| Name | When to use it | How to configure it when building an agent | What the agent will do |
|---|---|---|---|
| Search | To search across various data sources. (Most common method) | Select data from your Folders and Connected Data and describe what it is about. | Perform a semantic search across the selected data to find the most relevant content and generate a response using this context. |
| Include Data | To include data exhaustively. (entire documents) | Select data from your Folders and Connected Data, set a time limit if required, and describe what it is about. | Include as much data as possible - starting with the most recent - until reaching the context window limit or your set limit, and then generate a response using this context. |
| Query tables | To query structured data (Tables, Spreadsheets, DBs). | Select a database from your Folders or Connected Data, created from data warehouses (Snowflake/BigQuery) or CSV files, gsheets, or Notion databases. | Convert the user’s question into an SQL query, run it against the database, retrieve results, and generate a response from this content. Learn more: Table queries |
| Extract Data | To extract structured data from large data sources. | Select data from your Folders or Connected Data and define the desired data schema | Search the selected data and extract information following the defined schema. Learn more: Extract data |
| Find in data sources | To browse and navigate your data sources like a file system, instead of just by search query. | Available together with your Search-enabled Folders and Connected Data, no separate data source selection needed. | Lists folder contents, opens a specific document by its path, locates a document by its title, and reports where a document sits in the folder hierarchy, complementing semantic search for structured, path based lookups. |
Knowledge
Knowledge
Data sources are managed by Builders and Admins of the workspace via Connected Data, Folders and Websites. Knowledge allow the agent to retrieve and use selected data as context to answer questions, using the different methods below: