AWS Bedrock AgentCore Hands-On Workshop: A Recap
Source: Dev.to
Montréal AWS User Group
Date: December 18 , 2025
Workshop Overview
A hands‑on journey through Amazon Bedrock AgentCore (a platform to run AI agents at scale). We covered:
- Runtime
- Gateway
- Identity
- Memory
- Built‑in Tools
- Observability
Participants learned how to take AI agents from a simple PoC (Proof of Concept) to secure, enterprise‑ready applications.
Note: Each demo shown here is just one example, and the tools mentioned are a subset of what was explored during the workshop—not exhaustive.
Why Cloud Development Matters
“Getting into cloud development isn’t just about learning services—it’s about understanding the real problem first. Code is a tool for reliability, not the final asset. The bigger picture is knowing why a company would use Amazon Bedrock AgentCore.”
Enterprises want AI agents that can move from experiments to real‑life, secure, scalable, and observable applications. This workshop helped connect the dots: how modules and tools work together to create agents that are smart, reliable, and trustworthy.
Target audience:
Enterprises or developers who want AI agents without managing all the complex infrastructure themselves. Goals include:
- Building reliable agents
- Scaling safely
- Integrating with external systems
- Having full visibility (observability) into agent operations
1. Runtime
What it is
A secure environment that runs your agent (the software that answers questions or performs tasks), handling infrastructure, scaling, and session management.
Why it matters
Developers can focus on what the agent does instead of worrying about servers or security.
Example Demo – Weather + Calculator agent
- Runtime handled all container orchestration and session isolation.
Prompt Example
How is the weather?Tools Used
- Strands Agent
- Elastic Container Registry (ECR)
- Terminal prompts
Takeaway
Runtime is the backbone that turns a prototype into a production‑ready agent.
2. Gateway
What it is
The integration layer that allows agents to interact with external systems or APIs.
Why it matters
To provide real‑world insights, agents need safe, reliable access to external information. Gateway lets you define tools with metadata (name, description, input/output schemas, behavior).
Example Demo – Mars Weather agent
- Called NASA’s Open APIs using an API key.
Prompt Example
Hi, can you list all tools available to you?
What is the weather in the northern part of Mars?Tools Used
- REST APIs
- AgentCore Gateway
- API keys
Takeaway
Gateway bridges the agent and external systems, enabling actionable intelligence and structured tool integration.
3. Identity
What it is
Manages who can invoke agents and what they can access.
Why it matters
Protects sensitive data and ensures compliance in enterprise environments.
Example Demo – AgentCore Runtime with vs. without Authorization
- Weather agent invoked with authorization → succeeded.
- Weather agent invoked without authorization →
AccessDeniedException.
Prompt Example
How is the weather?Tools Used
- Amazon Cognito
- JWT tokens
Takeaway
Identity ensures only authorized users or systems interact with agents.
4. Memory
What it is
Stores context for multi‑turn conversations.
| Type | Description |
|---|---|
| Short‑term memory | Remembers context during a session (e.g., last few questions). |
| Long‑term memory | Preserves key information across sessions (e.g., user preferences, summaries). |
Why it matters
Enables agents to give personalized, context‑aware responses, improving over time.
Example Demo – AI Learning Agent
- The agent remembered the user’s name (Alex) and topics of interest in AI across sessions.
Prompt Flow
User: My name is Alex and I'm interested in learning about AI.
Agent: Hi Alex! I’m excited to help you learn about AI!
User: What was my name again?
Agent: Your name is Alex!Tools Used
- AgentCore Memory
- Strands MetricsClient
Takeaway
Short‑term memory provides session‑level context; long‑term memory provides persistent context that improves user experience and enables continuity over time.
5. Built‑in Tools
What it is
Pre‑built tools like Browser or Code Interpreter that extend agent capabilities.
Why it matters
Agents can perform specialized tasks safely and efficiently.
Example Demo – Amazon Revenue Extraction
- Extracted Amazon revenue data from a website using the Browser tool with Nova Act SDK.
Prompt Example
Extract and return Amazon revenue for the last 4 years from stockanalysis.com.Tools Used
- Browser Tool
- Code Interpreter
- Nova Act SDK
Takeaway
Built‑in tools enable agents to handle complex tasks, making them more useful in enterprise contexts.
6. Observability
What it is
Monitoring and logging for agent workflows, tool usage, performance, and errors.
Why it matters
Ensures agents are traceable, measurable, and debuggable—building trust in production.
Example Demo Workflow – CrewAI Travel Agent
-
Create a runtime‑ready CrewAI agent using Amazon Bedrock, defining its role, goal, backstory, and task.
-
Instrument the agent with
CrewAIInstrumentor().instrument()to enable observability. -
Invoke the agent via Boto3:
prompt = "What are some rodeo events happening in Oklahoma?" response = bedrock_client.invoke_agent(..., prompt=prompt) -
Multiple responses are found in parallel.
-
Dashboards on CloudWatch display metrics such as request latency, tool invocation counts, and error rates.
Tools Used
- CrewAIInstrumentor
- Boto3 (AWS SDK for Python)
- CloudWatch dashboards
Takeaway
Observability provides the insight needed to operate agents at scale, detect issues early, and continuously improve performance.
Closing Thoughts
The workshop demonstrated that Amazon Bedrock AgentCore ties together runtime, gateway, identity, memory, built‑in tools, and observability into a cohesive platform. Enterprises can now move from experimental AI agents to secure, scalable, and trustworthy production workloads—without having to manage the underlying infrastructure themselves.
Observability & Metrics
- Watch runtime metrics across all agents.
- Clicking on a specific agent reveals detailed metrics with custom time‑frame filtering.
Tools Used
- Amazon CloudWatch
- Boto3 SDK
- Crew AI
- Scarf
- AWS Distro for OpenTelemetry
Takeaway
Observability ensures production agents are monitored and performance is visible, supporting reliability and optimization.
Enterprise Adoption of Bedrock AgentCore
Enterprises adopt AgentCore to move from a proof‑of‑concept to production‑ready AI applications. It provides:
- Scalable deployment without managing infrastructure
- Secure, authorized execution
- Contextual and persistent memory
- Integration with external systems and workflows
- Full observability for performance and errors
Understanding these modules helps developers deliver AI solutions that meet enterprise goals.
Development Philosophy
- Cloud development is about seeing the big picture, not just writing code.
- AgentCore offers a sandbox to experiment safely with enterprise‑grade agents.
- Observability ensures live agents can be monitored, optimized, and trusted.
Learning & Community
Hands‑on workshops and community engagement are invaluable for learning how tools solve real‑world problems.