Make speed measurable.
Useful performance work starts with the experience your visitors have and the part of the page that causes delay. A CDN can improve delivery, while server processing, image choices, and browser work still need attention. Measure those stages separately so each change has a clear purpose.
Build a baseline you can compare
Choose representative pages: the homepage, a content page, a large image page, and an important interaction. Record the tested URL, device, location, network conditions, and cache state. Repeat measurements under comparable conditions instead of treating a single unusually fast or slow result as typical. Save the evidence before changing configuration.
Laboratory tests help reproduce a problem and inspect a proposed fix. Field measurements reflect the devices, connections, and interactions of real visitors. Use both when available. A laboratory page load does not describe every interaction that happens during a longer visit.
Read the metrics in context
- Largest Contentful Paint: indicates when the page's largest eligible visible content element renders.
- Interaction to Next Paint: describes responsiveness to user interactions across a visit.
- Cumulative Layout Shift: measures unexpected movement that affects visual stability.
- Time to first byte: helps investigate response delay, including connection and request stages.
These measurements answer different questions. Faster delivery of a script does not remove the time the browser spends executing it. Reserving space for an image can prevent movement without changing its download speed. Follow the full path from requesting a resource to showing useful content and responding to a visitor.
Match the change to the bottleneck
A CDN can help when reusable resources travel from a distant origin. Image optimization can help when the transferred image is larger than the display requires. Earlier resource discovery can help when a crucial image request starts late. Application work needs investigation when an uncached response waits on processing or another service.
Prioritize a change with an observable outcome, such as reducing a hero image's transfer size while preserving appearance. Recheck correctness, layout, and interaction behavior alongside timing. Then compare the same page under the same conditions. The Core Web Vitals guide explores these distinctions, while our delivery testing checklist helps separate browser caching from edge behavior. Keep improvements that survive representative testing and monitor the paths most important to your audience.