AI Prompt Best Practices

I’m hoping we can start a thread of best practices for using AI in Coda when referencing columns or tables to get the sought-after response? Prompting seems to work a little differently than ChatGPT given that we can include variables in the prompt.

I’ve been having issues getting the results I’m looking for when prompting the AI to generate a result based on content in column X under the contents related description in column Y. I’ve been able to get some results when only providing it with one reference formula to look at.

Anyone else have best practices they want to share in this thread?


I’m biased, but this is based on our team’s approach to establishing prompt practices, design, and testing.


This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.