How Salesforce standardizes agent evals with LangSmith
Ben Sklar
Director of Product Management, Salesforce
Watch full video
Enterprise
The enterprise platform for the full agent development lifecycle
Most enterprise AI initiatives stall before reaching customers. LangChain provides a single platform to build, evaluate, deploy, monitor, and iterate on your agents.
.svg)
Three ways to build,
from full harness to full control
Each package solves a different problem. Choose whereyou want to start, then compose the rest ofthestack around it.
Full Control
Own your AI stack
Build agents with the models, infrastructure, and tools that fit your business, while keeping control over the intelligence layer that differentiates your products and services.
Shared Standards
Standardize agent development
Align teams around a shared development lifecycle so they can reuse best practices, cut duplicated work, and collaborate with subject matter experts.
Faster Shipping
Move faster from pilot to production
Turn promising AI experiments into production agents faster, with built-in support for evaluation, deployment, and continuous improvement.
Built-in Governance
Scale AI responsibly
Grow agent adoption while supporting security and compliance programs with built-in role-based access control, audit trail, and sensitive data protection.
Iterate
LangSmith Engine
Build
deepagents
langchain
langgraph
LangSmith Fleet
Test
Datasets
Evals
Experiments
Monitor
Tracing
Dashboards
Online Evals
User Feedback
Deploy
Runtime
Agent Server
Sandboxes
Context Hub
Traces
SmithDB
Govern
LLM Gateway
One platform for the entire agent lifecycle
Iterate
Use production signals for root-cause analysis and continuous agent improvement.
Test
Validate behavior before deployment with traces, datasets, and evaluations that make quality measurable and repeatable.
Deploy
Run agents on secure infrastructure built for long-running tasks, persistent state, and reliability.
Govern
Set policies for sensitive data, retention, auditability, and model usage across your AI applications.
Monitor
Track quality, cost, latency, and reliability with dashboards, alerts, and online evaluations.
Build
Standardize how teams build agents, with the flexibility to choose the right models, architecture, and level of abstraction for each use case.
Govern data and LLM spend
Sensitive Data Management
Limit access to PII in-platform with ABAC, and redact sensitive data before it's sent to model providers.
Data Retention
Configure custom data retention policies at the project or workspace level to meet data privacy requirements.
Audit Trail
Stay prepared for security and compliance reviews by maintaining an immutable record of every user action.
Cost Controls
Monitor and set limits on evaluator and model spend, so teams can manage costs centrally.
Compliance and controls for enterprise teams
Infrastructure
choice
choice
SaaS with data residency in the US, Europe, and APAC
Bring your own cloud
Self-hosted deployment
Identity
& access control
& access control
SSO / SAML
RBAC / ABAC
SCIM + more
A team that helps you deploy and scale
[1]
Dedicated escalation
Page LangChain engineers directly on your highest-severity issues.
[2]
Custom SLAs
Agreed targets for uptime, latency, and support response.
[3]
White-glove onboarding
One-on-one setup for SSO, access controls, and data retention.
[4]
Recurring support reviews
Ticket and SLA reviews, plus advance notice of releases.
Learn how enterprises run agents in production
How Salesforce standardizes agent evals with LangSmith
Read Use Case
How Salesforce standardizes agent evals with LangSmith
Read Use Case
Enterprises
How ServiceNow built a GTM orchestration layer with LangChain and LangSmith
Read Use Case
How ServiceNow built a GTM orchestration layer with LangChain and LangSmith
Read Use Case
How ServiceNow built a GTM orchestration layer with LangChain and LangSmith
Mili Merchant
Staff Poduct Manager, Enterprise AI
Watch full video
Enterprises
Common questions from security and teams
Is our trace data used to train models?
No. LangChain commits that it will not train on your data, and you own all rights to it. Retention windows are configurable and PII masking can hide sensitive fields before they reach LangSmith servers.
What security certifications do you hold?
LangSmith is SOC 2 Type 2 and ISO 27001 certified, GDPR compliant, and HIPAA compliant. Audit reports, penetration test summaries, and a pre-signed DPA are available through the Trust Center (trust.langchain.com).
Are we locked into the LangChain frameworks?
No. LangSmith is framework-agnostic and built on open standards, so your AI strategy is never tied to a single stack. You can trace langgraph, langchain, or deepagents, or integrate any stack via the Python, TypeScript, Go, and Java SDKs or OpenTelemetry. This enables users to swap models or frameworks without losing your observability, evaluations, or history.
How does Enterprise pricing and support work?
Enterprise plans are tailored to your deployment model, trace volume, and support needs, with volume commitments, admin-level cost controls, and priority support with accelerated response-time SLAs. Talk to sales for a quote.
Bring reliable agents
to your enterprise
LangSmith, our agent engineering platform, helps developers debug every agent decision, eval changes, and deploy in one click.