Can You Trust What Your Software Factory Ships?
October 30, 2026
In this episode of The Agentic Review podcast, Wei-Wei Wu, Co-founder and CEO of Momentic, joins Itamar Friedman and Nnenna Ndukwe to talk about AI testing, independent verifiers, and the future of QA. AI now generates code faster than humans can check it. Wei-Wei explains why the same agent shouldn’t write both the code and its tests, how AI is finally forcing teams to shift left, and why tests are becoming an implementation detail behind plain-English product specs. He also argues that change failure rate hides what customers actually experience, and that quality and taste are the real moat when code costs almost nothing to produce.
In this episode of The Agentic Review podcast, Wei-Wei Wu, Co-founder and CEO of Momentic, joins Itamar Friedman and Nnenna Ndukwe to talk about AI testing, independent verifiers, and the future of QA. AI now generates code faster than humans can check it. Wei-Wei explains why the same agent shouldn’t write both the code and its tests, how AI is finally forcing teams to shift left, and why tests are becoming an implementation detail behind plain-English product specs. He also argues that change failure rate hides what customers actually experience, and that quality and taste are the real moat when code costs almost nothing to produce.
Key Takeaways:
Key Takeaways:
- Why the agent that writes your code shouldn’t write your tests
- How AI turned shift-left from a slogan into a requirement
- Why tests are becoming executable product specs written in plain English
- How agents scale exploratory testing past manual bug bashes
- What a bug report needs before it’s worth an engineer’s time
- Why change failure rate misleads teams shipping 100x more code
Wei-Wei Wu is the Co-founder and CEO of Momentic, an agentic quality platform for web and mobile software. Before founding Momentic, he worked across product engineering, frontend infrastructure, observability, reliability, and developer productivity at Qualtrics, WeWork, Nashi, and more. That background shaped his focus on scaling engineers through tooling. Today, Wei-Wei works on the bottleneck that AI coding has exposed: helping teams build software factories that verify code accurately, quickly, and at a reasonable cost.
Episode resources
- Wei-Wei Wu on LinkedIn : https://www.linkedin.com/in/hungweiwu/?isSelfProfile=false
- Momentic: https://momentic.ai/
- Itamar Friedman on LinkedIn: https://www.linkedin.com/in/itamarf/
- Nnenna Ndukwe on LinkedIn: https://www.linkedin.com/in/nnenna-ndukwe/
- Qodo Website: https://www.qodo.ai/?utm_source=podcast&utm_medium=show-notes&utm_campaign=the-agentic-review-show
The Agentic Review is handcrafted by our friends over at: fame.so