Stats
How to find out why traffic dropped
anomaly-investigator a saved expert workflow your assistant follows, in Claude, ChatGPT or Cursor
The "why did it move?" diagnostician: a fixed descent from is-it-real statistics through data artifacts, decomposition, localization, market events and technical suspects, ending in ranked causes with evidence.
Try it
traffic dropped, what happened
Private beta Part of the quattr-ai-search plugin, rolling out org by org. Request access ↗
Say any of these
why did clicks droptraffic fellwhat happened last weekimpressions spikedwhy are we downdiagnose this dropdid the update hit uscitations dropped, why
You never name the skill or a tool, the assistant routes on what you asked. These are the phrasings it recognises for this one.
And when it stays out of the way
Not for "are we up or down" (search-pulse), for scheduled reporting, or for pure "is this change real" verdicts with no cause-hunt wanted.
Use it instead of search-pulse when you want causes, not a headline; use weekly-search-report instead for the routine Monday readout.
What it runs
significance_checkcompare_periodsgsc_breakdowncompetitive_trendssite_health_cwv_checkindexation_gap_diagnosiscrawl_budget_wasteai_crawler_analysisweb_analytics_overview
9 governed analyses, composed and scoped for you. Named here for transparency, not because you have to ask for them.
The numbers behind it
Metrics it reads, each defined in the reference
AI Overview average daily results-page countAI referral session changeAverage CTRAverage positionBounce rateConversion-rate changeConversionsDomain moversFunnel drop-off rateKeyword-page click coveragep-valuePage-one footprint retentionPearson correlationPeriod-over-period changePeriod-over-period change, relativePractical magnitudeRanking movement (gainers and losers)Real, noise or can't-tellRelative changeSERP volatility indexSessionsSignificantSpearman correlationStatus-code hits
Reports these numbers feed
AI bot activity reportAI Overview and SERP feature reportAI referral traffic reportAI visibility reportCannibalization reportCompetitor search reportContent decay reportContent performance reportCrawl log reportCTR opportunity reportInternal linking reportKeyword ranking and movement reportMonthly executive search reportPaid and organic overlap reportPaid search performance reportSearch market share reportSearch opportunity reportSearch to revenue reportSERP volatility and algorithm update reportTechnical SEO audit reportWeekly search report
What it refuses to do
- Single-cause storytelling is the named failure mode: when two causes overlap (e.g. an algorithm update + a reporting artifact), present both with their separate evidence.
- Certainty language is banned on can't-tell verdicts; "confirmed" requires either significance + a mechanism, or an intervention test.
- Ranked causes are hypotheses with evidence, the card says what would CONFIRM each; this skill never asserts causation from observational reads alone.
What the answer looks like
Why did clicks drop?
Analysis plan, every step, resolved for you
- Routed to the governed workflow
anomaly-investigator - Dates bound explicitly
Jul 12 to Jul 18, 2026 - 4 analyses queued in parallel
significance_check · get_data_freshness · gsc_breakdown · competitive_trends - Honesty gates armed
significance α=0.05 · scope echo · freshness
The drop is real, and it isn't site-wide: 82% of it sits in How-to guides on mobile.
- Organic clicks
- 33.9K ▼ −18.6%
- Concentration
- 82% of the loss How-to guides · mobile
- Data artifacts
- none freshness verified, not a load gap
Jul 12 to Jul 18, 2026 vs Jul 5 to Jul 11, 2026organic
⚠ Observationalas of Aug 1, 2026 (GSC lags 1 to 2 days)IllustrativeOpen in Quattr ↗
Welch test on daily clicks vs the prior week, a real decline, not noise.
- Verdict
- Real — significant
- p-value
- 0.003
- 95% CI
- −24% to −12%
Ranked causes follow, a documented core update overlaps the window (correlation, not confirmation).
Jul 12 to Jul 18, 2026 vs Jul 5 to Jul 11, 2026organic
⚠ Observationalas of Aug 1, 2026 (GSC lags 1 to 2 days)IllustrativeOpen in Quattr ↗
Top-ranked cause: core-update volatility on How-to guides, rivals gained the same SERPs that week.
A simulated conversation on fictional data. Scope, freshness and the ⚠ Observational marker are attached by the same director that renders every demo here, not written by hand.
See this Skill inside a real analysis
All runs →A recorded run where this Skill does the work, the prompts as typed, and the decision that came back.
Want this Skill running on your own accounts? Every Quattr customer works with an AI Search Strategist who sets it up with you.