# LangSmith Fleet

## Agents for the whole company

Give every team the ability to build agents, use them in apps they already rely on, and manage them with security and control.

## Helping top teams ship great agents

### Three ways to build, from full harness to full control

Each package solves a different problem. Choose where you want to start, then compose the rest of the stack around it.

### Create specialized agents with chat

Start from a chat or a prebuilt template. Fleet guides you through adding tools, channels, and skills so you can build agents that handle real work without writing code.

[Build your first agent](https://smith.langchain.com/agents?skipOnboarding=true)

### Deploy

Use agents where people work

Fleet agents work inside the tools your team already uses, including Slack, Teams, and Gmail. Ask questions, kick off tasks, and get updates without leaving the flow of work.

[Build your first agent](https://smith.langchain.com/agents?skipOnboarding=true)

### Approve

Require approval for sensitive actions

Keep humans in the loop where it matters. Set tool-level approval requirements so agents check with you before executing sensitive steps. Review, edit, and approve actions with a centralized agent inbox.

[Learn about human approvals](https://docs.langchain.com/langsmith/agent-builder-essentials#human-in-the-loop)

### Connect

Connect your tools securely

Enable first-party integrations, with OAuth for user authentication, and extend agent capabilities with any remote MCP server. Admins control which tools are available.

[See how to add MCP servers](https://docs.langchain.com/langsmith/agent-builder-remote-mcp-servers)

### Scale and manage agents across your org

#### Model neutral

Use your preferred model. Fleet supports OpenAI, Anthropic, Gemini, or a model of your choice.

#### Admin and access controls

Control who can use and edit agents, which credentials they use, and which services they can connect to.

#### Full observability

Monitor agent performance with native tracing in LangSmith. Audit usage, debug issues, and improve reliability.

#### Extend with code

Engineering teams can invoke any agent via API or export agent files for use in pro-code development.

## Get started instantly with prebuilt agents

Choose an agent and customize it for your team.

### General

#### Executive Assistant

Manages your inbox, calendar, and daily brief

### Engineering

#### Software Engineer

Ships code from Slack, Linear, and GitHub in a sandbox

### FAQs for LangSmith Fleet

**Can I add my own tools to Fleet?**  
Yes. You can add custom tools and integrate third-party tools using a hosted MCP (Model Context Protocol) server. See the LangSmith Fleet [docs](https://docs.langchain.com/langsmith/agent-builder-remote-mcp-servers) for setup details.

**Can I use a custom model with Fleet?**  
Yes. You can configure which model your agent uses for inference, including a custom model. See the LangSmith Fleet [docs](https://docs.langchain.com/langsmith/agent-builder-manage-agent-settings#change-the-model) for configuration steps.

**Where is my data stored?**  
LangSmith cloud stores data in secure infrastructure. When using LangSmith hosted at [smith.langchain.com](https://smith.langchain.com/), data is stored in GCP us-central-1 or europe-west4. If you’re on the Enterprise plan, we can deliver LangSmith to run on your Kubernetes cluster in AWS, GCP, or Azure so that data never leaves your environment. For more information, check out our [documentation](https://docs.smith.langchain.com/self_hosting/kubernetes). For teams with compliance requirements, self-hosted and BYOC options let you control where your data lives.

**Can I self-host LangSmith Fleet?**  
Yes, we allow customers to self-host Fleet on our enterprise plan. We deliver the software to run on your Kubernetes cluster, and data will not leave your environment. For more information, check out our [documentation](https://docs.langchain.com/langsmith/architectural-overview).

**Can I use Fleet with LangSmith Observability and Evals?**  
Yes. Every Fleet run is traced in LangSmith, making it easy to debug performance and run evaluations at scale. Learn more about LangSmith [Observability](/content/langsmith/observability/index.html) and [Evaluation](/content/langsmith/evaluation/index.html).

**How much does Fleet cost?**  
See our [pricing page](/content/pricing-langsmith/index.html) for more information, and find a plan that works for you.