UC-08 Monthly EngineeringSEO lead

Technical and Core Web Vitals health

Someone forwarded a PageSpeed screenshot. You want the site-level read, which vital is actually failing, on which pages, and whether it is costing you anything.

What you'd type

Any Core Web Vitals regressions?
How is our page experience this month?
Which high-traffic pages have the worst LCP?

You never name a skill or a tool. The assistant routes on what you asked. Run it on your own data →

What comes back

Use case: Technical and Core Web Vitals health Simulated · illustrative

Any Core Web Vitals regressions?

Analysis plan, every step, resolved for you

Routed to the governed workflowtechnical-health-audit
Dates bound explicitlyJul 2026
2 analyses queued in parallelsite_health_cwv_check · page_traffic_cwv
Honesty gates armedscope echo · freshness

Core Web Vitals, mobileweighted across measured pages

Vital	Jul	Jun	Grade
LCP	2.9s	2.3s	Needs improvement
INP	0.18s	0.19s	Good
CLS	0.06	0.06	Good
Performance score	61	74	Needs improvement

Jul 2026 vs Jun 2026organic

⚠ Observationalas of Jul 24, 2026 (Lighthouse collection varies by page, this run is 8 days old)IllustrativeOpen in Quattr ↗

LCP moved 0.6s the wrong way on mobile and crossed the threshold. The other three vitals are unchanged, this is one regression, not a decline.

A simulated conversation on fictional data. Scope, freshness and the ⚠ Observational marker are attached by the same director that renders every demo on this site.

How fresh this actually is

Lighthouse collection varies by site and by page, some priority URLs are measured nightly, most far less often. The card carries the collection date, and a vital measured three weeks ago is labelled as measured three weeks ago.

What's behind it

Analyses it runs

site_health_cwv_check
page_traffic_cwv
cwv_breakdown

Sources it reads

The skills that own this

The dashboard rituals it replaces

Sub-page portfolio audit 4 pages × 4 metric switches · 1 notepad

Going deeper

Next use case Paid and organic balance →

See this use case run for real

All runs →