Here’s how to use OpenAI’s new o1 pro model to maximize coding productivity. I’ve used this workflow for the last 48hrs and I estimate it has 2x’d my output. Watch the full 19min tutorial. Prompt below.

Actual workflow demo at start. 17:00ish for tool stack. Here’s the full o1 XML prompt: — You are an expert software engineer. You are tasked with following my instructions. Use the included project instructions as a general guide. You will respond with 2 sections: A summary section and an XLM section. Here are some notes on how you should respond in the summary section: - Provide a brief overall summary - Provide a 1-sentence summary for each file changed and why. - Provide a 1-sentence summary for each file deleted and why. - Format this section as markdown. Here are some notes on how you should respond in the XML section: - Respond with the XML and nothing else - Include all of the changed files - Specify each file operation with CREATE, UPDATE, or DELETE - If it is a CREATE or UPDATE include the full file code. Do not get lazy. - Each file should include a brief change summary. - Include the full file path - I am going to copy/paste that entire XML section into a parser to automatically apply the changes you made, so put the XML block inside a markdown codeblock. - Make sure to enclose the code with ![CDATA[__CODE HERE__]] Here is how you should structure the XML: <code_changes> <changed_files> <file> <file_summary>**BRIEF CHANGE SUMMARY HERE**</file_summary> <file_operation>**FILE OPERATION HERE**</file_operation> <file_path>**FILE PATH HERE**</file_path> <file_code><![CDATA[ __FULL FILE CODE HERE__ ]]></file_code> </file> **REMAINING FILES HERE** </changed_files> </code_changes> So the XML section will be: ```xml __XML HERE__ ``` [[PUT CURSOR RULES HERE]] [[PUT YOUR INSTRUCTIONS HERE]]

Here’s the video on YouTube for a slightly longer version with tool links in description. Also worth noting the simplicity of the example is because it’s a workflow tutorial. o1 pro can handle much more advanced requests.

It’s also quite evident to me that there is significant opportunity to truly push the edge and build/optimize AI coding workflows that are far better than median ones. Workflows like this will require work. You can’t just lazyprompt or tab tab tab. But the rewards are great.

Just in case it’s not clear in the video (I try and show the official site a few times) the context tool I’m using in the video is Repo Prompt by @pvncher

Best test so far that this workflow is *actually* good is that I’ve been wayyyy less productive today due to the OpenAI outage.

I am hoping during the 12 days of openAI they announce an IDE that supports o1 pro. Cause as much as this workflow works and is amazing it shouldn’t require the middleware.

It will get much simpler once it hits API. Direct integration into Cursor is the dream.

Thank you so much Mckay for this detailed video explaining everything about the workflow and how to execute everything. I really loved that XML tool 👀 will this be out for other people?

Yes the XML parse-and-apply tool is public on my GitHub right now

I'm skeptical, but a 2x productivity boost is too enticing to ignore. Watching the tutorial now, thanks for sharing!

It is genuinely incredible if used correctly. Worth trying to optimize for it.