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

# Introduction 

> Observability and monitoring platform for AI applications with full trace visibility and data lineage tracking

Arcbeam is an <Tooltip tip="Observability helps you understand the internal state of your AI system by monitoring traces, metrics, and logs">observability platform</Tooltip> for LLM applications. It captures complete execution <Tooltip tip="A trace represents the complete path of execution through your AI application, from initial request to final response">traces</Tooltip> of your RAG pipelines, agent workflows, and model calls.

## Key Capabilities

* **Trace every interaction** - Monitor model calls, retrievals, and tool executions with full context
* **Track data lineage** - See which vector database documents influenced each output
* **Manage costs** - Monitor token usage and API costs across all models
* **Debug effectively** - Get complete context for errors including inputs, outputs, and timing
* **Collaborate with teams** - Create trace collections for review and feedback

## How It Works

<Steps>
  <Step title="Instrument your application">
    Add the Arcbeam connector to your Python or JavaScript code with a few lines.
  </Step>

  <Step title="Traces are sent automatically">
    Every LLM call, retrieval, and tool use is captured via <Tooltip tip="OpenTelemetry is an open-source observability framework for cloud-native software">OpenTelemetry</Tooltip>.
  </Step>

  <Step title="Connect your data sources">
    Link vector databases to see which documents are retrieved in each trace.
  </Step>

  <Step title="Analyze in the dashboard">
    View traces, track costs, and debug issues with full visibility into your AI system.
  </Step>
</Steps>

## What You Can Track

<CardGroup cols={2}>
  <Card title="LLM Calls" icon="robot">
    Monitor all model interactions with token counts, costs, latency, and errors
  </Card>

  <Card title="Data Retrieval" icon="database">
    See which documents are retrieved from vector databases and how they're used
  </Card>

  <Card title="Agent Workflows" icon="diagram-project">
    Visualize multi-step agent executions with full tool call history
  </Card>

  <Card title="Costs & Performance" icon="chart-line">
    Track spending across models and identify performance bottlenecks
  </Card>
</CardGroup>

## Common Use Cases

<AccordionGroup>
  <Accordion title="Debug RAG Pipelines" icon="magnifying-glass-chart">
    Trace wrong answers back to the exact documents that were retrieved. See why your RAG system chose certain content and understand retrieval quality issues.
  </Accordion>

  <Accordion title="Optimize Costs" icon="dollar-sign">
    Identify expensive traces and compare costs across different models. Track token usage patterns and find opportunities to reduce spending without sacrificing quality.
  </Accordion>

  <Accordion title="Monitor Production" icon="server">
    Track error rates, response times, and usage across environments. Set up alerts for anomalies and maintain SLAs with real-time visibility.
  </Accordion>

  <Accordion title="Improve Data Quality" icon="sparkles">
    Discover which documents are valuable and which go unused. Use data lineage to optimize your vector database and improve retrieval relevance.
  </Accordion>

  <Accordion title="Collaborate on Improvements" icon="users">
    Create trace collections for team review and feedback. Share specific examples of issues or successes with stakeholders.
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/v0/quickstart">
    Get Arcbeam running in 5 minutes
  </Card>

  <Card title="Send Traces" icon="paper-plane" href="/v0/setup/connect-your-ai-system">
    Instrument your application
  </Card>

  <Card title="Connect Data" icon="plug" href="/v0/setup/add-data-sources">
    Link your vector databases
  </Card>

  <Card title="View Traces" icon="eye" href="/v0/debugging/find-problematic-traces">
    Start analyzing your data
  </Card>
</CardGroup>

## Support

Questions? Contact [support@arcbeam.ai](mailto:support@arcbeam.ai).