World Congress 2026 North America • Sep 26, 2026 • Session details

21 Experiments in Six Weeks: A Playbook for Improving Your AI Agent

Sofia Rest

Think upgrading to a smarter model automatically improves your AI agent? Sentry ran 21 A/B tests in six weeks and discovered that more expensive models can actually hurt performance.

Starting at 0:02 · Watch from the beginning

21 Experiments in Six Weeks: A Playbook for Improving Your AI Agent thumbnail

Checking access…

Playback and chapters load privately for Free videos.

Matching moments

2:40 min

Reviewing live performance of self-correcting AI engineering agents

Ingo Eichhorst Ingo Eichhorst · World Congress 2026 Europe

2:28 min

Introduction to building reliable AI agents in production

Max Tkacz Max Tkacz · World Congress 2025

4:06 min

Debating the reliability of AI agents for quality assurance

Haimantika Mitra Haimantika Mitra +2 · LIVE

1:55 min

Shifting developer workloads and realistic AI productivity gains

Julia Kordick Julia Kordick +2 · LIVE

2:37 min

Implementing practical scrum adjustments to orchestrate AI usage correctly

Vera Slavnić Vera Slavnić · Europe 2026 Virtual

3:06 min

Key takeaways for reliable AI agent testing

Sebastian Messingfeld Sebastian Messingfeld · World Congress 2026 Europe

Upcoming sessions on this topic

Starts in 5 days

Conference India 2026

November 25–26, 2026

Bengaluru, India