World Congress 2026 Europe Jul 9, 2026 Session details

Developers become Orchestrators: From Human-in-the-Loop to Spec-in-the-Loop

Bastian Heilemann , Stefan Bley

Treating AI as a basic copilot creates a cognitive bottleneck. Stop hand-holding algorithms. Transition to spec-in-the-loop workflows where developers orchestrate architecture and agents execute code.

Pause
Mute Enter Fullscreen
#1 about 2 min

Overview of Zeiss and the shift to agentic workflows

Moving software from human-in-the-loop to spec-in-the-loop requires understanding the organizational context.

#2 about 2 min

Digital customer experience platforms and current development processes

Existing platform engineering foundations like backstage templates provide the necessary context for introducing AI-driven development.

#3 about 2 min

Mapping ai maturity levels in software development

Transitioning from unstructured code completion to agentic workflows shifts the developer role towards defining intent and execution boundaries.

#4 about 2 min

Establishing guardrails and verification for ai agents

Reliable agentic execution requires structured artifacts like coding guidelines, architectural decisions, and strict verification steps.

#5 about 2 min

Targeting low-criticality software components for full automation

Focusing AI delegation on low-criticality services frees up developer time for high-value feature delivery.

#6 about 2 min

Structuring software specifications as a strict execution boundary

A well-defined specification must include intent, technical stack context, execution boundaries, and explicit success criteria.

#7 about 3 min

Evaluating an existing microservice for full ai readiness

Assessing a data translation webhook service reveals how much existing platform engineering and documentation is needed for AI delegation.

#8 about 2 min

Customizing ai agent skills and deploying server hooks

Utilizing tools like Google agent skills and MCP servers allows managing context windows and parsing repository graphs.

#9 about 5 min

Automating service level objective implementation with agents

An AI agent successfully translates a service-level requirement into implementation, tests, and pull requests without manual intervention.

#10 about 4 min

Key learnings and infrastructure challenges with agentic automation

Adopting agent skill frameworks improves code base understanding but requires careful infrastructure guardrails to prevent catastrophic errors.

#11 about 3 min

Balancing human system intent with automated ai execution

While AI handles the tactical execution of code generation and pipelines, humans must own systemic intent and non-functional requirements.

#12 about 3 min

Exploring complete codebase regeneration and programming language migrations

Regenerating entire services or migrating programming languages using AI proves feasible but requires robust connections to specific coding guidelines.

#13 about 4 min

Enhancing agent repository context using engineering knowledge graphs

Combining code search indices with platform engineering databases provides agents with the required context to navigate complex organizational structures.

Matching moments

4:08 min

Transitioning software engineering teams to AI-native development workflows

Florian Deter Florian Deter +4 · World Congress 2026 Europe

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann +2 · LIVE

2:54 min

Designing complex software architecture in the era of AI

Chris Heilmann +2 · LIVE

59 sec

The limitations of spec-driven development with AI

Peter Caron Peter Caron · World Congress 2026 Europe

2:09 min

Designing task boundaries between human developers and AI tools

Vera Slavnić Vera Slavnić · Europe 2026 Virtual

3:33 min

Navigating developer bottlenecks and human accountability

Werner Vogels Werner Vogels +1 · World Congress 2026 Europe

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 11:10–11:15

Outdoor Stage

Architecting the 100X SDLC: Building Production Trust into AI-Assisted Delivery

Ranjan Parthasarathy

Founder, CPTO/CEO at AXIOMSTUDIO.AI

Ranjan Parthasarathy
Open session

World Congress 2026 North America

September 23, 2026 · 13:40–14:10

Stage 2

Building an AI-Native Development Workflow

Vanessa Minik

Senior Service Delivery Engineer, GitHub

Vanessa Minik
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 2

Reinventing Testing Practices in the AI Era

Eric Deandrea

Java Champion & Senior Principal Software Engineer, IBM

Eric Deandrea
Open session

World Congress 2026 North America

September 25, 2026 · 14:10–14:40

Stage 1

The Broken Rung: How AI is Rebuilding Software Development from the Ground Up

Tomislav Tipurić

Chief Technology Officer, Nephos

Tomislav Tipurić
Open session

World Congress 2026 North America

September 24, 2026 · 16:50–17:20

Mainstage

Building AI Products vs. Building With AI

Aparna Dhinakaran, Rukmini Reddy, Tamar Bercovici

Aparna Dhinakaran
Rukmini Reddy
Tamar Bercovici
Open session

World Congress 2026 North America

September 25, 2026 · 16:50–17:20

Outdoor Stage

Beyond the Code: Human-AI Synergies in Product Development

Ajita Kanchivakam Ananth

Staff Technical Program Manager at Google

Ajita Kanchivakam Ananth