What is INP by LLM Engine
INP by LLM Engine shows how different large language model (LLM) services impact Interaction to Next Paint (INP)on your pages — measuring how long it takes your site to respond to user interactions when powered by AI components.
This lens helps you pinpoint whether AI-based chatbots, assistants, or personalized content engines are introducing delays when users try to interact with your page.
Only LLM engines that were active and measurable during the selected period are listed.
Why it matters: LLMs are often integrated into core experiences, but if they block the main thread or delay UI updates, your pages may feel unresponsive — frustrating users before they even get an answer.
Healthy INP by LLM Engine sample
Should you worry
In a healthy view, LLM integrations are non-blocking and responsive. You may see AI services in the list, but if they stay green, they’re not interfering with interactivity.
A healthy setup typically includes:
Non-blocking API calls triggered after the initial paint.
Lightweight components for AI-driven interfaces.
Deferred hydration or lazy-loading of LLM-driven elements.
Efficient prompt-response architecture that doesn’t stall UI updates.
If INP values stay green for all engines, your AI is fast and user-friendly.
Unhealthy INP by LLM Engine sample
When a specific LLM engine is dragging down INP, it often means:
AI UI components (e.g. chat inputs, dynamic content blocks) delay readiness.
API calls or streaming responses block main-thread rendering.
Personalization or decision-making logic locks up the interface before interaction.
JavaScript tied to LLM initialization is loaded too early or too heavily.
This is common with:
Full-page chatbots that auto-open on load.
LLM-powered tools that delay first interactions.
Complex UIs powered by delayed AI-generated content.
If a specific LLM engine shows yellow or red INP consistently, your users may be experiencing a sluggish interface caused by the AI layer.
Resolving unhealthy INP by LLM Engine
Go-to action plan to resolve an unhealthy INP by LLM Engine:
Ask Uxi to analyze your INP by LLM Engine values and suggest improvements.
Use Filters to isolate pages or user types where the issue occurs.
Simulate INP of the suspected lens to see if fixing it will resolve the INP by LLM Engine. If yes, this is where the resolution focus should be.
Use an automated INP optimization tool like INProve to improve your INP by LLM Engine values.
Once you’ve improved INP, 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.