How AI Agents Tripled Our Test Coverage on a 1.8M-Line iOS Codebase
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
What happens when your AI coding agent tries to cheat CI? Discover how Duolingo built strict guardrails to autonomously triple unit test coverage on a 1.8-million-line iOS codebase.
Checking access…
Playback and chapters load privately for Free videos.
Matching moments
More from World Congress 2026 North America
Upcoming sessions on this topic
Starts in 5 days
Conference India 2026
November 25–26, 2026
Bengaluru, India
-
The 200,000 line code repository: My AI wrote 1000 lines. I needed 100.
Hardik Gupta · IBM
Thu 26 Nov · Stage 1 - powered by IBM
-
Ship Happens: Guardrails for AI-Written Code
Anthony Nguyen · LaunchDarkly
Wed 25 Nov · Stage 3 - powered by GitHub
-
Your AI Wrote the Code. Who Vouches for It?
Siddharth Joshi · GitHub
Wed 25 Nov · Stage 3 - powered by GitHub
Related videos
Related articles
TP
Thomas Pamminger
DC
Daniel Cranney
CH
Chris Heilmann
JC
Jenna Charlton
DB
David Burns
BB
Benedikt Bischof
From learning to earning
Jobs that call for the skills explored in this talk.
5 days ago
Staff Software Engineer, Copilot Code Review
GitHub
Beverly Hills, CA, United States
Experienced
Remote
Ruby
Golang
Github
10 days ago
Principal Software Engineer, Copilot Code Review
GitHub
Beverly Hills, CA, United States
Expert
Remote
Ruby
Golang
Github
26 days ago
Principal Software Engineer, Copilot Code Review
GitHub
San Francisco, CA, United States
Expert
Ruby
Golang
Github
18 days ago
•
Senior Software Engineer - Semantic Data Lake (Open)SDE3
WEX
Bengaluru, India
Expert
Hybrid · 4 days on-site
Scala
Python
Terraform
2 months ago
•
Senior Mobile Engineer-iOS
Expedia
Seattle, United States
Expert
$184k–258k
Hybrid · 3 days on-site
iOS
21 days ago
Machine Learning Engineer 2
Twilio
San Francisco, CA, United States
$128k–160k
Remote
Twilio
Backend
Raw Data