Workflow and analysis FAQs


Do I need to rerun the analysis every time I add a new data source?

When new entries are added to your dataset or existing data is edited in fields that have been used for any analysis, you will need to rerun the workflows, so that the new items or the updates are included in the analysis.

Do filters slow down the process?

No, filters are quick to run.

About Clustering

How data is clustered at Relevance AI? / Who does the data categorization?

We use famous and commonly used AI techniques proposed for clustering data and combine them with vector analysis.

Can we edit cluster names/labels?

Yes. Labels are cluster ids (e.g. cluster_1) by default. However, on the Explorer app, they can be changed manually or generated based on the values within the cluster using AI.

Can I filter clusters by sentiment?

Yes, it is possible to filter data based on any field values or categorize data based on categorical fields.

About Vectorizing

Can I apply filters before vectorizing, so vectors are generated for only a subset?

Yes, this is specifically very easy from the SDK side.

About Sentiment

Can I manually change the sentiment analysis results?

Yes, values can be modified on the Dataset view page or under the SDK.