Skip to main content
Resources give your Agent access to your organization’s data—CRM records, knowledge bases, product databases, and more. This is called RAG (Retrieval-Augmented Generation): the Agent retrieves relevant information before generating responses. Resources configuration
Without resources, an Agent only knows what’s in its instructions and what it can find via web search. Resources ground the Agent in your data.

​
Types of resources

There are two types of resources you can connect to your Agent:
TypeData formatExamples
ModelsStructured dataCRM objects, product databases, SQL tables
FilesUnstructured dataPDFs, documents, transcripts, knowledge articles

​
Models

Models connect your Agent to structured data—tables with rows and columns. The Agent queries this data using SQL, making it ideal for filtering, sorting, and aggregating records. Best for:
  • CRM Objects (HubSpot Deals, Salesforce Accounts, Attio Records)
  • Product Data (usage databases, analytics platforms)
  • Custom Databases (BigQuery, Snowflake)

​
Files

Files connect your Agent to unstructured data—documents, PDFs, and text content. You select which files or folders to include, and the Agent searches this content using vector similarity to find relevant information. Best for:
  • Knowledge Bases (Notion, Google Docs, uploaded files)
  • Playbooks, FAQs, and process documentation
  • Meeting transcripts and call notes

​
Configuring a Model

When you add a Model resource, you configure how the Agent queries your structured data.

​
Query mode

Choose how the Agent retrieves data from this model:
ModeDescriptionBest for
SQLAgent generates and executes SQL queries against the dataFiltering, sorting, aggregating records
VectorAgent uses semantic similarity search to find relevant text chunksSearching text fields, finding conceptual matches
SQL example:
“Find all deals in the Discovery stage with value over $50k”
Vector example:
“Find companies with product descriptions similar to AI automation”

​
Model settings

SettingDescription
ModelWhich data object to query (e.g., HubSpot Deals, a SQL table)
PromptCustom instructions for how the Agent should query this resource
FiltersRestrict which records the Agent can access
Selected ColumnsChoose which fields to return (SQL mode only)
LimitMaximum number of records returned per query

​
Configuring Files

When you add a File resource, you select the content the Agent can search.

​
Selecting content

Choose which files or folders to include. The Agent will search all selected content using vector similarity to find relevant information.

​
Prompt

Add custom instructions to guide how the Agent interprets or prioritizes this content. Example: 
This folder contains our sales playbooks. Prioritize the
objection handling guide when the user asks about pricing concerns.

​
Best practices

Start with filters

Narrow down data access to what the Agent actually needs. Less noise = better reasoning.

Write clear prompts

Help the Agent understand how to query your data and what matters most.

Choose the right query mode

For Models, use SQL for filtering and aggregating, Vector for semantic search.

Test before deploying

Run test prompts to verify the Agent retrieves the right data.

​
Learn more

Data models

Learn how to build and manage structured data models.

Files

Work with documents, PDFs, and unstructured content.