PLUGIN SETUP
Start using Google PageSpeed Insights in ChatGPT
Add Adzviser to ChatGPT and enter what you want to research.
No source login needed
No account authorization is required because Google PageSpeed Insights uses public data.
Install Adzviser in ChatGPT
Open Adzviser in ChatGPT's plugin directory, install it, and sign in to your Adzviser account when asked.
Open Adzviser in ChatGPT ↗Ask your first Google PageSpeed Insights question
In ChatGPT, enter the page URL you want to test, choose mobile or desktop, and ask which performance issues to fix first.
CONVERSATION FLOW
Turn Google PageSpeed Insights data into clear next steps in ChatGPT
Start with the results, focus on the decision in front of you, and keep asking follow-up questions in the same conversation.
Review recent performance
Get a concise snapshot of your page's Core Web Vitals health. Ask for a compact table and make the reporting period clear.
See the “Core Web Vitals Summary” promptFocus on a decision
Identify what is slowing your Largest Contentful Paint and how to fix it. Ask ChatGPT to compare the options, supporting evidence, and possible downsides.
See the “LCP Optimization Plan” promptAsk a follow-up
Compare Core Web Vitals and scores across desktop and mobile. Ask what may explain the result, what evidence is missing, and what to examine next.
See the “Desktop vs Mobile Comparison” promptCHATGPT STARTERS
Start with a quick check, then analyze Google PageSpeed Insights
First, confirm ChatGPT can access the right data. Then ask a detailed question and follow up on the recommendation that matters most.
Run PageSpeed Insights for https://example.com on mobile. Return the performance score, LCP, INP, CLS, TTFB, and whether each field metric is Good, Needs Improvement, or Poor.
Identify what is slowing your Largest Contentful Paint and how to fix it.
Analyze the Google PageSpeed Insights data for the URL I provide. Focus on Largest contentful paint (LCP) and Largest contentful paint (Lab test result) by Device type, alongside Time to first byte (TTFB) and the LCP assessment. Where LCP is not "Good", explain the likely causes (slow TTFB, render-blocking resources, large images) and recommend a prioritized list of fixes to bring LCP under 2.5s.
Keep the same data source and time period. Which recommendation should I prioritize, what results support it, and what should I review before acting on it?
