Cheat Sheet
Structure your data with semantics
Just like humans, Super performs better with well-organized documents.
Semantic structure through headings helps understand the information, and that works for AI too. For optimal results, try using semantic headings (H1/H2/H3/H4).
Ask actual questions
Asking instead of searching is something we all need to build a habit on.
If you just type keywords, Super will reformulate it as a question, but you may not get the most relevant information. By formulating your query as a question, you help Super think critically about what it should look for.
Boost keywords with double quotes
Super relies on Search to give you answers. If you know a specific term must appear in the results, you can boost its importance by enclosing it in double quotes:
What is "Super"? By using double quotes, you signal to the system that these words are particularly significant for your query, often leading to more precise and relevant answers.
Avoid too common keywords
This is a counter intuitive tip: often, you shouldn't use the keywords most present in your data such as "{your company name}".
The keyword "{your company name}" is everywhere in your data. Since Super relies on Search for one of its steps, using this keyword might add a lot of noise.
Add instructions after ?
You can specify instructions in Super on how you want the answer to be displayed.
But as a shortcut, you can simply write these instructions after the question mark:
"What is Slite? generate a blog article about it."
Choose Exactly Where Super Searches
You can choose exactly which sources Super should search in. Simply select the documents or folders you want Super to use, and it will generate an answer only from those sources.
