Over the last couple of months, our customer conversations on AI experimentation have increased dramatically (as you may have guessed), so we decided the time is now to dive deep into how experimentation can only benefit the development of AI features.
Enjoy this on-demand viewing and we hope you can join us live in the future!
Got AI on the brain? Statsig can help you run experiments with AI apps, using our recent launch of Statbot. During this Learning Lab we'll teach you how to record important model inputs and outputs, such as prompt, model choices, cost, and latency.
Additionally, we'll provide some tips on how to measure your application's performance and interpret the results to make data-driven decisions.
Thanks to our support team, our customers can feel like Statsig is a part of their org and not just a software vendor. We want our customers to know that we're here for them.
Migrating experimentation platforms is a chance to cleanse tech debt, streamline workflows, define ownership, promote democratization of testing, educate teams, and more.
Calculating the right sample size means balancing the level of precision desired, the anticipated effect size, the statistical power of the experiment, and more.
The term 'recency bias' has been all over the statistics and data analysis world, stealthily skewing our interpretation of patterns and trends.
A lot has changed in the past year. New hires, new products, and a new office (or two!) GB Lee tells the tale alongside pictures and illustrations:
A deep dive into CUPED: Why it was invented, how it works, and how to use CUPED to run experiments faster and with less bias.