LangSmith Fleet ↗

Documentation Index#

Fetch the complete documentation index at: https://docs.langchain.com/llms.txt Use this file to discover all available pages before exploring further.

Create helpful AI agents without code. Start from a template, connect your accounts, and let the agent handle routine work while you stay in control.

Agent Builder is now LangSmith Fleet. All existing agents, configurations, and integrations continue to work. No action is required.

LangSmith Fleet is a no-code platform for creating and managing AI agents. It allows you to create agents from templates, connect your accounts, and let the agent handle routine work while you stay in control.

Use Fleet to:

• Automate everyday tasks like drafting emails, summarizing updates, and organizing information.
• Connect your favorite apps to bring context into your agent’s work.
• Use in chat or where you work (e.g., Slack) to get help in the flow.
• Stay in control with simple approvals for important actions.

Start building#

Pick a ready-made starter (e.g., email assistant or team updates) and customize.

<span class=“card-start” data-card-raw=“title=“Create with AI” icon=“wand”"> Describe your goal in plain English and let AI draft your agent’s configuration. Review and edit before running.

Get started#

Sign up for a LangSmith account.

Start from a ready-to-use template, or describe your goal and let AI draft your agent’s instructions. You can edit details before running. Browse templates.

Securely sign in to the services you want the agent to use.

Run the agent and iterate on its instructions in a few clicks.

Privacy policy and disclaimers#

The LangSmith Fleet App for Slack collects, manages, and stores third-party data in accordance with our privacy policy. For full details on how your data is handled, please see our privacy policy.

Fleet uses the following approach to AI:

• Model: Uses LLMs provided through the LangSmith platform
• Data retention: User data is retained according to LangSmith’s data retention policies
• Data tenancy: Data is handled according to your LangSmith organization settings
• Data residency: Data residency follows your LangSmith configuration

Disclaimers:

• AI-generated content: All responses from agents are generated by AI and may contain errors or inaccuracies. Always verify important information.
• Data usage: Slack data is not used to train LLMs. Your workspace data remains private and is only used to provide agent functionality.
• Transparency: Fleet is transparent about the actions it will take once added to your workspace, as outlined in the permissions section above.

Learn more#

• Essentials: connections, automation, memory, approvals
• Create from a template
• Set up your workspace
• Connect apps and services and use remote connections
• Choose between workspace and private agents
• Authorize accounts when prompted
• Call agents from your app

Self-hosting for Fleet is available in Beta. For more information, see Enable Fleet.

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.