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

# Introduction

> A composable, pipeline-based testing framework for AI systems and APIs

## Why SemanticTest?

Testing AI systems is hard. Responses are non-deterministic, you need to validate tool usage, and semantic meaning matters more than exact text matching.

SemanticTest solves this with:

<CardGroup cols={2}>
  <Card title="Composable Blocks" icon="cubes" href="/blocks/overview">
    Build complex test scenarios using simple, reusable blocks for HTTP, parsing, validation, and AI evaluation
  </Card>

  <Card title="Pipeline Architecture" icon="diagram-project" href="/concepts/pipelines">
    Data flows through named slots, making tests readable and maintainable
  </Card>

  <Card title="LLM Judge" icon="gavel" href="/blocks/llm-judge">
    Evaluate responses semantically using AI instead of exact text matching
  </Card>

  <Card title="JSON Test Definitions" icon="code" href="/quickstart">
    Version-controllable, readable test definitions that anyone can understand
  </Card>
</CardGroup>

## Quick Example

Here's a simple test that validates an API response semantically:

```json theme={null}
{
  "name": "User API Test",
  "tests": [{
    "id": "get-user",
    "pipeline": [
      {
        "id": "request",
        "block": "HttpRequest",
        "input": {
          "url": "https://api.example.com/users/1",
          "method": "GET"
        },
        "output": "response"
      },
      {
        "id": "judge",
        "block": "LLMJudge",
        "input": {
          "text": "${response.body}",
          "expected": {
            "expectedBehavior": "Should return user information with name and email"
          }
        },
        "output": "validation"
      }
    ],
    "assertions": {
      "response.status": 200,
      "validation.score": { "gt": 0.7 }
    }
  }]
}
```

## What Makes It Different?

<AccordionGroup>
  <Accordion title="No More Fragile Exact Matching">
    Instead of exact text matching, SemanticTest uses AI to understand the **meaning** of responses. "2:00 PM", "2 PM", "14:00", and "two in the afternoon" are all semantically equivalent.
  </Accordion>

  <Accordion title="Built for AI Systems">
    Test tool calls, streaming responses, multi-turn conversations, and non-deterministic outputs with confidence.
  </Accordion>

  <Accordion title="Composable & Extensible">
    Mix and match 8 built-in blocks or create your own custom blocks. Each block does one thing well.
  </Accordion>

  <Accordion title="No Vendor Lock-in">
    100% open source, runs locally, works with any LLM provider. You control your data and costs.
  </Accordion>
</AccordionGroup>

## Use Cases

<CardGroup cols={2}>
  <Card title="AI Agent Testing" icon="robot">
    Test AI agents that use tools, make decisions, and maintain conversations
  </Card>

  <Card title="API Testing" icon="server">
    Traditional REST API testing with powerful validation and semantic checks
  </Card>

  <Card title="Streaming Responses" icon="wave-pulse">
    Parse and validate streaming SSE responses from OpenAI, Vercel AI SDK, and more
  </Card>

  <Card title="Integration Testing" icon="link">
    Test complex workflows with multiple API calls, data transformations, and validations
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get started in 30 seconds
  </Card>

  <Card title="Core Concepts" icon="book" href="/concepts/pipelines">
    Understand how SemanticTest works
  </Card>

  <Card title="Browse Blocks" icon="cube" href="/blocks/overview">
    Explore all available building blocks
  </Card>

  <Card title="View Examples" icon="code" href="/examples/basic-api-test">
    Learn from real-world examples
  </Card>
</CardGroup>