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.
- 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 – 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
- 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 – 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 – 14:15Palo 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
- 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
Securing AI Agents on Kubernetes: Identity, Sandboxes, and Policy Enforcement
AI agents call external APIs, access databases, and execute code on behalf of users. With the Model Context Protocol (MCP) becoming the standard for how agents discover and invoke tools, every MCP tool call is a security boundary crossing. The agent holds the user's intent, the MCP server holds the capability. The question is: who decides what the agent is allowed to ask for? This talk covers three operational patterns for securing agentic MCP interactions on Kubernetes. Workload identity with SPIFFE gives each agent a cryptographic identity without shared secrets, so MCP servers know exactly which agent is calling. Token exchange for delegated access lets agents act on behalf of users without holding their credentials: the agent presents its own identity, the platform issues a scoped token that the MCP server can verify and constrain. Kernel-enforced sandboxing with NVIDIA's OpenShell wraps the agent in per-binary network policies and L7 HTTP/MCP traffic inspection, so even a compromised agent cannot reach MCP servers it was not granted access to. Walk away knowing how to secure the MCP tool chain from agent identity to server-side verification, and why most agent deployments get this wrong.
Save your seat before it fills.
Early pricing runs while the programme is still being finalised.