Daily check-in model
The system supports four check-in tiers so users are never blocked from their tasks on low-capacity days.
Tier 1 - Full
Tier 2 - Quick
Tier 3 - Momentum
Tier 4 - None
Three ratings, one per axis using 1-5 circles.| Axis | Low anchor | High anchor | Measures |
|---|
| Body | ”Moving gently" | "Feeling strong” | Physical capacity |
| Mind | ”Foggy today" | "Sharp and clear” | Cognitive capacity |
| Mood | ”A hard one" | "Really good” | Emotional state |
One question with three options: rough / okay / good day.
- Rough -> 25th percentile vector (or
[2,2,2] for new users)
- Okay -> 50th percentile (or
[3,3,3])
- Good -> 75th percentile (or
[4,4,4])
Reuses yesterday’s check-in with conservative dampening (axis * 0.9, floor 1).
Uses a conservative estimated pool and unlocks task access with transparency copy.
Data quality across tiers
| Tier | Confidence weight | EWMA influence | Pool accuracy |
|---|
| Full | 1.0 | Full | Best |
| Quick | 0.7 | Reduced | Good |
| Momentum | 0.4 | Minimal | Approximate |
| None | 0.1 | Negligible | Conservative estimate |
Ratings are relative to personal baseline. A 3 means “about my usual,” not an objective severity level.
The onboarding sequence
Condition selection
Broad chronic illness categories, not diagnosis-level claims.
Severity self-assessment
Initializes the coefficient starting range.
Optional Visible import
Optional pace-point import for calibration support.
Difficulty calibration
User rates 6 common tasks (1-5), producing initial coefficient estimate.
Reference day anchors
User marks what they completed yesterday to seed initial pool estimate.
LLM estimation opt-in
Explains on-device vs cloud estimation; default is off.
Cold start pool and confidence
For the first week, pool blends reference estimate with observed behavior:
Day 1: pool = referenceEstimate x bias
Day 2-7: pool = blend(referenceEstimate, realSpendingEwma, blendWeight)
Day 8+: pool = realSpendingEwma x bias
| Day | Confidence | Bias | Pool protection |
|---|
| 1 | 0.00 | 0.80 | 20% below reference |
| 10 | ~0.30 | ~0.85 | 15% below spending |
| 27 | ~0.80 | ~0.94 | 6% below spending |
| 34 | ~1.00 | 0.97 | 3% permanent margin |
Read next
