"Gleipnir team on IBM Bob 2.0 hackathon Hackathon"
Team Idea
We are building an AI agent that find flaky tests in a codebase, and tells why they fail randomly, and fixes them. For this, the test suite will be run under varied conditions to statistically confirm which tests are truly flaky, then dispatches subagents to diagnose the root cause (could be timing issues, shared state, race conditions, or unstable external calls). Then it will suggests concrete code fixes and gives a simple dashboard showing how many hours your team is losing each week and how much of that time got reclaimed.
Team Members
Mahnoor Amir
Mano_78
Mareeha Nadeem
mareeha
Data Science Student
Submission
Submission draft in progress