World Congress 2026 Europe Jul 9, 2026 Session details

5 things I wish I hadn’t done building my AI agent

Shachar Azriel

Assuming a smarter model will automatically fix your AI agent is an expensive trap. Uncover five costly engineering and product mistakes to avoid when scaling AI for production.

Pause
Mute Enter Fullscreen
#1 about 2 min

Chasing product market fit in AI development

AI development creates a false sense of ease when striving for rapid viral growth and revenue.

#2 about 3 min

Building AI agents for software development life cycles

AI tools can automate maintenance tasks like code review and production monitoring to reduce developer friction.

#3 about 5 min

Defining and measuring success for AI coding agents

Capturing transaction outcomes like acceptance, ignorance, and explicit rejection reveals true product viability.

#4 about 4 min

Meeting developers in their existing workflow environments

Forcing developers into a new interface creates friction that prevents product adoption despite strong features.

#5 about 4 min

Protecting the product from silent language model updates

Relying on upstream language models introduces instability that requires strict operational guardrails and benchmarking.

#6 about 3 min

Deconstructing large agent workflows to control infrastructure costs

Analyzing pull requests at scale requires routing complex tasks to robust models and simpler tasks to cheaper alternatives.

#7 about 3 min

Rejecting extreme hustle culture in AI software engineering

Building a sustainable and resilient company requires prioritizing personal well-being over unsustainable sprint mentalities.

Matching moments

2:34 min

Balancing developer autonomy with the adoption of coding agents

Clemens Wasner Clemens Wasner +4 · WWC Europe 2026

4:06 min

Real-world case study of AI agents causing quiet instability

Vera Slavnić Vera Slavnić · Europe 2026 Virtual

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann +2 · LIVE

3:33 min

Navigating developer bottlenecks and human accountability

Werner Vogels Werner Vogels +1 · WWC Europe 2026

4:15 min

Security integration and AI skepticism in developer tooling

Chris Heilmann +2 · LIVE

7:07 min

Exploring AI agent usage within the software engineering industry

Chris Heilmann +2 · LIVE

Upcoming sessions on this topic

Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Dor Cohen, Yoav Gal

Dor Cohen
Yoav Gal
Open session

World Congress 2026 North America

Designing APIs That Survive AI Agents at Scale

Phani Pendurthi

Mastercard, Principal Software Engineer

Phani Pendurthi
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit
Open session

World Congress 2026 North America

Agents Can't Iterate Against Tests That Lie

Rocky Warren

Senior Staff Software Engineer at Clipboard

Rocky Warren
Open session

World Congress 2026 North America

Evals Are Infra: Building AI Systems Developers Can Actually Trust

Phoebe Wang

Member of Technical Staff at OpenAI

Phoebe Wang
Open session

World Congress 2026 North America

Agentic Drift: keeping pace with your agents

John Coghlan

Senior Director, Developer Advocacy at GitLab

John Coghlan