Daily Briefing
What moved, what to do, what to leave alone.
Sparklines show the 7-day trend — illustrative where no per-day export exists.
AI Briefing
🌿
Since yesterday
Needs attention
Running & next experiments
Experiments
Your ASA lab notebook — every theory, the change that tests it, and the verdict.
This is the layer Apple's console and a plain dashboard don't have: a hypothesis ledger that survives the ~24h reporting lag and a 7-day runway, and turns each finding into a reusable rule.
🌱 Learnings & rules adopted
The durable knowledge experiments leave behind — these constrain every future recommendation.
Keywords
Last 7 days · band by TTR · click a header to sort.
🟢 ≥4% 🟡 2–4% 🔴 <2% TTR. Rows under ~100 impressions are directional only. CPA shown where installs > 0.
Search Terms
What people actually typed — the source of negative-keyword discovery.
Timeline
Every account change on one axis — so you can read results against the change that caused them.
Blended TTR, with change marker
Change log
Data & Sync
Local-first, BYO-key. Your Apple Ads data, in a format the AI can read directly.
The pipeline
① Apple Ads API v5
Read-only key · campaigns, ad groups, keywords, search-terms reports. One key spans both orgs (SOLENOS/Yeliz).
→
② Local store
Dated JSON snapshots + SQLite. Diffable day-over-day. Secrets never leave the Mac.
→
③ Claude
Reads snapshot + open experiments + your own ASA rules → briefing & verdicts.
→
④ This view
Briefing, experiment ledger, scorecard. Verdicts flow back to SESSION-LOG.md.
Throwaway prototype runs on v5 (Python). The real build targets the new Platform API (v5 sunsets 2027-01-26) in Swift. RevenueCat revenue join is wired but expected sparse on Dopfast today — judge on installs / CPA / TTR for now.