Same agent Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
TypeScript agent-harnessagent-harness-engineeringai-engineeringai-observabilityamd-gpuclaude-codeclickhousecodexcoding-agentcoding-agentscursorgenaigpu-monitoringllm-observabilityllmopsnvidia-smiobservabilityopen-sourceopenaiopentelemetry
---
title: "Evaluate LLMs and AI Agents"
sidebarTitle: "Evaluations"
description: "Quickly evaluate your model responses for Hallucination, Bias, and Toxicity"
---
import EvalsQuickstart from '/snippets/quickstart-programmatic-evals.mdx';
<EvalsQuickstart />
---
<CardGroup cols={3}>
<Card title="Full SDK reference" href="/latest/sdk/features/evaluations" icon='book'>
Parameters, result objects, batch evaluation, and Rule Engine attribute resolution in depth
</Card>
<Card title="CI/CD integration" href="/latest/sdk/features/evaluations#ci-cd-integration" icon='code-branch'>
Use evaluations as quality gates in your test suite or pipeline
</Card>
<Card title="Online evaluations" href="/latest/openlit/quickstart-evals" icon='bolt'>
Auto-evaluate every production trace instead of calling evaluations yourself
</Card>
<Card title="Quickstart: LLM Guardrails" href="/latest/sdk/quickstart-guard" icon='shield'>
Protect and secure your LLM responses in 2 simple steps
</Card>
<Card title="Integrations" href="/latest/sdk/integrations/overview" icon='circle-nodes'>
60+ AI integrations with automatic instrumentation and performance tracking
</Card>
<Card title="Destinations" href="/latest/sdk/destinations/overview" icon='link'>
Send telemetry to Datadog, Grafana, New Relic, and other observability stacks
</Card>
</CardGroup>