The Building Blocks of Generative AI

Join me on a journey into generative AI! Catch up on the essential concepts and lingo, then see it in action! Discover how you as a developer can easily incorporate this cutting-edge tech into your projects using the very same skills you already posses and start adding genAI to your apps today!

Tech requirements: plugging my own laptop. Using powerpoint and switching over to VS Code during the talk.
First public delivery: May 2024
Link to rough recording as delivered in person and livestreamed on Aug 14th in Scotland: https://www.youtube.com/live/lrKYukXYM0U
Duration:
45-min version: accommodates time for questions and more interactive beats
30-min version: accommodates time for three questions at the end but no interactions during the talk
20-min version: split into 10-min theory and 10-min demo without interactions or questions

From Apps to Agents: The Next Wave of Digital Transformation

From monoliths to microservices, and from data centers to the cloud, every wave of digital transformation has reshaped how we build and run technology. Today we stand at the next wave: the shift from apps to agents. Agentic AI brings modular intelligence that can reason, plan, and act across systems. In this talk, we’ll explore the opportunities and challenges of this transition, and how tools like Strands Agents SDK, MCP, A2A, and Amazon Bedrock AgentCore help organizations make it real.

Bringing Generative AI into production

Building a generative AI demo is easy. Running it reliably in production is not.

What does it actually take to move generative AI systems from experimentation into real production environments? What are the architectural, operational, and organizational challenges teams run into when AI-powered features become part of critical systems?

Let’s explore where teams struggle most, including latency, cost control, reliability, security, observability, and governance, and how these concerns shape decisions around orchestration, agents, workflows, and data access. Using AWS-based examples, you’ll learn about practical design patterns, real trade-offs, and common failure modes that are often overlooked in early prototypes.

You will leave with a clearer understanding of how to design generative AI systems that are not only impressive in demos, but resilient, maintainable, and safe to run in production.

Target audience: backend engineers, platform engineers, and software architects responsible for designing or operating production systems that incorporate generative AI.

Session format: architecture-focused talk with practical examples drawn from real-world production systems. The session emphasizes design decisions, trade-offs, and failure modes rather than demos or service walkthroughs.

Duration: available as a 45-minute or 30-minute session.

Level: intermediate to advanced. Familiarity with distributed systems and cloud-based application architectures is assumed. No prior hands-on experience with generative AI is required.

Choosing How to Run Microservices on AWS

Choosing between Lambda, ECS, and EKS is rarely just a service decision. This talk reframes the question by looking at how each execution model changes core microservices concerns like service discoverability, recovery, and observability, helping teams build a practical decision framework for running microservices on AWS.

Target audience: Backend engineers, software architects, tech leads, and developers working with or planning microservices on AWS.
Session format: Architecture-focused talk with diagrams and real-world examples. No live coding. Emphasis on decision frameworks and operational tradeoffs.
Duration: Available as 30 or 45 minutes
Level: Intermediate. Familiarity with basic microservices concepts and AWS fundamentals is assumed.

Microservices Fundamentals on AWS

This beginner-friendly talk introduces microservices architecture, starting from monoliths and explaining how modern backend systems are built and run on AWS. You’ll learn core microservices concepts and explore serverless and container-based models using AWS Lambda and Amazon ECS, while seeing how Kiro can help you along the way.

Target audience: Students, early-career backend developers, and engineers new to microservices and distributed systems.
Session format: Conceptual, architecture-focused talk introducing microservices fundamentals, with simple visuals and light demos to illustrate how modern backend systems are commonly built and run on AWS.
Duration: available as a 45-minute or 30-minute session.
Level: Beginner. No prior experience with microservices or AWS required.