What is CLS by LLM Engine
CLS by LLM Engine shows how different large language model (LLM) engines contribute to layout instability during page load, as measured by Cumulative Layout Shift (CLS).
This lens helps you identify which AI-powered services—such as chatbots, content generators, or personalization engines—may be causing elements to move unexpectedly, disrupting the user experience.
Only LLM engines that were active and measurable during the selected period are included.
CLS is a Core Web Vital that tracks visual stability and how much the layout shifts while the page is loading.
Healthy CLS by LLM Engine sample
In a healthy view, LLM engines contribute little to no layout instability. They may be listed, but they won’t appear in yellow or red.
A well-optimized setup typically includes:
Reserved space for LLM-generated content that avoids layout jumps.
Asynchronous rendering of AI elements after primary content is painted.
Smart loading strategies that don’t inject or shift visible elements after load.
If CLS values are green for all LLM engines, it means your AI integrations are visually stable and user-friendly.
Unhealthy CLS by LLM Engine sample
When an LLM engine negatively affects CLS, it often causes visible shifts after the page starts rendering. Common reasons include:
Late-injected chat windows or assistants shifting existing content.
Dynamic AI content loading into containers that don’t reserve space upfront.
Personalization elements modifying layout dimensions after the user starts interacting.
Examples of high-impact cases:
AI chatbots expanding near the bottom or corner of the viewport.
Personalized banners or product carousels being injected too late.
LLM-powered content changing the height of containers without animation or space reservation.
If a particular LLM engine consistently shows red or yellow CLS values, it's a signal to revise how its output is introduced to the page.
Resolving unhealthy CLS by LLM Engine
Go-to action plan to resolve an unhealthy CLS by LLM Engine:
Ask Uxi to analyze your CLS by LLM Engine values and suggest improvements
Use Filters to isolate pages and user journeys where instability is high.
Simulate CLS of the suspected lens to see if fixing it will resolve the CLS by LLM Engine. If yes, this is where the resolution focus should be.
Use an automated CLS optimization tool like Navigation AI to improve your CLS by LLM Engine values
Once you’ve improved CLS, set an alert to be the first to know if it starts worsening again.
Try it yourself
Discover how your website performs with real user data.