Ronny Kohavi and GrowthBook cover the A/B testing best practices for designing experiments that drive long-term growth.
Stop guessing what works and start knowing: A/B testing transforms hunches into data-driven decisions, turning every change on your website from a risky bet into a calculated experiment that can boost conversions without spending more on traffic.
Khan Academy went from vibes-based prompt testing to running A/B experiments on their AI tutor, Khanmigo, in production. Kelli Hill shares the journey, including a fascinating iterative case study on latency vs. math accuracy.
Stop relying on "vibe checks" to ship GenAI. While AI Evals answer "can the model do the job?", only A/B testing answers "do users care?" Discover how to combine offline evaluation with online experimentation to build a reliable pipeline for shipping LLM features.
Why optimizing for short-term A/B test wins can degrade user trust and product quality. A look at common dark
Only 10–30% of experiments produce a clear winner — and that’s not a problem, it’s reality. This article shows how high-performing teams design experiments to learn faster and make better decisions, even when results are neutral.
Most AI coding tools today help teams build faster, but they don’t provide the feedback needed to know what’s worth building. Feedback loops—drawn from millions of experiments—will be the next breakthrough in agentic coding, making AI smarter, faster, and more valuable to every software team.
Most holdouts measure only shipped features. Ours measure everything—including failed experiments. This technical deep dive reveals why we chose reality over clean rooms, and how we built it.
Many teams ship features weekly but struggle to measure their true cumulative impact. Holdouts in GrowthBook provide a simple way to maintain a control group across multiple features, answering the critical question: What did all this shipping actually do to our key metrics?
GrowthBook 4.0 includes a huge number of new features and updates. Continue reading for a full list of changes.
GrowthBook provides you with 3 different types of experimentation for different purposes: Bandits for picking a winner among many, Safe Rollouts for releasing safely, and Experiments for learning.
A platform builder discovers why experimentation tools need to become more fluid. How MCP and conversational AI are creating experimentation's ambient era.
In under two minutes, GrowthBook can be set up and ready for feature flagging and A/B testing, whether you use our cloud or self-host.
