Amazon Bedrock Agents Tracing

Google Colab

colab.research.google.com

Amazon Bedrock Agents allow you to easily define, deploy, and manage agents on your AWS infrastructure. Traces on invocations of these agents can be captured using OpenInference and viewed in Phoenix. This instrumentation will capture data on LLM calls, action group invocations (as tools), knowledgebase lookups, and more.

Install

pip install openinference-instrumentation-bedrock

Setup

Connect your application to Phoenix with the register function: After connecting to your Phoenix server, instrument boto3 prior to initializing a bedrock-runtime client. All clients created after instrumentation will send traces on all calls to invoke_model, invoke_agent, and their streaming variations.

import boto3

session = boto3.session.Session()
client = session.client("bedrock-runtime")

Run Bedrock Agents

From here you can run Bedrock as normal

session_id = f"default-session1_{int(time.time())}"

attributes = dict(
    inputText=input_text,
    agentId=AGENT_ID,
    agentAliasId=AGENT_ALIAS_ID,
    sessionId=session_id,
    enableTrace=True,
)
response = client.invoke_agent(**attributes)

Observe

Now that you have tracing setup, all calls will be streamed to your running Phoenix for observability and evaluation.

Resources

Amazon Bedrock SDK for JavaScript Amazon Bedrock Agent Runtime JavaScript

⌘I

Developer Tools

MCP

LLM Providers

TypeScript

Python

Java

Platform

Sandboxes

Evaluation Integrations

Coding Agents

Amazon Bedrock Agents Tracing

Google Colab

Install

Setup

Run Bedrock Agents

Observe

Resources

Google Colab

​Install

​Setup

​Run Bedrock Agents

​Observe

​Resources

Install

Setup

Run Bedrock Agents

Observe

Resources