Skip to main content

What are Built-in Tools?

When your agent runs in Agent reasoning mode, it has access to a powerful set of built-in tools. These tools let your agent search knowledge, manage files, remember users, book meetings, capture CRM records, plan complex tasks, and more.
Built-in tools are only available in Agent reasoning mode. Switch your agent’s reasoning mode in Settings → Reasoning.

Available Tools

Knowledge & Research

Your agent can search its training data and capture web pages:

User Memory

When User Memory is enabled, your agent can manage what it remembers about each user:

File Operations

When your agent has access to a Workspace, it can create and manage files:

Planning

For complex tasks, your agent can create structured plans and execute them step by step:
Plans always require your approval before the agent starts executing. This gives you a chance to review, modify, or reject the approach.

Communication

Your agent can interact with users and other agents:

Calendar

When Calendar is enabled, your agent can turn booking intent into a confirmed event:
The booking card waits for visitor input. After a slot is selected, the agent should create the event instead of sending a separate notification as the calendar invite.

CRM

When CRM is enabled, your agent can capture and update lead or customer records:

Code Execution

When your agent has access to a Workspace and Code Sandbox is enabled, it can run code and shell commands:

Automation

Your agent can set up tasks that run on a schedule:

Boost platform tools

The official dashboard assistant, Boost, can use internal BoostGPT platform tools to inspect and configure your agents when you ask it to. These tools are user-scoped and are designed for platform operations such as listing agents, checking setup readiness, enabling CRM/calendar/workspace features, publishing agents, applying templates, and preparing test conversations. Boost will summarize changes before using tools that alter user-facing behavior.

Reasoning

Your agent has an internal thinking tool:

Tool Approval Levels

Built-in tools have approval levels that control when your agent needs permission or visitor input:

Best Practices

  • Use Agent reasoning mode for tasks that require multiple tools (research + writing, reading + editing)
  • Let your agent create plans for complex multi-step tasks — review the plan before approving
  • Enable User Memory for agents with repeat users to provide personalized experiences
  • Enable CRM and Calendar for front office agents that should capture leads and book meetings
  • The Ask User tool is great for gathering requirements before the agent starts working
  • Use Schedule Task for automated monitoring, reporting, or maintenance workflows

Next Steps

Workspaces

Learn about your agent’s sandbox file system

User Memory

How your agent remembers users across conversations

Training Your Agent

Teach your agent what it needs to know

Technical Reference

Detailed parameter schemas for developers