AWS and Arize AI Enhance Amazon Bedrock Agents with Observability
AWS and Arize AI announce an integration for Amazon Bedrock Agents, offering advanced observability tools to monitor and evaluate AI agent performance.
Amazon Web Services (AWS) and Arize AI have unveiled a new integration designed to enhance the observability of Amazon Bedrock Agents, addressing a critical challenge in AI development. This collaboration provides developers with comprehensive tools to trace, evaluate, and optimize AI agent performance, ensuring reliability and efficiency in production environments.
Key Features of the Integration
The integration leverages Arize Phoenix, an open-source system for tracing and evaluation, to offer:
- Comprehensive Traceability: Visibility into every step of an agent’s execution, from user queries to API calls and tool invocations.
- Systematic Evaluation Framework: Consistent methodologies to measure agent performance, including function calling accuracy and path convergence.
- Data-Driven Optimization: Structured experiments to compare agent configurations and identify optimal settings.
How It Works
The solution uses OpenInference, a set of instrumentations for ML frameworks, to automatically capture traces of Amazon Bedrock Agent interactions. These traces are then visualized in the Phoenix dashboard, enabling developers to:
- Monitor latency, token usage, and runtime exceptions.
- Inspect retrieved documents, embeddings, and LLM parameters.
- Debug inefficient paths or unexpected behaviors in agent decision-making.
Evaluation Capabilities
Phoenix includes built-in LLM-as-a-Judge templates to evaluate agent performance, such as:
- Agent Function Calling: Measures how well the agent selects and executes tools.
- Agent Path Convergence: Evaluates whether the agent takes optimal paths to solutions.
- Agent Planning and Reflection: Assesses the agent’s reasoning and adaptability.
Developers can log evaluation results directly to Phoenix, gaining actionable insights to refine agent behavior.
Getting Started
To implement this integration, users need:
- An AWS account with access to Amazon Bedrock.
- An Amazon Bedrock Agent (created manually or via AWS CDK).
- An Arize account for Phoenix API keys.
The GitHub repo provides sample code and Jupyter notebooks to streamline setup.
Conclusion
This integration marks a significant step forward in AI agent observability, empowering developers to build more reliable and performant generative AI applications. For more details, explore the Phoenix documentation or read the Arize AI blog.
Authored by AWS and Arize AI specialists, including Ishan Singh, John Gilhuly, and Richa Gupta.
Related News
Zscaler CAIO on securing AI agents and blending rule-based with generative models
Claudionor Coelho Jr, Chief AI Officer at Zscaler, discusses AI's rapid evolution, cybersecurity challenges, and combining rule-based reasoning with generative models for enterprise transformation.
AWS Launches Amazon Bedrock AgentCore Code Interpreter for Secure AI Code Execution
AWS introduces the Amazon Bedrock AgentCore Code Interpreter, a managed service enabling AI agents to securely execute code in isolated sandbox environments, addressing security and scalability challenges.
About the Author

Alex Thompson
AI Technology Editor
Senior technology editor specializing in AI and machine learning content creation for 8 years. Former technical editor at AI Magazine, now provides technical documentation and content strategy services for multiple AI companies. Excels at transforming complex AI technical concepts into accessible content.