Documentation Index
Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-fjmorr-1778259990-38b7dcc.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
LangSmith Fleet is an enterprise agent platform for building, sharing, and governing agents across your organization. This page compares it with similar platforms to help you choose the right one for your team.
| Platform | Choose if… |
|---|
| LangSmith Fleet | You want to build and share purpose-built agents across your organization, stay model-agnostic, and keep full observability via LangSmith. Fleet is the only option with a self-hosted deployment path and the ability to export agents to code via Deep Agents. |
| Claude Cowork | You want to delegate open-ended tasks to Claude from the desktop for personal knowledge work, and on-device data storage meets your privacy requirements. |
| Amazon Quick | You are already on AWS and want an AI assistant with direct access to your AWS data sources and enterprise integrations. |
| Google Workspace Studio | Your organization runs on Google Workspace and you want no-code agents that work natively inside Gmail, Drive, and Sheets without leaving the Google ecosystem. |
| Microsoft Copilot | Your organization runs on Microsoft 365 and you want low-code agents (via Copilot Studio) that publish natively to Teams and Microsoft 365 Copilot, governed through the Power Platform admin center. |
Compare capabilities
- ❌ Not available
- ⚠️ Partial or limited
- — Not confirmed from public documentation
| Aspect | LangSmith Fleet | Claude Cowork | Amazon Quick | Google Workspace Studio | Microsoft Copilot |
|---|
| Primary use case | Teams building purpose-built agents to share across an organization, with no-code creation and code export for custom deployments; individuals using a general-purpose chat agent for any task | Individual desktop knowledge work | Enterprise AI with AWS data integration | No-code agents for Google Workspace | Low-code agents for Microsoft 365 |
| Model support | Model-agnostic: any LLM with an OpenAI-compatible or Anthropic-compatible API | Claude only | — | Gemini 3 | Curated OpenAI + Anthropic models; bring-your-own via Azure AI Foundry |
| Interface | Web app, Slack app, Teams app, API | Desktop, mobile, Slack, M365 connectors | Web, desktop, browser extensions, Slack, Teams | Web app, Gmail and Chat sidebars | Teams, M365 apps, web, mobile, Windows, Copilot Studio |
| Deployment | Cloud (LangSmith) or self-hosted | Local by default; remote on Anthropic cloud | Cloud (AWS) | Cloud (Google) | Cloud (Microsoft) |
| Self-hosting | ✅ Beta, contact sales for production readiness details | ❌ | ❌ | ❌ | ❌ |
| Code export | ✅ Export to Deep Agents | ❌ | ❌ | ❌ | ❌ |
| Observability | LangSmith tracing and evaluations at scale | OpenTelemetry to SIEM | CloudTrail + run logs | Activity tab + audit logs | App Insights + Purview |
| Platform license | Proprietary | Proprietary | Proprietary | Proprietary | Proprietary |
| Code export license | MIT (Deep Agents) | N/A | N/A | N/A | N/A |
Target users
Fleet covers both org-wide and personal use cases. Teams can build purpose-built agents to share across an organization (for example, a vendor intake agent that serves an entire ops org, or a weekly report agent that saves every account manager thirty minutes on Monday morning), and any user can get help with any task using any tool via Fleet’s general-purpose default chat. Other platforms focus on individual productivity, ecosystem-specific automation, or both, but none combine no-code agent building with org-wide sharing and code export.
Fleet also lets you set tool-level approval requirements so agents check with you before executing sensitive steps, with a centralized inbox for reviewing, editing, and approving actions. No other platform in this comparison offers a single centralized approvals inbox spanning all agents.
Enterprise controls and access
Fleet provides RBAC, attribute-based access control, and per-agent sharing permissions (Clone, Run, and Edit). Among the platforms compared here, only Fleet documents per-MCP-server attribute-based access control. All platforms offer some form of RBAC, but granularity varies.
Fleet manages spending at the workspace level. For enterprise billing options, contact sales.
Model flexibility
Fleet supports any LLM via the OpenAI or Anthropic chat spec, including self-hosted providers, with no ecosystem dependency. Microsoft Copilot offers curated multi-vendor models and a bring-your-own path via Azure AI Foundry, but full flexibility requires Azure infrastructure. Google Workspace Studio and Amazon Quick are more constrained to their respective vendor ecosystems.
Of the platforms compared here, only Fleet works with any OpenAI- or Anthropic-compatible API endpoint regardless of cloud provider.
Memory, self-updates, and learning
Fleet agents can persist context across conversations using a dedicated memory system, and can update their own instructions, add tools, or remove tools as they learn from interactions. Of the platforms compared here, only Fleet documents agent self-modification at runtime.
Observability and governance
Fleet’s clearest advantage is its native connection to LangSmith. Every agent run is traced in LangSmith, making it easy to debug performance and run evaluations at scale. Other platforms offer basic logging and audit trails, but none match Fleet’s depth of LLM-aware tracing, evaluations, and debugging through a dedicated observability platform.
Code export and hosting
Fleet lets you export any agent you build to code via Deep Agents, the open-source agent runtime that Fleet runs on. Exported agents are MIT-licensed and can be deployed independently of Fleet, modified in code, or integrated directly into your own applications via the API. None of the other platforms in this comparison offer a code export path.
Fleet is the only platform in this comparison with a self-hosted deployment option. For teams with compliance requirements, self-hosted and BYOC (bring your own cloud) configurations let you run Fleet entirely within your own infrastructure. All other platforms are cloud-only managed services.
A ✅ indicates the integration is available; supported actions and depth vary by platform. See Fleet tool integrations for the full list of Fleet’s built-in integrations and what each one can do.
| Feature | Fleet | Claude Cowork | Amazon Quick | Google Workspace Studio | Microsoft Copilot |
|---|
| Google Workspace (Gmail, Drive, Sheets, Docs) | ✅ | ✅ | ⚠️ | ✅ | ⚠️ |
| Microsoft 365 (Outlook, Teams, SharePoint, Excel) | ✅ | ✅ | ✅ | ❌ | ✅ |
| GitHub | ✅ | ✅ | ✅ | — | — |
| Slack | ✅ Native | ✅ | ✅ | ⚠️ | ❌ |
| CRM (Salesforce, HubSpot) | ✅ | — | ✅ | ⚠️ | ✅ |
| Project management (Linear, Jira, Notion) | ✅ | ✅ | ✅ | ⚠️ | ⚠️ |
| Custom tools via MCP | ✅ | ✅ | ✅ | ❌ | ✅ |
| Webhooks | ✅ Webhooks | ❌ | ❌ | ⚠️ | ✅ |
Last updated May 5, 2026. These products evolve quickly. If something has changed, please file an issue to help us keep this page current.
