Relevance AI's onboarding process includes two main steps.
- Sign up where you create your account on the platform
- Analysing your first dataset through the onboarding wizard
Below is the full description of the process.
- Go to tryrelevance.com and click on Sign up.
- Enter your email address and create a new password and click on Continue.
- You will be directed to a new page to set up your profile. Enter your name, company name, role and set your closest data region (based on your current location).
Now that you have a profile, you're ready to analyze your first dataset!
Through this wizard:
- You will upload your dataset (we recommend reading our guide on Dataset Requirements in advance)
- You will identify the free-text field that you wish to analyse
- AI analysis will identify the themes in your dataset
- You will be directed to Relevance AI's Explorer dashboard - a great place to understand and visualise your data to extract insight
- AI will generate automatically label the themes
- You will be prompted to update names/descriptions if you want to fine tune how they are labelled
- Choose how you'd like to get started. We recommend our 'No Code Flow: Text Analysis'. Click on the box to continue.
- Follow the prompts to complete the onboarding flow. Welcome to Relevance AI!
- Drag and drop your CSV file, read our guide on Dataset Requirements.
- Type in a name for your dataset otherwise the platform uses the same name as the name of the uploaded file.
Specify which field is the Free-Text field that you wish to analyse (e.g. the column in a dataset where comments or reviews are stored).
The platform starts analysing your data. This includes running AI techniques to identify conceptual similarities and grouping entries in the dataset accordingly. You can read more about the AI process here
In the final step, your data is presented in Relevance AI's Explorer dashboard. This dashboard is fully configurable for different personas. And is a great tool for understanding the data, underlying trends and extracting insights.
Here you'll be automatically prompted to use AI to label your top themes.
To continue, click on 'Use AI to label your categories'.
At any stage, you are encouraged to manually label some of the categories to personalise how you would describe a category. Next to the category name, click on the 'pencil' icon and type in how you would label / describe the shown items / responses within that group.
Then click on 'Autolabel AI Categories' to update the labels for all categories. The underlying model can learn your preferred structure for description by seeing a few examples on how you describe a group. This is why you are encouraged to enter a description for two (or so) of the groups/themes/trends.
Check it out!
Updated 18 days ago