> ## Documentation Index
> Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details.

# Observability & Tracing

> Monitor, debug, and optimize your LLM applications with comprehensive observability and tracing capabilities

LangWatch tracks every interaction inside your LLM applications, helps you debug issues, and shows you how your AI systems work in production.

![LangWatch Observability Dashboard](https://mintcdn.com/langwatch/CYVXWbKFuujxTm5z/images/llm-observability/overview.webp?fit=max\&auto=format\&n=CYVXWbKFuujxTm5z\&q=85\&s=7a4b821ffba7245468439d747524247a)

## Core Features

> [card] [Real-time Tracing](https://langwatch.ai/docs/concepts.md)
>
> Watch every LLM call and tool usage as it happens, with full context.

> [card] [User Events](https://langwatch.ai/docs/user-events/overview.md)
>
> See how users actually interact with your AI - thumbs up, selections, custom events.

> [card] [Cost Tracking](https://langwatch.ai/docs/integration/python/tutorials/tracking-llm-costs.md)
>
> Know exactly how much each model call costs you, down to the token.

> [card] Monitor Performance
>
> Spot slow calls and bottlenecks before your users complain.

> [card] [Automations & Alerts](https://langwatch.ai/docs/features/automations.md)
>
> Get notified when things go wrong, or when costs spike unexpectedly.

> [card] [Embedded Analytics](https://langwatch.ai/docs/features/embedded-analytics.md)
>
> Drop dashboards right into your app so your team can see what's happening.

## How it works

Add a few lines to your code and LangWatch starts tracking everything:

1. **Add the SDK** - Drop in a few lines of code to your existing app
2. **We track everything** - Automatically captures all your LLM calls and interactions
3. **See it live** - Watch what's happening in real-time through the dashboard
4. **Debug** - Click into any trace to see exactly what went wrong

## Get started

Pick your language and start tracking:

> [card] [Python SDK](https://langwatch.ai/docs/integration/python/guide.md)

> [card] [TypeScript SDK](https://langwatch.ai/docs/integration/typescript/guide.md)

> [card] [Go SDK](https://langwatch.ai/docs/integration/go/guide.md)

> [card] [View All Integrations](https://langwatch.ai/docs/integration/overview.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.