Tables

Tables — referred to internally as datagrids — are structured data stores that AI agents can query and populate during conversations. Unlike a Knowledge Base, which stores free text for semantic search, a table stores data in columns and rows with defined types, like a lightweight database directly accessible by the agent. The same records can be displayed as a Table or a Kanban board. When a Select column is used to group the board, each option becomes a stage. This makes it possible to build reusable CRMs, pipelines, and visual workflows without creating a separate data store.

Core Concepts

Concept	Description
Table (Datagrid)	A data structure with named and typed columns, organized into rows. Each table belongs to a workspace and can be connected to one or more agents.
Column	Defines a field in the table. Each column has a name, description, data type (`String`, `Number`, `Boolean`, `File`, or `Select`), and optional settings such as semantic search and required field.
Row	A record in the table. In the Kanban view, each row is displayed as a card.
Select	A field with predefined options. Each option has a label, color, and position and can represent a category, priority, owner, or process stage.
Kanban Configuration	Defines which Select column creates the stages, which field is used as the card title, and which additional fields appear on cards.
Datagrid Tool	A capability made available to the agent for interacting with the table. The available actions are: `semantic_search`, `similarity_search`, `insert_row`, and `update_row`. Each action is activated individually per table.
Column Semantic Search	When enabled on a `String` column, values are vectorized using the `text-embedding-3-small` model (1,536 dimensions) and indexed for similarity search — the agent finds rows by meaning, not just exact match.

Why Tables Matter

Real-time data without external integration: the agent accesses tables directly during a conversation. No webhooks, APIs, or integrations need to be configured for the agent to query a product catalog or register a lead.
Separation of structured and unstructured knowledge: Knowledge Bases are ideal for free text — manuals, policies, FAQs. Tables are ideal for data with a defined structure — catalogs, schedules, inventories, records. Using each resource for what it was designed for improves agent accuracy.
Writing during the conversation: unlike Knowledge Bases (read-only for the agent), tables allow the agent to insert and update data in real time — the agent collects information from the user and records it in a structured way in the table, without human intervention.
Updates independent of the prompt: data changes in the table without needing to edit the agent prompt. A price updated in the table is immediately available for the agent on the next query.
Reusable visual workflows: the same table can support sales, support, recruiting, project management, or any other stage-based process.

Typical use cases where tables outperform other approaches:

Product catalog with price, availability, and description
Professional or event schedule with time slots and vacancies
Lead records collected during conversations
Inventory with real-time quantity tracking
Sales CRM with stages such as New lead, Qualified, Proposal, and Won
Support queue with Open, In progress, and Resolved stages

Create a Kanban view

Configure a Select column and organize table records as cards grouped by stage.

Agents

Squads

Tools

MCPS

Workflows

Inbox

Workers

Channels

Knowledge Base

Settings

Tables — Overview

Core Concepts

Why Tables Matter

Create a Kanban view

​Core Concepts

​Why Tables Matter

Create a Kanban view

Core Concepts

Why Tables Matter