised valid points about the cost and efficiency of our approach, which aims to make the LLM function as closely as possible to a human user. We chose this approach primarily for its compatibility with various websites, as it aligns closely with a website's intended audience, which is typically human.

Addressing complex website interactions is a key advantage of this approach. For instance, in the process of generating an auto insurance quote, the sequence of questions and their specifics can vary greatly depending on prior responses. A simple example is the choice of a foreign versus a California driver's license. Selecting a foreign license triggers additional queries about the country of issuance and expiry date, illustrating the complexity and branching nature of such web interactions.

However, we recognize the concerns about cost and are actively working on strategies to reduce it: - Optimizing the context provided to the LLM - Implementing caching mechanisms for certain repeated actions and only use LLMs when there's a problem - Anticipating advancements in LLM efficiency and cost-effectiveness, with the hope of eventually finetuning our own models for greater efficiency