Two days, built for engineers.
Sessions, keynotes, and breaks across every stage. Released day by day as the lineup locks in.
Where to be, and when.
- 09:30 – 10:15CupertinoEvals in AI: A Deep DiveAI Engineering & DataTejas Kumar
- 10:30 – 11:15RedmondMigration to Quantum-Resilient Cryptography: Case X-RoadCybersecurityPetteri Kivimäki
- 10:30 – 11:15Los GatosI packaged my application in a container image, and now what?Cloud, DevOps & Platform EngineeringAurélie Vache
- 10:30 – 11:15CupertinoSecuring AI Agents on Kubernetes: Identity, Sandboxes, and Policy EnforcementAI Engineering & DataRoland Huß
- 10:30 – 12:00Silicon ValleyStop guessing. Start measuring: hands-on AI observability & evalsAI Engineering & DataRocky Bhatia
- 10:30 – 11:15Palo AltoForensic DDD: Reverse-Engineering the Domain Your Legacy System Never DocumentedSoftware Architecture & Engineering ExcellenceRaj Navakoti
- 10:30 – 11:15SeattleSenior Architecture 2.0: Unlearning & Job Crafting – Stop being the ultimate bottleneck in your own codebaseEngineering careersKinga Bazior
- 11:30 – 12:15Los GatosSame Bug Twice: What Happens When AI Writes Your Code And Your TestsSoftware Architecture & Engineering ExcellenceMourjo Sen
- 11:30 – 12:15SeattleNo Framework, No Server: Making AI Agents Collaborate in One TerminalAI Engineering & DataLech Kalinowski
- 11:30 – 12:15CupertinoAI Tokenomics: Principles for Cost-Efficient GenAIAI Engineering & DataGrzegorz Wasilewski
- 11:30 – 12:15Palo Alto"I choo-choo-choose you"; or how to build modern platforms in a 200 year old industryCloud, DevOps & Platform EngineeringManfred Bjørlin
- 12:30 – 13:15CupertinoPlatforms That Don't Suck - Creating tools that teams might actually loveCloud, DevOps & Platform EngineeringKarolina Ochlik
- 12:30 – 13:15Los GatosPinpointing misconceptions with tracingSoftware Architecture & Engineering ExcellenceTomas Dambrauskas
- 12:30 – 13:15RedmondCRAcking Compliance - The EU Cyber Resilience ActCybersecurityChristian Schabetsberger
- 12:30 – 13:15SeattleMaintainability of vibe-coded application without b***tSoftware Architecture & Engineering ExcellencePiotr Śliwa
- 12:30 – 14:00Silicon Valley(Cancelled due to speaker illness)Private AI with Docker and UpCloudCloud, DevOps & Platform EngineeringPaweł Piwosz
- 12:30 – 13:15Palo AltoAgents are easy, enterprises are where they breakAI Engineering & DataKonrad Bujak
- 13:30 – 14:15Cupertino(MCP Security) - How Your Friendly MCP Tool Might Betray YouCybersecurityDaniel Ostrovsky
- 13:30 – 14:15Los GatosHow will we prompt AGI? A History of Harness Hacks.AI Engineering & DataIvan Charapanau
- 13:30 – 14:15RedmondBeyond Coding Assistants: Orchestrating the Entire SDLCAI Engineering & DataIllia Slepau
- 13:30 – 14:15SeattleI know OTel: giving your coding agents expert-level OpenTelemetry knowledgeCloud, DevOps & Platform EngineeringJuraci Paixão Kröhling
- 13:30 – 14:15Palo AltoBeyond Hello World: building production ready Go ServicesSoftware Architecture & Engineering ExcellenceIrina Branovic
- 14:30 – 15:15CupertinoAgents Propose, Git DisposesCloud, DevOps & Platform EngineeringJaroslaw Gajewski
- 14:30 – 15:15Los GatosAgile isn't dead, you're just doing it wrongEngineering careersKarolina Ochlik
- 14:30 – 15:15Palo AltoSourcecode translation as a step in Legacy ModernizationSoftware Architecture & Engineering ExcellenceLeszek Włodarski
- 14:30 – 15:15RedmondFrom GenAI Training to Production. Lessons learned from Building AI Agents for Financial Services ClientsAI Engineering & DataAnna Żółtańska
- 14:30 – 15:15SeattleMicro Frontends: From Savior to Dragon — Our JourneySoftware Architecture & Engineering ExcellenceAmir Eslamdoust
- 15:30 – 16:15CupertinoTailor Made ArchitectureSoftware Architecture & Engineering ExcellenceKarol Rogowski
- 15:30 – 16:15Los GatosBuilding Hybrid AgentsAI Engineering & DataCristina Poncela Cubeiro
- 15:30 – 16:15RedmondFrom 3GPP Spec to Live Network: Safely Deploying 6G Security in a Multi-RAT, Legacy OAM Environment.Software Architecture & Engineering ExcellencePawel Owczarski
- 15:30 – 16:15SeattleTerraform, day 1001Cloud, DevOps & Platform EngineeringPiotr Trębacz
- 15:30 – 17:00Silicon ValleySecuring AI Agents with Fine Grained AuthorizationCybersecuritySohan Maheshwar
- 15:30 – 16:15Palo AltoBuilding an AI-Native Engineering Team: Lessons LearnedAI Engineering & DataHimash Tehan
- 16:30 – 17:15CupertinoDesign Systems That Explain ThemselvesSoftware Architecture & Engineering ExcellenceSzymon Chudy
- 16:30 – 17:15Los GatosBuilding the next generation of AI developer toolsAI Engineering & DataKrzysztof Cieślak
- 16:30 – 17:15Palo AltoGitHub Actions moves to CosmosDB: data migration at internet scaleSoftware Architecture & Engineering ExcellenceBassem Dghaidi
- 16:30 – 17:15SeattleWhy Agentic AI Projects Fail and How to Make Them WorkAI Engineering & DataIlona Pietras
- 16:30 – 17:15RedmondMFA? Game over! Watch your protection collapse – liveCybersecurityChristoph Menzel
Stop guessing. Start measuring: hands-on AI observability & evals
Your AI system passed staging. Now it's in production and quietly failing. Token costs are climbing, the agent occasionally loops, and after last week's model version bump, something changed but nobody can prove what. This workshop fixes that. Working with realistic production-like scenarios, you will instrument a multi-agent workflow end-to-end, analyze real traces to surface the failure patterns invisible without observability, and build an evaluation dataset that gives you measurable baselines. You will implement LLM-as-a-judge to assess quality automatically and learn exactly where it lies to you. By the end, you will have a system health view that brings quality, latency, token cost, and reliability together in one place. You leave with a checklist of production failure modes, a practical eval setup you can adapt the following week, and a clear answer to the question most teams can't answer: is my AI system actually getting better or worse?
Save your seat before it fills.
Early pricing runs while the programme is still being finalised.