Use ICE and PIE frameworks to rank objectively. Focus resources on tests with highest potential impact, not just easy wins.

You can't run every experiment at once. Limited time, budget, and traffic force trade-offs. Prioritisation frameworks like ICE (Impact, Confidence, Ease) and PIE (Potential, Importance, Ease) score experiments objectively so you're not guessing. This removes politics and gut feel from the decision. The highest-scoring experiments get resourced first. This chapter shows you how to score experiments consistently and build a prioritised testing queue.
Execute tests with proper controls. Avoid peeking early. Monitor external factors. Maintain experiment integrity start to finish.
Random experiments waste time and budget. A structured framework ensures every test teaches you something, even when it fails. Decide what to test, design experiments properly, analyse results accurately, and share learnings so the whole team gets smarter.
See playbook
Compare two versions of a page, email, or feature to determine which performs better using statistical methods that isolate the impact of specific changes.
Structure experiments around clear predictions to focus efforts on learning rather than random changes and make results easier to interpret afterward.
Systematically rank projects and opportunities using objective frameworks, ensuring scarce resources flow to highest-impact work.
Identify and leverage limitations as forcing functions that drive creative problem-solving and strategic focus.