WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

The Last Mile of AI: From Prototype to Production

Clemens Wasner , Holger Hammel , Martin Remmelgas , Max Jacobson , Marius Cosareanu

Developers now spend 95% of their time reviewing AI-generated code rather than writing it. Learn how top engineering teams are overhauling testing to conquer AI’s chaotic last mile.

Pause
Mute Enter Fullscreen
#1 about 2 min

Company backgrounds and engineering organization scale

An overview of the panelist software products and their respective engineering team sizes.

#2 about 3 min

Personal and professional workflow changes from large language models

How coding agents and recent models have accelerated delivery and simplified information retrieval.

#3 about 4 min

Adapting team structures and agile workflows for agentic tools

Why organizations must reinvent workflows and adopt lean methods to leverage AI effectively.

#4 about 3 min

Blurring roles and cross-functional expectations in engineering pods

How AI tools blur traditional job boundaries and enable engineers to handle broader scopes of work.

#5 about 3 min

Reviewing and adapting machine-generated code in smaller teams

The shifting discipline of maintaining codebases when human reviewers evaluate non-human architectural models.

#6 about 1 min

Productivity amplification and technical debt risks with AI

How AI magnifies both the output of strong developers and the complexity introduced by weaker ones.

#7 about 3 min

Transitioning toward AI-first coding and managing token costs

The push to maximize coding agent usage while balancing the rising costs of frontier models.

#8 about 3 min

Balancing developer autonomy with the adoption of coding agents

Why mandating AI tool usage can frustrate engineers who value deep technical flow over managing unreliable agents.

#9 about 3 min

Creating reliable feedback loops and automated testing for AI

Applying mutation testing and deterministic checks to prevent agents from introducing unreviewed complexity.

#10 about 3 min

Implementing property-based randomized testing for generated code

Using continuous adversarial testing to align AI-generated logic with actual business invariants.

#11 about 5 min

Treating plain English specifications as the new compiler

Why comprehensive specifications and end-to-end testing are required to safely integrate black-box AI logic.

#12 about 2 min

Exploring progressive deployments and production monitoring

The potential for making highly granular iterative changes directly to production relying purely on monitoring.

Matching moments

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann Chris Heilmann +2 · LIVE

2:52 min

Moving beyond demos to build production-ready software

Seth Webster Seth Webster · World Congress 2026 Europe

4:08 min

Transitioning software engineering teams to AI-native development workflows

Florian Deter Florian Deter +4 · World Congress 2026 Europe

3:33 min

Navigating developer bottlenecks and human accountability

Werner Vogels Werner Vogels +1 · World Congress 2026 Europe

2:03 min

Addressing institutional inertia and AI pilot failures

Alexandre Guenoun Alexandre Guenoun +3 · World Congress 2026 Europe

1:59 min

Shifting from AI experimentation to real-world production

General Program · World Congress 2026 Europe

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

Running AI at Scale: The Secret Ingredients thumbnail
30:04
World Congress 2026 Europe • 3 months ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

What Production Knows: Closing the Loop Between AI Agents and the Systems They Build thumbnail
26:33
World Congress 2026 Europe • 3 months ago

What Production Knows: Closing the Loop Between AI Agents and the Systems They Build

May Walter

The AI-Ready Stack: Rethinking the Engineering Org of the Future thumbnail
28:09
World Congress 2025 • about 1 year ago

The AI-Ready Stack: Rethinking the Engineering Org of the Future

Alex Laubscher, Jan Oberhauser, Keno Dreßel, Mirko Novakovic

AI Killed DevOps... What Now? - Lee Faus thumbnail
57:43
Coffee With Developers • 10 months ago

AI Killed DevOps... What Now? - Lee Faus

Lee Faus

AI-Enabled Organisations: From Strategy to Practice thumbnail
28:10
World Congress 2026 Europe • 3 months ago

AI-Enabled Organisations: From Strategy to Practice

Benedikt Höck, Chris Daden, Lars Rogge, Damiana Casile

Shipping with Confidence: Observability and Quality at Scale thumbnail
31:24
World Congress 2026 Europe • 3 months ago

Shipping with Confidence: Observability and Quality at Scale

Christian Heilmann, Mirko Novakovic, Prince Kohli, Daniel Gebler

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.