AWS AI in Practice

Welcome to our June event. We're delighted to welcome Marina Kim, Tech Lead, Vidatec and Damien Jones, AWS Consultant, Steamhaus

You've seen the AgentCore demos. Marina has taken them into production, and lived to tell the tale. Tonight she's giving us the engineering reality behind building AI agents on AWS with Amazon Bedrock and tooling: what breaks, what costs you, and what actually ships.

Five weeks. A brand new business. A Crufts deadline. Damien didn't whiteboard this one - he shipped it. Tonight he's walking us through every decision that made it possible: AWS CDK, Amplify, Q Developer, and Kiro working together under real pressure.

A big thank you to our sponsors Cloudscaler, Rayo & The Scale Factory

Programme:
18:00: Arrival, registration
18:15: Talks start
20:00: Networking with food and a drink provided by the generosity of our sponsors.

Talk 1:
AgentCore vs Reality: Lessons from Building AI Agents on AWS with Marina Kim

In this talk, I will explore the reality of what happens when you try to build an AI agent on AWS using Amazon Bedrock and tool calling, inspired by still new and emerging AgentCore patterns.

Through a live demo and practical examples, I’ll walk through what worked, what didn't work, and the unexpected challenges that appear when moving from theory to implementation, including hallucinations, incorrect tool usage, and trade-offs around cost and latency.

The goal is to give a realistic, engineering-first perspective on building agentic systems today, and help developers understand where these patterns are useful and where they still fall short.
By the end of this talk, you’ll have a clear understanding of how to approach building AI agents on AWS, what pitfalls to expect, and how to make informed decisions when applying agentic patterns in real-world systems.

Learning Takeaways

• How to approach building AI agents on AWS using Amazon Bedrock and tool calling, with focus on emerging AgentCore patterns
• What actually happens when you move from theory to implementation, including common failure modes like hallucinations, incorrect tool usage, and overconfident decisions.
• How to iteratively improve an agent by testing, identifying issues, and introducing guardrails and constraints
• How to evaluate trade-offs between autonomy, reliability, cost, and latency in agentic systems

Marina is a Tech Lead at Vidatec working with web, mobile, MS Teams and AI solutions across multiple industries. She has significant experience working with AWS services, managing deployments and maintenance across multiple production workloads. Marina is a founder of Catbytes - online community for women in tech and a co-organiser of AWS UG UK and AWS AI In Practice community events

Talk 2:
Best in Show: Building a Crufts-Ready AWS Business Platform in 5 Weeks with Damien Jones

A new dog training business is launched. You have 5 weeks to develop a new production-ready platform before Crufts: the world's biggest dog show. Could you deliver?

In this talk, I'll share the real-world journey of building WolfieAndFriends on AWS. We'll review my architectural choices, "build vs buy" decisions and the trade-offs made during those hectic early days. You'll learn how to use AWS serverless, IaC and AI services to enable rapid delivery, shorten development times and transform a greenfield project into a professional, scalable platform that pays the bills.

Whether you're a startup founder or an enterprise dev, you'll walk away with a blueprint for rapid delivery without sacrificing long-term stability. Expect Amplify, CDK, Q Developer, Kiro and more!

Learning Takeaways

• How to make fast, defensible architectural decisions under genuine time pressure.
• How to use AWS CDK, Amplify Gen 2, Q Developer, and Kiro as an integrated rapid-delivery stack.
• Practical "build vs buy" trade-offs: what to own, what to delegate, and how to decide.
• How serverless IaC enables safe iteration from greenfield to production.
• A reusable blueprint for going from zero to a scalable, paying platform in weeks — not months.

Damien is an AWS consultant, data specialist, and cloud enthusiast with a strong record of designing, building, and optimising cloud-native solutions. He has extensive knowledge of data engineering, DevOps and cloud architectures, fueled by a passion for using emerging technologies to solve complex problems and support data-driven decision making. Damien is also active in the cloud community, serving as a content creator, user group leader and public speaker.

Do you have a story to share?
If you are interested in speaking at one of our events, please check out our call for papers here.

We are advocates for greater inclusion & diversity in UK Tech and are especially keen to receive talk submissions from people in underrepresented groups. If you are interested in speaking at a future meetup but would like to discuss what to expect or need assistance, please contact our Inclusion & Diversity Lead Natalie Gray - graynataliej@gmail.com or DM her @natjgray

Check out our website for more information about our community and our code of conduct. Remember to follow us @AWSUserGroupUK and on LinkedIn for the latest updates, and you can find videos of our past meetups here.

Remember to follow us @AWSUserGroupUK and on LinkedIn for the latest updates and you can find videos of our past meetups on YouTube.

Remember to follow us @AWSUserGroupUK and on LinkedIn for the latest updates and you can find videos of our past meetups on YouTube.

Remember to follow us @AWSUserGroupUK and on LinkedIn for the latest updates and you can find videos of our past meetups on YouTube.