Testing Real World Gen AI Systems
At the AI Verify Foundation, we focus on making AI reliable through effective testing. In the real world (hospitals, airports, banks… not just on chatbots and social media).
Join us for a community event on the 30th of May, as we bring together lessons from two of our biggest initiatives in this space: the world’s first GenAI technical testing pilot and the AILuminate safety benchmark together with ML Commons.
In the room will be founders of 10 local and overseas AI testing startups and 100+ other GenAI practitioners from across the Singapore. We expect to cover 4 key themes
· Deciding what to test
· Synthetic test data: (when) does it work?
· Looking under the hood: the importance of "observability" through the app pipeline, particularly for agentic workflows
· Scaling automated testing with effective human feedback
The team from ML Commons and their local partners at NUS will also walk us through their journey in adapting the AIluminate safety benchmarks for other languages.
Spaces are limited, so please express your interest early. Confirmed participants will be notified closer to the date of the event.
Arrive early to fuel up on caffeine!
Let’s get cracking!