What is PLS by LLM Engine
PLS by LLM Engine shows how fast your website feels to load for users coming through different large language model (LLM) engines — such as AI tools or chatbot platforms that send traffic to your site (e.g., ChatGPT, Gemini, Claude).
As more users rely on AI for discovery, these models often open links in new tabs or embedded browsers. Understanding how these engines influence perceived load speed (PLS) helps ensure a consistent user experience for this growing segment.
Healthy PLS by LLM Engine sample
Should you worry
A healthy PLS by LLM Engine view shows that users arriving via different AI platforms experience quick perceived load times. There’s no major drop-off in engagement, and performance remains stable regardless of which model referred the traffic.
This suggests your site handles these new discovery surfaces well and leaves a good first impression.
If users referred by certain LLM engines consistently experience slow perceived load speeds. AI-referred users often come with high intent (they clicked on a model-generated suggestion), but a sluggish experience can lead to bounce or loss of trust in your brand.
This performance dip may stem from embedded rendering environments or from specific script behavior that loads differently in these contexts.
Unhealthy PLS by LLM Engine sample
An unhealthy distribution may show one or more engines — like embedded ChatGPT browsers — consistently resulting in slower perceived load speeds. These experiences may be degraded due to how content is rendered or delayed third-party interactions.
It’s crucial to treat LLM-referral traffic as first-touch discovery and optimize for speed and clarity right away.
Resolving unhealthy PLS by LLM Engine
Go-to action plan to resolve an unhealthy PLS by LLM Engine:
Ask Uxi to analyze your PLS by LLM Engine and suggest improvements.
Use Filters to isolate sessions with items in the cart and check which pages have the highest PLS with the most traffic.
Simulate LCP of the suspected lens to see if fixing it will resolve the PLS by LLM Engine. If yes, this is where the resolution focus should be.
Use an automated optimization tool like Navigation AI to improve your PLS by LLM Engine.
Once you’ve improved PLS, 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.