# Run and track PageSpeed tests with ChatGPT dots

> Tracking PageSpeed scores with ChatGPT dots means giving your always-on dot a standing job: read the stored PageSpeed history of your sites through the xSpeed Hub app, report what moved, and stop to ask before any fresh test.

Page: https://xspeedcache.com/agent/chatgpt-dots/pagespeed-tests/
Last updated: October 2026

A dot is the ChatGPT agent you leave running, so PageSpeed fits it as a habit rather than a one-off question. Ask it once, in plain words, for a weekly report: read get_score_history for each site, compare the newest mobile and desktop runs with the ones before, and post a short list of anything that dropped, with LCP, CLS and TBT beside the score. The dot schedules it, each run appears in the conversation, and you change the timing from Recent activity in its profile or the Scheduled section in ChatGPT. The Hub has no scheduler for agent prompts, so the timer is the dot's.

The report is only as fresh as what is stored. get_score_history reads the PageSpeed Insights and GTmetrix runs the plugin saved on each site and starts nothing, and the Hub does not run PageSpeed tests on a timer, so a quiet week can repeat last week's numbers. When a site does show a drop, the next step is run_speed_test, a real PageSpeed Insights run from the Hub, mobile or desktop, which takes up to about two minutes and spends a shared allowance. Its result goes to the Hub's own report history, the Reports tab, so next week's history read may not include it. run_benchmark, the cached against uncached timing, is quicker and carries no Lighthouse score, so ask the dot to keep it on a separate line.

The dot reaches the Hub through the same xspeedhub app you created in ChatGPT developer mode, because OpenAI shares plugin permissions across dots and ChatGPT. Check under Customize, then Plugins, that xspeedhub is listed before you hand over the job, since OpenAI notes the apps available to a dot may differ. A dot comes with OpenAI's defaults for which actions need your approval, and Custom rules change that for actions you describe, which is where the speed test belongs.

## Set up ChatGPT dots once

### 1. Put your sites in xSpeed Hub

Sign in at app.xspeedcache.com with Google or email; the Hub is free and has no site cap. Then connect each WordPress site from its own dashboard: click Connect Hub in the xSpeed Cache top bar, then Connect via xSpeed Hub. Each site needs the free xSpeed Cache plugin.

### 2. Create the xspeedhub app in ChatGPT

In ChatGPT on the web, turn on Developer mode under Settings, Security and login. Open Plugins, select the plus button and create a developer-mode app named xspeedhub with this URL and OAuth. Click Scan Tools, approve access on the xSpeed Hub page that opens, then click Create. If ChatGPT already has the app, skip this step. On a Business workspace only an admin or owner can turn on developer mode and publish the app.

```
https://app.xspeedcache.com/xspeed/mcp
```

### 3. Check that your dot can see it

OpenAI says plugin permissions are shared across dots and ChatGPT. Open your dot's profile, then Customize and Plugins, and check that xspeedhub is there. That screen uses the shared ChatGPT settings, and OpenAI notes the apps available to a dot may differ, so confirm it before you hand over a task.

```
Dot profile  >  Customize  >  Plugins  >  xspeedhub
```

### 4. Add a custom rule for site changes

Under Customize, Custom rules, describe the action and pick a behavior: Take action without asking, Take action if pre-approved, Ask before taking action, or Hand off to you. Add a rule that covers purging a cache, changing settings or running a speed test through xSpeed Hub, and choose Ask before taking action.

```
Customize  >  Custom rules  >  xSpeed Hub changes: Ask before taking action
```

Full setup: https://xspeedcache.com/agent/chatgpt-dots/

### Before you send a prompt that changes something

Reads change nothing on your sites, though contact_support emails xSpeed support. Writes run once your connection allows them, so your client's approval prompt and a read-only connection (the token's Read-only everywhere switch, or a Viewer sign-in) are the gates that matter. In a ChatGPT chat, write actions from a developer-mode app need your confirmation by default, and ChatGPT treats a tool without a read-only annotation as a write. xSpeed Hub's tools carry no such annotation. A dot comes with OpenAI's defaults for which actions need approval, and Custom rules let you set, for an action you describe, Take action without asking, Take action if pre-approved, Ask before taking action or Hand off to you. xSpeed Hub has no confirmation step of its own, so a rule that lets your dot act without asking runs a purge or a settings change as soon as your connection allows writes. Keep xSpeed Hub changes on Ask before taking action. For read-only access, sign in as a Viewer member of the workspace; the connection token's Read-only everywhere switch does not apply, because the app signs in with OAuth.

## Prompts

- Every Monday, use xSpeed Hub to read the PageSpeed history for each site and post any site whose mobile or desktop score dropped. Do not run new tests.
- Using xSpeed Hub, which of my sites has the oldest stored PageSpeed run, and how old is it?
- With xSpeed Hub, run one mobile test on the site this week's report flagged and compare it with its stored run.

## Example session

```
You: Every Monday morning, use xSpeed Hub to read the PageSpeed history for my sites and post any drops. History only.
Agent: Scheduled for Monday mornings, history only. Running the first one now.
  → list_sites [read-only]: 3 sites: shop, blog, docs
  → get_score_history(site: shop) [read-only]: latest mobile 54 (4 days ago), previous 61; LCP 4.1 s against 3.4 s
  → get_score_history(site: blog) [read-only]: latest mobile 68, previous 67; desktop 88, previous 88
  → get_score_history(site: docs) [read-only]: latest mobile 73 (5 weeks ago), previous 73
Agent: shop mobile fell seven points, mostly on LCP. blog is flat. docs has no run newer than five weeks, so its line says nothing new. A fresh mobile test on shop would confirm the drop and uses shared allowance. Run it now?
You: Yes, just shop.
  → run_speed_test(site: shop, strategy: mobile) [uses quota]: mobile score 56, LCP 3.9 s, TBT 310 ms, saved to the Hub report history
Agent: shop is 56 on a fresh run, so the drop is real and LCP is the metric to chase. The Monday runs stay history only.
```

## How it works

1. **Read before you test**: get_score_history returns the stored PageSpeed Insights and GTmetrix runs for a site: the score per run, with LCP, FCP, CLS, TBT, Speed Index and TTFB, mobile and desktop. It starts nothing. The Hub tells the agent to use it whenever you ask what your score is, or whether it improved, because a new test spends a shared allowance.
2. **Run a new test when you need one**: run_speed_test runs a real PageSpeed Insights audit on the site from the Hub and returns the score, the Core Web Vitals and the top opportunities. strategy is mobile (the default) or desktop, and one call tests one of them. It can take up to about 2 minutes, so the agent should say it is running before it calls.
3. **Test the other device**: Mobile and desktop scores differ, often by a lot. For both, the agent makes two calls, one per strategy. A failure is reported with its reason: PageSpeed not configured, quota reached, a timeout, or a site the audit cannot reach.
4. **Measure the cache on its own**: run_benchmark times the home page with the cache bypassed and again served from cache, and returns the response times. It is a read tool, and it accepts site: "all" for every site. It does not return a Lighthouse score, so the agent must not use it to answer a PageSpeed question.
5. **Compare over time**: get_benchmark_history returns past benchmark runs, uncached against cached, together with the settings changes on the same timeline, which is how you answer "did that change help?". For PageSpeed scores over time, use get_score_history.

## Reference

| | |
| --- | --- |
| Read stored scores | get_score_history (read): PageSpeed Insights and GTmetrix runs, starts nothing |
| Metrics per run | Score, LCP, FCP, CLS, TBT, Speed Index, TTFB, for mobile and desktop |
| Run a new test | run_speed_test (write, uses the shared allowance): one PageSpeed Insights run per call |
| strategy | mobile (default) or desktop |
| Duration | Up to about 2 minutes per run |
| Why a test is a write | It spends a shared PageSpeed allowance and stores a report; it changes nothing on the site |
| Read-only access | A connection token with Read-only everywhere on, or a Viewer member's sign-in: run_speed_test is refused; get_score_history, run_benchmark and get_benchmark_history still work. An OAuth sign-in gets the scopes the client asks for |
| Benchmark | run_benchmark (read): cached against uncached response time for the home page, no Lighthouse score |
| Benchmark history | get_benchmark_history (read): past runs plus settings changes on the same timeline |
| Scheduling | The Hub does not schedule PageSpeed tests itself; its daily pass only reads reports the plugin already stored |
| Where a new test is stored | In the Hub's own report history, the one the Hub dashboard shows |

## Rules

- Check the history first. Ask for stored scores before starting a test, and run a new one only when you want a fresh measurement or something changed.
- Never answer a PageSpeed or Lighthouse question with run_benchmark. It times your own cache and carries no score.
- run_speed_test changes nothing on your site, but the Hub classes it a write because it spends a shared allowance. A connection token with Read-only everywhere on, or a Viewer sign-in, refuses it. An OAuth sign-in gets the scopes the client asks for, so there your client's approval prompt is the gate.
- Lab scores move a few points between runs of the same page. The agent should compare like with like, same site, same strategy, and not report one run's difference as a trend.
- A new test does not run on a timer. If you want a regular test, the agent has to be started by something else, such as a scheduled job in your client, and a scheduled run that spends the allowance should be one you are comfortable leaving unattended.

## Good to know with ChatGPT dots

Write a Custom rule that covers running a PageSpeed test, purging or changing settings through xSpeed Hub, and set it to Ask before taking action. A rule set to Take action without asking lets a scheduled run call run_speed_test on every site it thinks needs one, and each run spends the shared allowance with nobody watching, because the Hub has no confirmation step of its own. Word the scheduled prompt as history only, so the dot posts the drop and leaves the test to you. The app signs in with OAuth and ChatGPT custom apps have no header field, so the connection token's Read-only everywhere switch does not apply. For a dot that can only read, sign in as a Viewer member of the workspace, which refuses run_speed_test outright. OpenAI lists dots for Pro outside the EEA, Switzerland and the UK, Business Premium, and an admin-enabled beta on Enterprise, Edu and Healthcare, and developer mode has plan rules of its own.

## More prompts for this job

They work in any client connected to xSpeed Hub.

- Using xSpeed Hub, what is the mobile PageSpeed score for shop? Check the stored history before you run anything.
- Use xSpeed Hub to run a new mobile PageSpeed test on blog and tell me the score, LCP and the top opportunities.
- With xSpeed Hub, test shop on desktop and mobile and tell me which one is worse.
- Using xSpeed Hub, has the PageSpeed score on docs improved over the last few runs?
- Use xSpeed Hub to benchmark the cache on every site and tell me which one saves the least time.
- Did turning on minification on shop help? Use xSpeed Hub to compare the benchmark history around that change.
- My PageSpeed test failed on staging. Use xSpeed Hub to tell me why.

## Frequently asked questions

### Can my ChatGPT dot run a PageSpeed test every week on its own?

It can call run_speed_test from a scheduled task if your Custom rules let it, but every run spends the shared speed-test allowance and nobody is watching. The Hub does not schedule tests itself. A weekly report that reads get_score_history, with a rule that keeps speed tests on Ask before taking action, is the safer pattern.

### Why might a fresh test be missing from the next weekly report?

run_speed_test saves its result to the Hub's own report history, the one the Reports tab shows, while get_score_history reads the runs the plugin stored on each site. Ask the dot to name the date of the newest run per site, so an old number is not read as a fresh one.

### What is the difference between run_speed_test and run_benchmark?

run_speed_test runs a real PageSpeed Insights audit and returns a Lighthouse score with Core Web Vitals. run_benchmark measures how fast your own cache answers compared with an uncached request for the home page, and returns no Lighthouse score. Use the first for "what is my PageSpeed score" and the second for "is my caching working".

### How long does a PageSpeed test take?

A single run can take up to about 2 minutes, so the agent should tell you it has started before it calls. One call tests one device, mobile or desktop, so checking both takes two calls.

### Can I ask for the last score without running a new test?

Yes. get_score_history reads the stored PageSpeed Insights and GTmetrix runs for the site and starts nothing. The Hub tells the agent to read it first whenever you ask what your score is, because a new test spends a shared allowance.

### Will the Hub run PageSpeed tests on a schedule?

No. The Hub does not schedule PageSpeed tests itself. Its daily pass re-verifies sites, snapshots cache status and pulls the PageSpeed and GTmetrix reports the plugin has already stored, and it can alert on a score regression. If you want regular new tests, they have to be started by a client that can run scheduled jobs.

### Why is a speed test treated as a write tool?

It does not change your site. The Hub classes run_speed_test as a write because it spends a shared PageSpeed allowance and stores a report, and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) should not be able to cost the owner anything. Such a connection can still read stored scores with get_score_history.

## Track PageSpeed scores with other agents

[Claude Code](https://xspeedcache.com/agent/claude-code/pagespeed-tests/) · [Claude](https://xspeedcache.com/agent/claude/pagespeed-tests/) · [Claude Cowork](https://xspeedcache.com/agent/claude-cowork/pagespeed-tests/) · [ChatGPT](https://xspeedcache.com/agent/chatgpt/pagespeed-tests/) · [Codex](https://xspeedcache.com/agent/codex/pagespeed-tests/) · [Cursor](https://xspeedcache.com/agent/cursor/pagespeed-tests/) · [GitHub Copilot in VS Code](https://xspeedcache.com/agent/github-copilot/pagespeed-tests/) · [Windsurf](https://xspeedcache.com/agent/windsurf/pagespeed-tests/) · [Gemini CLI](https://xspeedcache.com/agent/gemini-cli/pagespeed-tests/) · [Antigravity](https://xspeedcache.com/agent/antigravity/pagespeed-tests/) · [Zed](https://xspeedcache.com/agent/zed/pagespeed-tests/) · [Kiro](https://xspeedcache.com/agent/kiro/pagespeed-tests/) · [OpenCode](https://xspeedcache.com/agent/opencode/pagespeed-tests/) · [OpenClaw](https://xspeedcache.com/agent/openclaw/pagespeed-tests/) · [Hermes Agent](https://xspeedcache.com/agent/hermes-agent/pagespeed-tests/) · [Grok Build](https://xspeedcache.com/agent/grok-build/pagespeed-tests/) · [Grok](https://xspeedcache.com/agent/grok/pagespeed-tests/) · [Grok Bot](https://xspeedcache.com/agent/grok-bot/pagespeed-tests/) · [Muse](https://xspeedcache.com/agent/muse/pagespeed-tests/) · [Manus](https://xspeedcache.com/agent/manus/pagespeed-tests/) · [Kimi Code](https://xspeedcache.com/agent/kimi/pagespeed-tests/) · [Paperclip](https://xspeedcache.com/agent/paperclip/pagespeed-tests/) · [NanoClaw](https://xspeedcache.com/agent/nanoclaw/pagespeed-tests/)

## More with ChatGPT dots

- [Purge the WordPress cache with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/purge-cache/)
- [Find out why WordPress pages are not cached with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/troubleshoot-cache/)
- [Scan a website for speed problems with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/speed-scan/)
- [Raise a WordPress site's PageSpeed score with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/optimize-site/)
- [Tune WordPress cache settings with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/cache-settings/)
- [Warm the WordPress cache with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/preload-cache/)
- [Set up the Redis object cache with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/object-cache/)
- [Manage Cloudflare caching with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/cloudflare/)
- [Manage every WordPress site at once with ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/fleet/)

## Documentation

- How to run a speed test: https://xspeedcache.com/docs/external-score/
- PageSpeed Insights integration: https://xspeedcache.com/docs/pagespeed-insights-integration/
- Running speed tests in xSpeed Hub: https://xspeedcache.com/docs/hub-speed-tests-and-notifications/
- How to run a PageSpeed audit: https://xspeedcache.com/docs/pagespeed/