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

# AWS Strands Agents integration

> Connect AWS Strands Agents to Orq.ai's AI Router with OpenTelemetry observability. Access 300+ LLMs with built-in reliability and tracing.

<CardGroup cols={2}>
  <Card title="AI Router" icon="arrow-right-arrow-left" href="#ai-router">
    Route your LLM calls through the AI Router with a single base URL change. Zero vendor lock-in: always run on the best model at the lowest cost for your use case.
  </Card>

  <Card title="Observability" icon="chart-line" href="#observability">
    Instrument your code with OpenTelemetry to capture traces, logs, and metrics for every LLM call, agent step, and tool use.
  </Card>
</CardGroup>

## AI Router

### Overview

AWS Strands is a framework for building AI agents with structured reasoning and tool use. By connecting AWS Strands to Orq.ai's AI Router, you transform experimental agents into production-ready systems with enterprise-grade capabilities.

### Key Benefits

Orq.ai's AI Router enhances your AWS Strands Agents with:

<CardGroup cols={2}>
  <Card title="Complete Observability" icon="chart-line">
    Track every agent step, tool use, and interaction with detailed traces and analytics
  </Card>

  <Card title="Built-in Reliability" icon="shield-check">
    Automatic fallbacks, retries, and load balancing for production resilience
  </Card>

  <Card title="Cost Optimization" icon="chart-pie">
    Real-time cost tracking and spend management across all your AI operations
  </Card>

  <Card title="Multi-Provider Access" icon="cubes">
    Access 300+ LLMs and 20+ providers through a single, unified integration
  </Card>
</CardGroup>

### Prerequisites

Before integrating AWS Strands with Orq.ai, ensure you have:

* An Orq.ai account and [API Key](/docs/administer/api-keys)
* Python 3.8 or higher
* AWS Strands SDK installed

<Info>
  To setup your API key, see [API keys & Endpoints](/docs/administer/api-keys).
</Info>

### Installation

Install the Strands Agents SDK (requires Python 3.10+):

<CodeGroup>
  ```bash Bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
  # Install Strands Agents SDK
  pip install strands-agents

  # Optional: Install additional tools
  pip install strands-agents-tools
  ```
</CodeGroup>

### Configuration

Configure Strands Agents to use Orq.ai's AI Router by passing custom client arguments with the base URL:

<CodeGroup>
  ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
  from strands import Agent
  from strands.models.openai import OpenAIModel
  import os

  # Configure model with Orq.ai AI Router
  model = OpenAIModel(
      model_id="gpt-4o",
      client_args={
          "api_key": os.getenv('ORQ_API_KEY'),
          "base_url": "https://api.orq.ai/v3/router"
      }
  )

  # Create agent with Orq.ai-powered model
  agent = Agent(
      model=model,
      system_prompt="You are a helpful AI assistant."
  )
  ```
</CodeGroup>

> **base\_url**: `https://api.orq.ai/v3/router`

### Basic Agent Example

Here's a complete example of creating and running a Strands agent through Orq.ai:

<CodeGroup>
  ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
  from strands import Agent
  from strands.models.openai import OpenAIModel
  import os

  # Configure model with Orq.ai AI Router
  model = OpenAIModel(
      model_id="gpt-4o",
      client_args={
          "api_key": os.getenv('ORQ_API_KEY'),
          "base_url": "https://api.orq.ai/v3/router"
      }
  )

  # Create a simple agent
  agent = Agent(
      model=model,
      system_prompt="You are a research assistant that helps users find and summarize information."
  )

  # Run the agent
  result = agent("Explain quantum computing in simple terms")
  print(result)
  ```
</CodeGroup>

### Agent with Tools

Strands agents can use tools while routing through Orq.ai:

<CodeGroup>
  ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
  from strands import Agent, tool
  from strands.models.openai import OpenAIModel
  import os

  # Configure model
  model = OpenAIModel(
      model_id="gpt-4o",
      client_args={
          "api_key": os.getenv('ORQ_API_KEY'),
          "base_url": "https://api.orq.ai/v3/router"
      }
  )

  # Define a custom tool using the @tool decorator
  @tool
  def search_database(query: str) -> str:
      """Search the knowledge database for relevant information."""
      # Your database search logic here
      return f"Search results for: {query}"

  # Create agent with tools
  agent = Agent(
      model=model,
      tools=[search_database],
      system_prompt="You are a knowledge assistant. Use the search_database tool to find information when needed."
  )

  # Run agent with tool access
  result = agent("Find information about machine learning best practices")
  print(result)
  ```
</CodeGroup>

### Fallback Configuration

Configure automatic fallbacks for reliability:

<CodeGroup>
  ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
  from strands import Agent
  from strands.models.openai import OpenAIModel
  import os

  # Configure model - Orq.ai handles fallbacks automatically
  model = OpenAIModel(
      model_id="gpt-4o",
      client_args={
          "api_key": os.getenv('ORQ_API_KEY'),
          "base_url": "https://api.orq.ai/v3/router"
      }
  )

  agent = Agent(
      model=model,
      system_prompt="You are a helpful assistant."
  )
  ```
</CodeGroup>

## Observability

AWS Strands integrates with Orq.ai's [Observability Platform](/docs/observability/overview) through OpenTelemetry. Capture complete traces of your agent interactions, tool calls, and model invocations to gain deep insights into agent behavior, performance, and costs.

### Prerequisites

Before you begin, ensure you have:

* An Orq.ai account and an [API Key](/docs/administer/api-keys)
* AWS Strands SDK installed
* Python 3.10+

<Info>
  The examples below use OpenAI models with OpenTelemetry tracing sent to Orq.ai. Set both `OPENAI_API_KEY` (for model access) and `ORQ_API_KEY` (for telemetry export) environment variables.
</Info>

### Installation

<CodeGroup>
  ```bash bash wrap theme={"theme":{"light":"github-light","dark":"github-dark"}}
  pip install strands-agents opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
  ```
</CodeGroup>

### Configuration

Configure OpenTelemetry to send traces to Orq.ai:

```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
import os
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import Resource

# Configure OTLP exporter
exporter = OTLPSpanExporter(
    endpoint="https://api.orq.ai/v2/otel/v1/traces",
    headers={"Authorization": f"Bearer {os.getenv('ORQ_API_KEY')}"}
)

# Create tracer provider with service name
resource = Resource(attributes={
    "service.name": "strands-agent-app"
})
provider = TracerProvider(resource=resource)
provider.add_span_processor(BatchSpanProcessor(exporter))

# Set as global tracer provider
trace.set_tracer_provider(provider)
```

### Basic Example

```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
import os
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import Resource
from strands import Agent
from strands.models.openai import OpenAIModel

# Setup OpenTelemetry
exporter = OTLPSpanExporter(
    endpoint="https://api.orq.ai/v2/otel/v1/traces",
    headers={"Authorization": f"Bearer {os.getenv('ORQ_API_KEY')}"}
)
resource = Resource(attributes={"service.name": "strands-agent"})
provider = TracerProvider(resource=resource)
provider.add_span_processor(BatchSpanProcessor(exporter))
trace.set_tracer_provider(provider)

# Configure model
model = OpenAIModel(
    model_id="gpt-4o",
    client_args={
        "api_key": os.getenv('OPENAI_API_KEY'),
    }
)

# Create agent
agent = Agent(
    model=model,
    system_prompt="You are a helpful research assistant."
)

# Run agent (traces automatically sent to Orq.ai)
result = agent("Explain quantum computing in simple terms")
print(result)
```

### Agent with Tools

```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
import os
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import Resource
from strands import Agent, tool
from strands.models.openai import OpenAIModel

# Setup OpenTelemetry
exporter = OTLPSpanExporter(
    endpoint="https://api.orq.ai/v2/otel/v1/traces",
    headers={"Authorization": f"Bearer {os.getenv('ORQ_API_KEY')}"}
)
resource = Resource(attributes={"service.name": "strands-agent-tools"})
provider = TracerProvider(resource=resource)
provider.add_span_processor(BatchSpanProcessor(exporter))
trace.set_tracer_provider(provider)

# Configure model
model = OpenAIModel(
    model_id="gpt-4o",
    client_args={
        "api_key": os.getenv('OPENAI_API_KEY'),
    }
)

# Define tools
@tool
def search_database(query: str) -> str:
    """Search the knowledge database for relevant information."""
    return f"Search results for: {query}"

@tool
def get_weather(location: str) -> str:
    """Get current weather for a location."""
    return f"Weather in {location}: Sunny, 72°F"

# Create agent with tools
agent = Agent(
    model=model,
    tools=[search_database, get_weather],
    system_prompt="You are a helpful assistant with access to search and weather tools."
)

# Run agent (all tool calls traced)
result = agent("What's the weather like in San Francisco?")
print(result)
```

## Evaluations & Experiments

Once your agents are running, use **Evaluatorq** to score outputs across a dataset and **Experiments** to compare configurations side-by-side.

<CardGroup cols={2}>
  <Card title="Run Evaluations with Evaluatorq" icon="flask" href="/docs/evaluators/build#evaluatorq">
    Run parallel evaluations across your agents and compare results.
  </Card>

  <Card title="Run Experiments via the API" icon="flask-vial" href="/docs/experiments/api">
    Compare agent configurations and view results in the AI Studio.
  </Card>
</CardGroup>