WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe - Virtual Stage • Jul 7, 2026 • Session details

From Black Box to Glass Box : Bedrock AgentCore Observability

Yasemin Aktürk

Why did your AI hallucinate? Discover how Bedrock Agent Core uses automated tracing to expose every reasoning step, turning complex LLM logic into a transparent glass box.

Pause
Mute Enter Fullscreen
#1 about 1 min

Introduction to Amazon Bedrock Agent Core capabilities

Agent Core provides production-ready building blocks to simplify the overall development and infrastructure of AI agents.

#2 about 3 min

How Agent Core runtime executes and tracks agent requests

Runtime infrastructure paths prompts through sandbox environments to safely execute tool calls and track latency.

#3 about 3 min

Retaining conversation context with short and long-term memory

Background models automatically extract and synchronize important facts across both active and historical conversation memory streams.

#4 about 2 min

Architecture overview of the demo customer support agent

The agent requires access to specific endpoints and environment tools to successfully fulfill customer support queries.

#5 about 4 min

Navigating the GenAI observability dashboard in Amazon CloudWatch

Centralized monitoring dashboards present detailed traces, event memory metrics, and token usage statistics for root cause analysis.

#6 about 5 min

Analyzing tool selection and execution within trace details

Trace trajectories demonstrate whether an agent routed user requests correctly while simultaneously tracking total token usage.

#7 about 2 min

Reviewing traces to uncover missed tool calls and inaccuracies

Trace logs expose factual inaccuracies when agents hallucinate answers instead of querying appropriate external data tools.

#8 about 3 min

Evaluating agent response accuracy and tool selection logic

Built-in correctness metrics score factual accuracy to help developers diagnose the root cause of hallucinated answers.

#9 about 2 min

Reviewing agent interactions completed without external tool execution

Execution steps verify that basic conversational queries successfully bypass external endpoints to lower overall tool usage.

Matching moments

1:01 min

Capturing AI session telemetry for deep usage insights

Brian Scanlan Brian Scanlan · World Congress 2026 Europe

1:27 min

Building observability to verify unexpected AI agent behavior

Adam Bird Adam Bird · World Congress 2026 Europe

2:55 min

Executing and analyzing the core AI agent sub-workflow

Max Tkacz Max Tkacz · World Congress 2025

2:10 min

Choosing the right runtime environment for hosting AI agents

Ahmad Adel Ahmad Adel · Europe 2026 Virtual

4:10 min

Architectural building blocks for enterprise agent development platforms

Dennis Zielke Dennis Zielke +1 · World Congress 2025

2:42 min

Tracing agentic capabilities and step-by-step code execution

Jemiah Sius Jemiah Sius +1 · World Congress 2026 Europe

More from World Congress 2026 Europe - Virtual Stage

One Does Not Simply Make Architecture Decisions Alone thumbnail
36:15
2 months ago

One Does Not Simply Make Architecture Decisions Alone

Vladas Diržys

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence thumbnail
30:41
3 months ago

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence

Julia Grosse

Better Together: Leveraging Your Observability Tools as a SIEM thumbnail
39:06
3 months ago

Better Together: Leveraging Your Observability Tools as a SIEM

Mathias Palmersheim

ChatGPT Apps: From Chat to Checkout thumbnail
30:29
3 months ago

ChatGPT Apps: From Chat to Checkout

Aaron Koivunen

Interior Decorating (TypeScript Decorators) thumbnail
29:22
3 months ago

Interior Decorating (TypeScript Decorators)

Michael Dowden

Designing the intelligence layer: The future of products beyond interfaces thumbnail
24:21
3 months ago

Designing the intelligence layer: The future of products beyond interfaces

Madalena Costa

Related videos

What 500+ Production Environments Taught Us About Shipping AI Agents thumbnail
23:05
World Congress 2026 Europe • 3 months ago

What 500+ Production Environments Taught Us About Shipping AI Agents

Liran Hason

Beyond the Benchmark: How to Evaluate AI Agents in the Real World thumbnail
30:04
World Congress 2026 Europe • 3 months ago

Beyond the Benchmark: How to Evaluate AI Agents in the Real World

Taylor Jordan Smith

How we built an AI-powered code reviewer in 80 hours thumbnail
28:07
World Congress 2025 • about 1 year ago

How we built an AI-powered code reviewer in 80 hours

Yan Cui

Unlocking the AI Black Box: Building Trust in the Era of Agentic Production thumbnail
27:40
World Congress 2026 Europe • 3 months ago

Unlocking the AI Black Box: Building Trust in the Era of Agentic Production

Jemiah Sius, Harry Kimpel

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems thumbnail
32:48
World Congress 2026 Europe • 3 months ago

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems

Matheus Guimaraes

Building Agentic Applications: A Deep Dive into Zooka, an AI Cardiologist Assistant thumbnail
27:54
Europe 2026 Virtual • 3 months ago

Building Agentic Applications: A Deep Dive into Zooka, an AI Cardiologist Assistant

Ahmad Adel

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.