Unleash the power of Sana Search, an AI-driven powerhouse designed to swiftly navigate through your content and material on the platform, and deliver precise answers. With a simple prompt, you can tap into the collective knowledge of your organization, spanning the content in your platform. Experience lightning-fast results and intelligent feedback, tailored to your needs. With Sana Search, the information you need is always at your fingertips, fueling productivity and fostering a culture of knowledge sharing.
Using Search & the Assistant
Search
Simply write what you want to know in your own words, and Sana will search for the answer. As you type, relevant courses, articles, or resources will be displayed instantly, providing quick access to the information you're looking for without needing to press Enter.
Just type your prompt in the search bar.
Results will appear immediately—no need to press Enter.
💡 If you press Enter, you’ll enter the assistant chat mode. If you just want to search for results, there’s no need to press enter (see more here)
Sana’s Assistant in Search
Powered by ChatGPT, Sana’s AI assistant is integrated into Search. To use it, follow a similar format to using search by just writing what you want to know in your own words, but this time press Enter and Sana’s AI will provide a result based on your prompt
Type your prompt
Press Enter
And Sana’s AI will get to work
Feel free to converse with the assistant to refine results or get more information.
Initial Search Query
Topic-Based Retrieval: When you enter a search query, the system retrieves relevant courses and sessions tied to the topic, providing the Assistant with focused context. If the content available on the platform doesn't fully address your query, the Assistant will draw on knowledge sourced from ChatGPT to offer additional insights and fill in any gaps. This ensures that responses remain as accurate and comprehensive as possible, even when specific platform content is unavailable.
Follow-Up Questions
Follow-Up Questions: You can ask follow-up questions within the same interaction window. However, the system will only use the documents or courses that have already been retrieved to answer these follow-up questions. This means follow-up questions should relate to the context established by the initial search query.
Asking a New Question
New Query Requirement: For questions that are completely different and unrelated to the initial query, you need to initiate a new search. Update the search bar with your new question to get relevant results. This is because the assistant's responses are based on the context of the previously retrieved documents and courses, and new, unrelated queries require a fresh search.
💡 For more information and tips and tricks for using the assistant click here
Top Tip!
If you want to reference a specific course in Sana, type @ followed by the course name in your prompt
What can I use Search for?
Find course information
Searching for company knowledge in Sana
Look for inspiration to build courses
Answer any question with the AI assistant!
Search transcriptions from Sana Live sessions when smart transcriptions and summaries has been enabled. Never regret not taking notes again.
Who can use Search and the Assistant?
Everyone with a Sana account has access to Search and the Assistant.
However, your search results will only contain information from content you have access to. For example, content you are assigned as a learner or content you have collaborator rights to as an admin
FAQ
How does the search algorithm learn?
We use a dedicated training set of internal data to manually and automatically train our ranking algorithm to find the most relevant matches. No customer data is used, unless specifically agreed upon.
Furthermore, we log the queries asked by users, and how a user interacted with the results or the assistant, so that we can learn to serve the types of queries users need the most in the best way possible.
The Search assistant answer is based on OpenAI's large language models. OpenAI does not train their models on API data.
Will our data go into the model, so others might access it?
OpenAI does not train their models on the data passed through the API. Sana Labs has a Zero Data Retention policy in place with OpenAI, which means that request and response bodies are not persisted to any logging mechanism and exist only in memory in order to serve the request. Source: OpenAI's API data usage policies
Sana does not store the data. We store the user queries to improve our search algorithms and to be able to offer insights to your organization in the future.
No data leaks from one organization to another.
For further information, please find Sana's data privacy documentation below.
Related articles: