Peregrine All case studies

Case study

JDL Automation

jdlautomation.co.uk

Every image in the library re-encoded to AVIF, with WebP behind it and the untouched original behind that. No redesign, no rebuild, and nothing deleted.

19.3%

less for a visitor to download, measured across 7 pages of the live site.

Before7.4 MB
Now6.0 MB
25images on the pages measured
59.6%off the image bytes themselves
1.4 MBremoved from an average visit
7pages weighed, not sampled

The heaviest page

Averages hide the page that actually hurts. On jdlautomation.co.uk it is /, which went from 2.5 MB to 1.4 MB — 43.3% lighter. That is the page a visitor on a phone was waiting for.

Page by page

Every page, weighed as a browser loads it

HTML, stylesheets, scripts and images together — not a lab score and not a projection. Re-runnable at any time, because the page carries both halves of its own comparison: the AVIF a modern browser takes, and the original still sitting in the <img> fallback inside it.

PageBeforeNowLighter
Home page2.5 MB1.4 MB43%
Qs961 KB961 KB0%
Uncategorized920 KB804 KB13%
Xposestatic yojt52oq920 KB804 KB13%
Blog920 KB804 KB13%
Hello world703 KB703 KB0%
Contact603 KB603 KB0%
Every page7.4 MB6.0 MB19.3%

The images alone came down 59.6%. The whole-page figure is lower because every page also carries text, layout and code, which this work does not touch — and the whole page is what a visitor waits for, so that is the number quoted at the top.

What was not done

Nothing was rebuilt, and nothing was thrown away

Originals are untouched

The AVIF and WebP files sit alongside the originals, never over them. Deactivate the plugin and the site serves exactly the bytes it did before, because those bytes never moved.

No browser is left behind

Serving uses <picture>. Anything that cannot read AVIF takes the WebP, and anything that cannot read either takes the original. Nobody sees a broken image.

The design did not change

Same theme, same layout, same photographs at the same dimensions. Put this against a screenshot from the week before and it should be indistinguishable.

Want the same measurement on your site?

The analyser fetches your real images and re-encodes them, so the figure you get is yours, not an average.

Test your site