Would love to be able to let the LLM think more before responding. Any ways to do that? This is one that I requested for the roadmap, please upvote if it sounds good to you: https://vapi.canny.io/feature-requests/p/allow-specifying-partial-llm-output-within-xml-tags-to-use-as-response

Allow specifying partial LLM output within <xml> tags to use as response

It's well known that when LLMs 'think through' something before speaking, it improves the quality of responses.
To facilitate this if you could let us specify to speak only the text within specified XML tags, then we could instruct the LLM to output e.g.:

<thinking>
step 1
step 2
</thinking>
<response>
This is my response
</response>

And speak only:
This is my response