4 filters unified. 321 experiments ranked. Math dictates what to work on.
Every experiment must pass through four sequential gates. Fail any gate and it's blocked from the queue until remediated.
The 306 blocked experiments aren't dead — most are blocked on "no mechanism documented." Adding mechanism unlocks scoring.
Click any row to expand Trust / Math / Method breakdown. Score = (trust × math × method × impact × priority_weight × step_weight) / effort.
| # | ID | Name | Score | Step | Trust | Math | Method | Impact | Effort |
|---|---|---|---|---|---|---|---|---|---|
| 1 | E315 | Weaponization Ladder Enforcement | 600,000 | 3 / 6 | 100% | 90% | 100% | $500K | 3d |
Trust Layers (5/5)
Math Checks (9/10)
Method Phases (5/5)
Ladder Position
| |||||||||
| 2 | E309 | Landing Page Launch Blitz | 214,286 | 2 / 6 | 100% | 100% | 100% | $750K | 14d |
Trust
Math
Method
Notes
| |||||||||
| 3 | E300 | Smart Bidding Clean Data Recovery | 200,000 | 2 / 6 | 100% | 100% | 100% | $350K | 7d |
Trust
Math
Method
Notes
| |||||||||
| 4 | E306 | Antibody Actualization | 180,000 | 2 / 6 | 100% | 100% | 100% | $200K | 3d |
Trust
Math
Method
Notes
| |||||||||
| 5 | E311 | Session Decay Timer | 90,000 | 3 / 6 | 100% | 100% | 100% | $100K | 3d |
Trust
Math
Method
Notes
| |||||||||
| 6 | E312 | Gemini Notes Auto-Pull | 72,000 | 2 / 6 | 100% | 100% | 100% | $80K | 3d |
Trust
Math
Method
Notes
| |||||||||
| 7 | E301 | CRO Form Position Fix | 51,429 | 3 / 6 | 100% | 100% | 100% | $180K | 14d |
Trust
Math
Method
Notes
| |||||||||
| 8 | E305 | RAG Incident Ingestion Loop | 45,000 | 3 / 6 | 100% | 100% | 100% | $50K | 3d |
Trust
Math
Method
Notes
| |||||||||
| 9 | E308 | Oxygen Builder Health Monitor | 36,000 | 2 / 6 | 80% | 80% | 80% | $50K | 3d |
Trust (4/5)
Math (8/10)
Method (4/5)
Notes
| |||||||||
| 10 | E307 | CRO Form Architecture Rebuild | 30,857 | 3 / 6 | 100% | 90% | 100% | $180K | 14d |
Trust
Math (9/10)
Method
Notes
| |||||||||
Worked example — E315: (1.00 × 0.90 × 1.00 × 500000 × 1.0 × 0.5) / 3 ≈ 600,000
Where our 15 scored experiments currently sit. The jump from Step 3 → Step 4 is the gap — timers running but no verified output yet.
306 of 321 experiments are blocked from scoring. Adding a documented mechanism to each unlocks the queue. This is the single biggest cleanup opportunity.
Priority engine recalculates. Queue refreshes overnight. Top-10 stored in stats.json.
Hit GET /api/priority/next to know what to work on. No guessing.
Pull the queue as talking points. Stephanie + Kalen see why each item is #1.
Robert picks #1. Executes to Step 6 before starting #2. No parallel drift.
If #1 stays #1 for 14 days: force-activate or archive. No zombies.
Every completed step logs back. Feeds the feedback loop. Compound learning.
curl http://localhost:8765/api/priority/next
curl 'http://localhost:8765/api/priority/queue?limit=10'
curl http://localhost:8765/api/priority/stats
curl http://localhost:8765/api/priority/all | jq '.queue[0:5]'