OPENING KEYNOTE
From Compilers to Copilots:
The Evolution of Software and the Al-Powered Future
Sheen Brisals | Technologist | Author | Team Topologies Advocate
Angela Timofte | Co-Founder & CTO @ Stride
David Anderson | Author - Value Flywheel Effect
Software engineering is at an inflection point.
The way we build software has changed repeatedly, from physical infrastructure to the cloud, from monoliths to distributed systems, from deterministic to probabilistic systems, and from manual delivery to increasingly automated platforms. But the current shift feels different. AI is not just changing our tools. It is beginning to change the role of the engineer itself.
In this three-act keynote, Sheen Brisals, Angela Timofte and David Anderson explore software development through the lens of the past, present and future.
Sheen looks at how we got here and what past technology shifts can teach us.
Angela brings the discussion into the present, sharing what building with AI in the cloud actually looks like today, where it delivers real value, where it falls short, and how the engineering workflow is already changing.
David then looks ahead at what these signals could mean for the future of software development, engineering teams and the skills that will matter most.
The central question is simple: if our ability to produce code is no longer the main constraint, what becomes the job of the software engineer?
The keynote will be followed by an interactive roundtable, giving the audience the opportunity to challenge the ideas, share their own experiences and explore what engineers and technology leaders should start doing differently now.
CLOSING KEYNOTE
Beyond Software Engineering.
Q: What should engineers do when writing code is the easy part?
A: Focus on bigger, more creative and more impactful challenges.
Ian Massingham | Applied AI @ Anthropic
Have you noticed that things are getting weird? Frontier model capability is compounding on every axis that matters: the length of task a model can complete unaided, collapsing cost per task, increasing context length, and reliability. Transformative AI now genuinely solves entire categories of tasks, software engineering being a prime example, and recursive self improvement is a reality we are seeing today.
The way Anthropic works has shifted with these advancements. Drawing on how we work inside Anthropic and what we see from the 1000s of startups building on and with Claude, this talk sets out what engineers do when writing code is the easy part: choosing the outcomes, making systems legible to models, and ultimately going beyond software to focus on bigger, more impactful challenges.
Serverless, the hard parts
Yan Cui | Independent Consultant
Serverless promises infinite scale and zero ops, but the reality for most teams is more… complicated.
In this talk, we’ll look at the hard parts of serverless: unpredictable performance and cost, local development and testing, and the mindset change needed for success.
Yan will draw on his real-world experiences and share practical strategies and patterns to overcome these challenges. So your team can deliver reliable, secure, and cost-efficient serverless applications at scale.
Level L200
Using Gen AI to rebuild a Serverless Stripe Integration
Matt Evans | Principal Engineer at Mony Group
To migrate away from a legacy Azure cloud,Rebuilding a business-critical payment system with no subject matter experts, zero downtime requirements, and a three-month deadline sounds unrealistic—until you add GenAI to the mix.
In this talk, we’ll walk through how a small team of principal engineers migrated a Stripe-based payment platform from Azure to AWS using a fully serverless architecture. By leveraging GenAI to accelerate understanding, design, and implementation, we were able to reconstruct a complex system—complete with webhook handling, idempotency, and transactional rollback—without access to the original expertise.
This session shares practical lessons on using GenAI beyond code generation, and how to apply it safely and effectively in high-stakes systems.
Level L200
Diagrams will Save Your Serverless Spaghetti: Mapping Boundaries to Visualise Complex Architectures
Isabel Maccabee | Senior Software Engineer, Kraken
As organisations grow, the lack of hierarchy of serverless often results in “Serverless Spaghetti”; thousands of lambdas, buckets, streams, and databases all connected in opaque ways. Communicating these complex relationships on a diagram inevitably becomes chaotic, inconsistent and immediately out of date.
This session introduces a tiered domain-mapping diagramming framework. The power of this framework is in allowing the act of diagramming to enforce clear boundaries within your serverless estate. This talk will help you harness that power.
By building on the principles of the C4 model, we will explore how to re-align architectural tiers to bridge the gap between high-level business logic and low-level cloud infrastructure. The result is a "zoomable" architecture that reduces cognitive load for various audiences, from engineers to stakeholders.
**Key Takeaways:**
- The Rule of Granularity: How to build a "zoomable" architecture, decoupling high-level strategy from low-level implementation swaps (e.g. moving from an SQS queue to a Kinesis Stream) without requiring a total diagram overhaul.
- Defining the Service Boundaries: In serverless architectures, business logic is often encoded in the infrastructure - blurring the lines between the platform and application layer. We’ll discuss how diagrams make it easier to define boundaries and the benefits of grouping resources into units that are deployable by a single pipeline.
- Reaping the Operational Rewards: Practical methods for mapping these diagrammatic boundaries to AWS Tagging to enable consistent billing and ownership across the business. This will let you point at a diagram and say “This part of the diagram costs this much”.
- Sustainable Documentation: A pragmatic look at emerging strategies for maintenance, including architectural guilds, automated "scorecards," and touching on the future role of AI in keeping code and diagrams in sync.
- Beyond the Big Picture: Practical pro-tips on arrow semantics, hyperlinking, and the fine art of making complex systems look simple.
Instead of a fog of icon-heavy chaos, transform your organisation’s diagrams into functional blueprints that bridge the gap between architectural design, deployment units, and the bottom line.
Level L100
Bedrock Ships Faster Than Its Security Primitives
Osama Okunbo | Security Engineer, Immibuddy
Bedrock makes shipping an AI agent straightforward. Guardrails, IAM integration, CloudTrail invocation logging, knowledge bases, action groups. The building blocks are there, the docs are solid, and a working agent can be in production in a weekend.
The security primitives around those building blocks are still catching up. This session covers six attack paths against a Bedrock agent, tested against a reference implementation built to model the kind of production deployment a compliance-constrained SaaS would ship. Prompt injection through document ingestion pipelines. Tool invocation abuse via action groups. Secrets leaking from agent context into CloudWatch and X-Ray.
Credential escalation through execution role misconfiguration. Memory poisoning via OpenSearch-backed knowledge bases. And the one most teams miss, inference-time exfiltration of sensitive prompt context into the model provider's own observability.
For each I show the chain, the CloudWatch or CloudTrail signal that reveals it, and the AWS-native control that stops it where one exists. Some attacks have clean controls. Some do not yet, and I am honest about which is which. I cover what to build at the IAM, VPC, and KMS layers to close the gaps that Bedrock Guardrails alone do not cover, and how to keep agentic workloads inside the same ISO 27001 and SOC 2 evidence envelope as the rest of an AWS estate.
This is a practitioner talk drawn from hands-on work with agentic systems in regulated environments, presented on a sanitised reference architecture.
Attendees leave with a Bedrock threat model, a CloudWatch and CloudTrail detection ruleset, an honest view of what Guardrails covers, and a concrete list of controls to layer on top.
Level L300
Your AI Tools Might Be Ready. Your Organisation Isn't
Owen Hawkins | Principal Solutions Architect, AWS
The vision for AI-native development is compelling. The gap between that vision and a working, auditable production system is where almost every organisation is stuck right now.
Most teams have AI coding tools. A developer here, a team there, moving faster. But individual productivity gains aren't organisational transformation — and faster code generation without traceability just creates faster technical and compliance debt.
In this talk, I'll share what it actually looks like when organisations try to make that shift. Not the demo. The Monday morning after the demo.
Drawing on real customer engagements, I'll cover three things: how to evaluate AI development tooling at an organisational level rather than an individual one; what AI-DLC genuinely demands from your teams and your leadership — and what fights back when you try to change; and the path to production — treating the spec as a first-class pipeline artefact, validated against version-controlled organisational standards before a line of code is written, then backed by the pipeline controls you already trust (SAST, policy-as-code, dependency scanning) on the generated code itself. Two layers of guardrails using the same mental model your teams already understand — just applied earlier.
I'll show briefly what spec-driven development looks like in practice, but the real conversation is about the organisational conditions and the controls that make AI-generated code something you can actually trust in production — not just in a sandbox.
You'll leave with an honest picture of where the friction is, and some opinionated ideas on how to close the gap — drawn from customers who are working through this right now.
Level L200
Hidden trade-offs in distributed architectures
Anahit Pogosova | AWS Data Hero & Cloud Architecture and Engineering Lead, F-Secure
Asynchronous event-driven architectures enable loosely coupled, scalable, and resilient systems. But the devil is in the details, and the true complexity lies in how components interact under real-world pressure. Ordering, idempotency, failure handling, latency, and cost aren’t shaped by high-level architecture diagrams with boxes and arrows — they’re shaped by the strategies and services you choose to integrate systems in distributed environments.
In this talk, you’ll uncover common design trade-offs behind integration decisions, illustrated with lessons from the field working with services like AWS Lambda, Amazon DynamoDB, and AWS Step Functions. You’ll leave with a sharper intuition for how distributed architectures behave, and how to design event-driven systems that are both resilient and intentional.
Level L300
Lessons learn building a Serverless first business with AI
Mark Sailes | Solutions Architect, Amazon Web Services
Lee Gilmore | AWS Serverless Hero & Serverless Advocate
In March, Lee Gilmore and Mark Sailes took their business idea and turned it into a real product.
Being die hard AWS Serverless fans they naturally built with a serverless first mindset. In this talk
learn about what worked well, and what they would never do again. Lee and Mark will share how they
used steering docs, hooks and skills to tailor AI output, and how they used MCP and an AI-DLC to
collaborate.
Level L300
Migrating 200 Engineers and Tens of Millions of LOC from Azure to AWS in Six Months, With AI
Mo Khazali | Associate Partner - AI Tooling @ Theodo UK
Ben Ellerby | CINO, Partner @ Theodo UK
Cross-cloud migrations are usually pitched as a choice between two bad options: a multi-year lift-and-shift that just moves the technical debt to a new cloud, or a ground-up rewrite that freezes the roadmap while the business holds its breath. Neither was viable for a live, serverless-native estate spanning tens of millions of lines of code with 200 engineers. The problem at this scale was not as simple as pointing Copilot or Cursor at the code and asking it to migrate.
In this session, Ben Ellerby and Mo Khazali walk through how they moved the entire estate off Azure and onto AWS in six months, using an AI toolchain grounded in compiler tooling and formal grammars rather than vibe coding.
Key takeaways include:
- Automated Mapping with ASTs: Parsing Azure Functions and logic into Abstract Syntax Trees to map service dependencies, ensuring that AWS Lambda triggers and event-driven architectures are provisioned with all required upstream and downstream resources.
- Compiler-Informed LLM Context: Using static analysis to provide LLMs with specific code structures rather than broad grep search results, enabling for reliable translation of Azure-specific SDKs to AWS SDK.
- Infrastructure-as-Code Refactoring: A two-step pipeline using deterministic scripts for initial AWS CDK/Terraform generation, followed by human-in-the-loop agents to resolve complex networking and IAM policy discrepancies.
- Behavioural Verification: Validating the migration by generating integration tests from original Azure execution paths to ensure the new AWS environment maintains functional parity and consistent performance metrics.
- AWS AI Gateway for Governance: Implementing a centralised entry point on AWS to enforce data residency policies, manage API usage for LLM providers, and monitor operational costs across the developer estate.
This will include the theory as well as real numbers and real stories from replatforming a live, serverless, large scale estate across clouds.
Level L300
Context Over Code: Why AI-DLC Is an Organisational Transformation, Not a Productivity Hack
Matt Houghton | AI, Data and Analytics Architect at CDL Software, AWS Community Builder, AWS Ambassador. AWS Gold Jacket.
AI coding assistants are everywhere, but faster code generation isn't the problem most teams need to solve. At CDL, we rolled out Amazon Q Developer to 150+ engineers and saw real results — but we quickly realised the bigger opportunity wasn't in the tools, it was in rethinking how we work.
This talk covers our journey from AI code companion to AI-Driven Development Lifecycle (AI-DLC): how we trialled and scaled AI tooling, why we built a Context Store to give AI access to decades of institutional knowledge, and what it actually takes to make AI-native development work in practice. We'll cover steering, semantic retrieval with Bedrock Knowledge Bases and MCP, verification debt, and why the developers who thrive aren't the fastest coders — they're the ones who curate context and own quality.
Level L200
Rethinking Microservices: Lessons from Refactoring to AWS Lambda Durable Functions
Matheus das Mercês | AWS Community Builder @ Serverless | Senior Cloud Engineer, PostNL
For more than a decade, software teams have been balancing the trade-offs between monoliths and microservices on AWS. From simple Lambdaliths to complex design patterns to achieve microservices benefits, this debate has been anything but settled.
At AWS re:Invent, AWS introduced Lambda Durable Functions with an interesting premise: build like a monolith, deploy as microservices. By bringing durable execution to Lambda Functions, AWS is challenging assumptions about how serverless applications should be designed.
In this talk, I will walk through a real-world refactor of a multi-step data pipeline at PostNL, migrating from AWS Step Functions to AWS Lambda Durable Functions and still respecting the application's design pattern. We’ll explore what worked, what didn’t, and the trade-offs we encountered along the way.
When you walk out of this session, you will understand how Lambda Durable Functions work under the hood, when they are a better fit than state machines, the trade-offs they introduce, and how they influence microservice design decisions in practice, or whether this marks the end of the monolith vs. microservices debate as we know it.
Level L300
Letting It Think For Itself: Permissions, Context, and the Tension of Semi-Autonomous AI Agents
Julian Wiffen | Chief of AI and Data Science, Matillion & Maia
Sam Perrin | Principal Engineer - Matillion & Maia
Every team building with AI agents hits the same tension: to be useful, the agent needs permissions - access to data, the ability to trigger pipelines, the authority to act while nobody's watching. But the more autonomy you grant, the more you need to trust that the agent knows what it's doing and won't cause damage.
This talk shares what we've learned building Maia, an AWS Bedrock powered virtual data engineer that operates semi-autonomously across async workflows. We'll cover the practical architecture of letting an AI agent work on its own - how we manage model permissions, git-based guardrails, and multi-persona interaction through what we call Mission Control - and why none of it works without a context engine underneath.
The context engine captures tribal knowledge (from Slack threads, analyst notes, business rules) as a byproduct of everyday work, giving the agent enough understanding of your business to act intelligently rather than just execute blindly. We'll demo the difference context makes: the same agent, the same task, with and without the context layer - so you can see how the quality of autonomous work degrades when the agent doesn't know what "right" looks like.
If you're building agentic systems and wrestling with how much rope to give them, this session is for you.
Level L300
Immutable Patterns of System Design; From Monolith to Agentic AI
James Eastham | Talking Serverless @ Datadog | International Speaker | Microsoft MVP
Technology is changing rapidly and it often feels like the skills you learned just a few years ago are becoming obsolete. From simple, single process apps running on-premises, through the cloud revoloution. From monoliths to microservices. Service oriented architecture to event-driven architecture. And now, we have agentic AI. As someone working on modern software, you've got a lot to think about. But really, how much has actually changed?
You still need your software to be reliable, performant and to solve a problem for your users. And regardless of what 'style' of system your building, there are some unchanging patterns that are always going to help you.
In this talk, you'll learn all about these unchanging patterns of systems design. This isn't an escoteric talk. This is a talk that is going to give you practical patterns of system design that you can take away and use in your business. Whether your working on a 20 year old monolith, working on the cutting edge of agentic AI, or whatever hype train comes next in software development. You'll have the skills to ensure your systems are always reliable, performant and solve real problems.
Level L300
The Sound of Databases
Renato Losio | Cloud Expert, AWS Data Hero, InfoQ Editor
Databases are not just about storing data. They are about time. And nothing exposes time like music. In this session, we use sound to explore how AWS databases behave under pressure. Instead of charts and traditional benchmarks, we listen.
By turning database behavior into music, we reveal how different services handle timing, consistency, and scale. Small delays, uneven performance, and unexpected pauses quickly become audible.
We will compare several AWS databases, relational and non-relational, serverless and provisioned, and let them perform. If a database can’t sing, it probably can’t scale.
Level L300
Open Standards for Agents
Ryan Cormack | Principal Engineer, Motorway
In this session Ryan will look at the various open source technologies available to us when it comes to building AI Agents and the open protocols that power them. We'll focus on how we can use AWS's open source Strands Framework to build custom agents, that can work with open protocols like Agent Client Protocol, AG UI and A2UI for building interfaces for our agents. We'll look at how we can run these agents on Bedrock AgentCore Runtime and monitor them with open standards like Open Telemetry in Cloudwatch. Finally we'll look at how Agent2Agent can allow our agents to talk to each other over http.
Notes: I'll primarily look at how AWS's Strands framework adopts open standards for running agents and how we can run and operate them on AgentCore Runtime. This is a rapidly changing landscape and the concrete specifics may change between now and October, but content will be up to date
Level L300
Taming Dead-Letter Queues: A Serverless Framework for Triage, Patch, and Replay
Chidimma Dominic Nweke | Software Engineer | Cloud-Native Systems & Applied AI
IDead Letter Queues (DLQs) are supposed to protect production systems, but in reality, they often become a graveyard; messages pile up, replays are risky, and the same failures keep repeating. Even worse, a "blast replay" can trigger a retry storm, double-processing, or a brand-new incident.
In this session, we'll build a practical AWS-native approach to DLQ remediation that's safe, observable, and repeatable. You'll see how to turn DLQs into a controlled recovery pipeline using services like SQS, Durable Functions, DynamoDB, and EventBridge, with guardrails like throttled replay, stop condition, quarantine, and idempotency.
We'll walk through a reference architecture that works not only for SQS-triggered Lambdas, but also for EventBridge and SNS failure paths, and we will cover how to generalize the same approach for DLQ-like failures from other workloads.
If you’ve ever opened a DLQ and thought "where do I even start?", this session turns that moment into an automated, measurable, and production-friendly recovery practice.
Level L300
Orchestrating a workflow in Lambda
Chris Dobson | Senior engineer, Trustpilot & AWS Community Builder
There’s a new kid on the block in the world of workflow orchestration, the Lambda Durable Function, which allows an orchestration to be created as a single Lambda Function which can run for up to a year.
-
How do you build an orchestration?
-
How much will it cost?
-
What pitfalls should you look out for?
-
Can it do everything you need?
-
How do you test or debug it?
Are just some of the questions I had about this new extensions to Lambda.
This talk will take an existing production workflow and look at how it could be built as a Lambda Durable Function from start to finish. I’ll implement the complete workflow, look at how the checkpoint/replay execution model affects this implementation, test and debug the workflow, and look at versioning all through a number of demos which have helped me answer those questions.
Level L200
Building a real-time voice agent that feels conversational, not transactional
Niall Keys | Software Engineer, Instil | AI
In 2025 we were tasked with building a real-time voice assistant for on-the-ground sales reps working in global Pharma. They were struggling to keep accurate notes after meetings, capture outcomes from conversations and update their CRM often doing this admin work in their own personal time.
In this talk we share the story of building a production-grade voice agent on AWS using Amazon Nova Sonic 2.
This application had a measurable real-world impact on work–life balance of the sales reps. However building something that feels conversational is very different from stitching together AI services.
We’ll cover the hard lessons learnt from building real-time voice applications:
- Keeping an agent on task over multi-turn conversations.
- Managing context windows.
- Handling turn detection in noisy, real-world environments.
- Architecting for conversations longer than Lambda’s 15 minute timeout.
We’ll also explore why evals and observability with CloudWatch become mission-critical when prompt tweaks and model swaps can subtly degrade behaviour in ways traditional monitoring won’t catch.
This session is for engineers building AI systems that need to feel conversational, not transactional and who are discovering that “serverless” sometimes means knowing when not to use Lambda and look at ECS Fargate instead.
Level L300
Building Secure and Efficient SaaS Platforms on AWS Serverless
Guilherme Dalla Rosa | CTO, MerCloud
Let's go on a journey through the world of multi-tenant architectures on AWS using serverless technologies. In this talk, we will uncover the key aspects of multi-tenancy, including security, tenant isolation, and performance.
We will learn how to utilise Cognito for authentication, DynamoDB to store millions of tenant-partitioned records and lambda for compute. We will also explore different deployment models and their tradeoffs, and, finally, we will learn how to implement policy-based isolation with IAM to keep our execution context tied to one specific tenant and avoid data leakage.
By the end of this talk, you will feel more confident building SaaS applications on AWS with serverless technologies and you will have learned some of the many insights that come from the AWS Well-Architected SaaS Lens.
Level L300
Security from the edge to the core: AWS Multi‑Layer Defence
Robin Ford | AWS Community Builder and Senior Technical Architect at Accenture
This session explores defence in depth on AWS, showing how security controls can be applied from the network edge through to the core of the platform. It examines layered protections across edge services, networking, and compute, as well as looking at IAM and least privilege access, and data security including isolation and encryption. Using AWS best practices and real architectural patterns, the talk demonstrates how multiple security boundaries work together to reduce risk and limit blast radius while also improving resiliency, performance and cost.
Level L200
Supporting Ukraine’s National Gen AI CoE with AWS Rapid Flexible Infrastructure
Eric Applewhite | Director | Engineering, AI & Data | Government & Public Services, Deloitte
Anastasiia Shpyt | Consultant, Deloitte
Against the backdrop of conflict, limited funds, and fragmented architecture, the CoE needed a way to rapidly launch PoCs to scale. Directly supports Ukraine's strategic objective of leveraging technology for economic growth and citizen services. Ukraine launched its national Gen AI CoE in 2024 and launch its first Open Data PoC in 2025.
Delivered Open Data Source Validator PoC in 11 weeks, reducing data set review times from 30 minutes to 2 minutes per data set. And turning a 3 year data backlog into a 12 week one. Our AWS alliance and access to AWS assets provided the critical flexibility, pace, and foundational assets to deliver a scale ready PoC. Our talk will describe the background, outcomes, approach, and critical role AWS played.
Level L100
Who orchestrates your agents? Four ways to connect them to your systems, and what each one costs
Jon Hammant | CEO, Orbital
Every enterprise wants AI agents doing real work, and every agent needs to reach the systems a business already runs on. So who works out how those systems fit together - the model, your code, or a model of your business?
This talk walks the four approaches teams are using today: a growing pile of MCP servers, integration written down as workflows, "code mode" where the model writes code on the fly, and semantic layers where a model of the business plans each query. For each, we'll show how it's built on AWS - MCP tools behind Bedrock AgentCore Gateway, Step Functions and EventBridge, AgentCore's code interpreter - what it's good at, where it breaks as the number of tools grows, and what it really costs in latency, change, governance and build effort. Including the downsides of the approach we take at Orbital. We'll detail how you can build a flexible platform that can be used by application developers who are Vibecoding new apps at a rate higher than ever before.
You'll leave with a simple way to choose the right pattern for each job, and a clearer view of why orchestration, not the model, is now what stands between agents and production.
From Classroom to Cloud: On Fear, Failure, and Finding Your Way into Tech
Maria Kourtesi | Platform & Cloud/Software Engineer, Capgemini
At 32, I decided to change career and step into tech. I sent over 200 job applications as a self-taught career changer with no tech degree, no network, and no clear roadmap. Most went unanswered. The rest were rejections.
I eventually landed a junior front-end role, and over the next seven years I worked my way to Platform Engineer. Along the way, I earned three AWS certifications and completed a Master’s in Information Systems, often studying at 5am before work while holding down a full-time job.
But the technical climb was only part of the story. I navigated dysfunctional teams that impacted my mental health, and entered male-dominated environments where I often felt like I didn’t belong. Imposter syndrome didn’t disappear; I learned to work with it.
What kept me going wasn’t talent or luck. It was persistence, the courage to ask for opportunities before I felt ready, and the people who supported me when I struggled to support myself. A mentor, a community, and a few honest conversations at the right time quietly changed the trajectory of my career.
This talk shares what career change really looks like beyond the success story: the setbacks, the slow progress, and the human support systems that make growth possible in tech.
You May Be More Ready Than You Think
Sibgha Naeem | Senior Software Engineer @ LatusGroup
Some of the biggest opportunities in our careers arrive before we feel completely ready for them.
Uncertainty can appear when we step into something new, take on greater responsibility or try to grow alongside the demands of everyday life. It does not always mean we lack ability; sometimes it means we need preparation, honest feedback, practical support or simply the chance to recognise how far we have already come.
In this personal talk, I share moments from my own journey, from choosing engineering in a small town where very few girls followed that path, to returning to higher education after seven years while raising my son, and adapting to a new professional environment.
Rather than suggesting women simply need to “be more confident”, this session explores why confidence is only part of the picture, and how support, feedback, capacity and recognising our own progress can make a meaningful difference.
The audience will leave with a practical reminder: feeling uncertain does not always mean you are not ready. Sometimes it simply means you are stepping into something new.
Why a non-linear career path is your biggest advantage
Surbhi Badhwar | Automation & AI Lead
In my talk I will walk about my career journey. The diverse roles and opportunities that helped shape my professional path. As a woman of Indian ethnicity, I will share my experiences from living in more than 16 cities across the world and in working across 2 continents. I will also talk about self limiting beliefs that hold women back at the workplace and practical examples to overcome these.
I have given a talk at AWS Cloud Women Manchester in Jun'26 on wiggly career paths and what they teach us and would love to be a part of the AWS community summit in Oct.
Leading Through Ambiguity: How Amazonians Navigate Uncertainty
In a world where 73% of UK decision-makers report increased business complexity and up to 50% of work activities could be automated by 2030, the ability to lead through ambiguity is no longer optional; it's essential. Yet 60% of businesses say employees lack the training to navigate change effectively.
This interactive session explores how to lead confidently when the path forward isn't clear. We begin by defining ambiguity and leadership, then examine how Amazon's Leadership Principles, particularly Ownership, Bias for Action, Earn Trust, and Disagree and Commit, provide a practical framework for navigating uncertainty at every level, regardless of title or seniority.
Engine Room
Workshop:
Kill the Database, Save the Platform: Chaos Engineering for a Resilient Data Layer
Rob Reid | Technical Evangelist, Cockroach Labs
Most Internal Developer Platforms still rely on databases that become single points of failure. In this hands-on workshop, you'll break a database on purpose and learn how to build a resilient, distributed data layer that survives outages.
Reliability is a core promise of every Internal Developer Platform, yet many platform teams still depend on databases that can become critical points of failure. In this interactive workshop, participants will deploy CockroachDB within a platform environment, deliberately introduce failures, and observe how a distributed SQL database maintains availability without downtime. Through live demos and guided exercises, we'll explore node failures, multi-region deployment strategies, data residency requirements, and self-service data provisioning. Attendees will leave with practical patterns for building resilient platform architectures and applying chaos engineering techniques to uncover weaknesses before they impact users.
And once your platform can survive a single cluster going sideways, the next question is how you run many of them without the operational sprawl. We'll close with a brief look at Cockroach Continuum, our new Agentic Database Cloud, and how it extends this same resilience thinking across an entire database estate - not as the focus of the session, but as a glimpse of where this pattern goes next.
Workshop:
Agentic Football Cup
Tom Ellis | Senior SA Manager at AWS
Owen Hawkins | Principal Solutions Architect, AWS
Thomas Moore | Senior Solutions Architect at AWS
You're about to build a team of AI agents, deploy them to the cloud, and watch them play live football matches — against three AWS-built AI squads — Bedrock Ballers FC (balanced), Total Attack United (extremely aggressive), and Fort Knox Athletic (extremely defensive) — or head-to-head against other teams in the room.
This isn't a typical workshop. There are no pre-baked demos to click through. You'll write real agent code, deploy it to Amazon Bedrock AgentCore, and step into the Player Portal to see your agents compete on a live 3D pitch. Every decision your agents make — pass, shoot, press, defend — comes from the logic you give them.
No AI experience required. No deep coding background needed. AWS Solutions Architects and certified partners will be on hand throughout to help you at every step. Whether you've built agents before or this is your first time, you'll walk out of here having deployed a working multi-agent system and competed with it live.
The workshop is built around three phases:
Build Your Team — Write your agent code and deploy it to Amazon Bedrock AgentCore with the help of Kiro, an agentic IDE that accelerates every part of the workflow.
Play Matches — Set up the Player Portal, register your agents, benchmark against AI opponents, and compete in tournament matches.
Supercharge Your Agents — Learn advanced techniques to iterate fast, improve your agents' decision-making, and dominate the leaderboard.
And when the final whistle blows, you'll take the same skills, tools, and patterns back to your organization — because everything you learn here maps directly to production agentic AI use cases across industries.
Along the way, you'll pick up real skills that go well beyond football:
How to design agents that reason, coordinate, and adapt in real time
How to deploy and scale agents using production-grade AWS infrastructure
How multi-agent systems work — the same patterns behind customer service bots, supply chain automation, and more
How agentic coding tools like Kiro accelerate every part of the development cycle
Your Toolkit
You'll work hands-on with a focused set of AWS services and open-source SDKs — the same tools teams use to build production agentic systems today:
Amazon Bedrock — Foundation models that power your agents' reasoning
Bedrock AgentCore — A managed runtime to deploy, scale, and monitor your agents
Strands Agents SDK — An open-source framework for building agents with minimal boilerplate
Kiro — An agentic IDE that understands your project and helps you build, debug, and iterate on agents through natural conversation
💡 Why these tools? They reflect real-world production choices made by AWS customers. By the end of this workshop, you won't just have a football team — you'll have hands-on experience building agentic solutions you can apply to any domain.
Let's get started. Your squad is waiting. ⚽
Workshop:
Building and scaling inference workloads on Amazon EKS
Preslav Draganov | AWS Consultant, Steamhaus
Join us for an immersive hands-on workshop exploring how to build and scale production-ready inference deployments on Amazon EKS using NVIDIA GPUs. As organizations move beyond experimentation to production deployment of GenAI applications, Kubernetes has emerged as a preferred platform for managing inference workloads at scale, offering robust orchestration, cost optimization, and enterprise-grade reliability.
Whether you're looking to deploy your first language model or scale existing inference workloads, this workshop will provide you with best practices and hands-on experience using industry-leading tools and frameworks. Learn directly from AWS experts who have helped organizations successfully deploy and manage large-scale GenAI infrastructure.
Through hands-on labs and real-world examples, you'll learn to master:
EKS cluster setup optimised for NVIDIA GPU workloads
Efficient model serving and scaling using vLLM
Distributed inference architecture implementation with Ray
Comprehensive monitoring and observability using Prometheus and Grafana
Best practices for production GenAI deployments on Kubernetes
Agentic AI on Amazon EKS
Who should attend: DevOps/MLOps engineers, AI/ML developers, Solution Architects, Product owners (or similar functions/titles).
Please do not forget to bring your laptops as this is a hands-on workshop.
