Agents Can't Iterate Against Tests That Lie
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Flaky tests forced one platform's AI agents to blindly add useless timeouts. Discover how feeding agents deep observability traces transforms superficial guesses into durable backend refactors.
Checking access…
Playback and chapters load privately for Free videos.
Matching moments
More from World Congress 2026 North America
Related videos
Related articles
DC
Daniel Cranney
TP
Thomas Pamminger
DC
Daniel Cranney
CH
Chris Heilmann
IK
Igor Khokhriakov
CH
Chris Heilmann
From learning to earning
Jobs that call for the skills explored in this talk.
26 days ago
Senior AI Developer
PwC
United States
Expert
Remote
Docker
Github
Fastapi
about 2 months ago
Staff Software Engineer, GitHub Intelligence (Copilot Agents)
GitHub
San Francisco, CA, United States
Experienced
Ruby
Golang
Github
2 months ago
MLOps AI Engineer
TeamViewer Germany GmbH,
Austin, TX, United States
Expert
Caching
Routing
Standard Sql
about 1 month ago
•
Verified
Staff Software Engineer, Agentic Platform
Docker, Inc.
Seattle, United States
Expert
Remote
Cloud (AWS/Google/Azure)
about 2 months ago
•
Verified
Senior AI/ML Engineer
PagerDuty
Lisbon, Portugal
Expert
Remote
AI Frameworks
AI-assisted coding tools
15 days ago
•
Verified
Principal Software Engineer (m/f/x)
Dynatrace
Graz, Austria
Expert
€90k–112k
Remote
Java
Agentic AI