Week-on-week paid diagnostic

Use the StoreHero MCP to do the following analysis. Always anchor the answer in real StoreHero data, not platform-reported metrics.

Run a week-on-week paid advertising diagnostic. Compare the last 7 days vs. the prior 7 days across all paid channels (Google, Meta, TikTok). Pull blended CPA, new customer acquisition cost (nCAC), MER, and contribution margin as the ground truth. Then layer platform-level data for the diagnosis.

Surface the biggest deltas across:

1. Blended metrics — total paid spend, blended ROAS, blended CPA, MER, new customer CM
2. Channel-level — Google, Meta, and TikTok spend, platform-reported ROAS, and the gap between platform-reported and StoreHero blended performance
3. Campaign-level — biggest movers up and down by spend, biggest CPA shifts, campaigns crossing target thresholds in either direction

For each major delta: identify the primary driver (auction pressure / CPM shift, CTR change, conversion rate change, landing page issue, pacing change, audience or creative shift) and isolate brand vs. non-brand performance so brand traffic doesn't mask the picture.

Apply a traffic-light status to each channel and call out whether the change is seasonal noise, a real shift, or an early warning of something larger.

End with: (1) what's working — keep doing, (2) what's broken — fix this week, (3) what to watch — monitor next week.

At the bottom of your answer, render an inline visual summary: KPI cards for blended spend, blended CPA, MER, and new customer CM (each with WoW % and traffic-light status). Add a side-by-side channel comparison bar showing Google, Meta, and TikTok with WoW spend change and CPA change. Place text commentary alongside the visuals. Use the Spend Advisor tool to suggest what to explore next.