diff --git a/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx b/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx
index 98710964..739e99b6 100644
--- a/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx
+++ b/fern/pages/text-generation/prompt-engineering/prompting-command-r.mdx
@@ -196,15 +196,7 @@ Below is a detailed look at the fully rendered prompt for Augmented Generation.
 > <b><span class="green-text">## Basic Rules</span></b>  
 > <b><span class="green-text">You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.</span><br /><br /><span class="dark-purple-text"># User Preamble</span></b>  
 > <b><span class="purple-text">## Task and Context</span></b>   
-> <b><span class="purple-text">You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.</span><br /><br /><span class="dark-sangria-text">## Style Guide</span></b>  
-> <b><span class="dark-sangria-text">Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.</span><span class="brown-text">\<|END_OF_TURN_TOKEN|></span><span class="brown-text">\<|START_OF_TURN_TOKEN|></span><span class="dark-orange-text">\<|USER_TOKEN|></span>Where do the tallest penguins live?<span class="brown-text">\<|END_OF_TURN_TOKEN|></span><span class="brown-text">\<|START_OF_TURN_TOKEN|></span><span class="dark-orange-text">\<|SYSTEM_TOKEN|></span><span class="orange-text"><span class="dark-red-text">\<results></span></b>  
-> <b><span class="dark-red-text">Document: 0</span></b>  
-> <b><span class="dark-red-text">title: Tall penguins</span></b>  
-> <b><span class="dark-red-text">snippet: Emperor penguins are the tallest growing up to 122 cm in height.<br /><br />Document: 1</span></b>  
-> <b><span class="dark-red-text">title: Penguin habitats</span></b>  
-> <b><span class="dark-red-text">snippet: Emperor penguins only live in Antarctica.</span></b>  
-> <b><span class="dark-red-text">\</results></span><span class="brown-text">\<|END_OF_TURN_TOKEN|></span><span class="brown-text">\<|START_OF_TURN_TOKEN|></span><span class="dark-orange-text">\<|SYSTEM_TOKEN|></span><span class="dark-pink-text">Carefully perform the following instructions, in order, starting each with a new line.</span></b>  
-> <b><span class="dark-pink-text">Write 'Grounded answer:' followed by a response to the user’s last input in high quality natural english. Use square brackets to indicate a citation from the search results, e.g. "my fact [0]" for a fact from document 0.</span><span class="brown-text">\<|END_OF_TURN_TOKEN|></span><span class="brown-text">\<|START_OF_TURN_TOKEN|></span><span class="dark-orange-text">\<|CHATBOT_TOKEN|></span>"""</b>
+