Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getbasalt.ai/llms.txt

Use this file to discover all available pages before exploring further.

title: ‘Introduction’ description: ‘Understand the purpose and benefits of monitoring your AI applications with Basalt.’ Monitoring is a crucial component of any AI application, providing visibility into how your LLMs are performing in production. Basalt’s monitoring system helps you track, analyze, and optimize your AI interactions to ensure they’re delivering value to your users.

​
Why Monitor AI Applications?

AI applications present unique monitoring challenges compared to traditional software. Large language models can be unpredictable, produce varying outputs for similar inputs, and their behavior can evolve over time. Effective monitoring helps you:

​
Monitoring Approaches in Basalt

Basalt offers two main approaches to monitoring:

​
1. Basic Monitoring

Basic monitoring is the simplest way to track AI interactions. It’s automatically included when you use Basalt-managed prompts and requires minimal code changes: 
// Get a prompt from Basalt (includes monitoring)
const { value, generation } = await basalt.prompt.get('prompt-slug')

// Use the prompt with your LLM provider
const response = await yourLLM.generate(value.text)

// Record the completion
generation.end(response)
This approach is ideal for simple workflows where you’re using a single prompt to generate a response.

​
2. Tracing

For more complex workflows involving multiple steps, parallel processes, or branching logic, Basalt offers a comprehensive tracing system: 
// Create a trace for a multi-step workflow
const trace = basalt.monitor.createTrace('feature-slug')

// Add logs and generations to track each step
const classificationLog = trace.createLog({ name: 'classify-input' })
const generationLog = trace.createGeneration({ name: 'generate-response' })

// Record results at each step
classificationLog.end(classificationResult)
generationLog.end(generatedResponse)

// End the trace when the workflow completes
trace.end(finalResult)
Tracing gives you deeper visibility into your AI application’s behavior and performance, allowing you to identify bottlenecks and optimize each step of your workflow.

​
Key Monitoring Features

Basalt’s monitoring system includes several powerful features:

​
Getting Started

To start monitoring your AI applications with Basalt:
  1. For simple workflows, use Basic Monitoring
  2. For complex workflows, use Tracing
  3. Add Evaluations to automatically assess output quality
  4. Explore Monitoring Examples for practical patterns you can adapt
By integrating monitoring into your AI applications from the beginning, you’ll gain valuable insights that help you deliver more reliable, performant, and cost-effective AI experiences to your users.