Day one of the ledger
Prospecta launched in June 2026. Every prediction Scout makes from day one is logged here — before the outcome is known. Nothing gets deleted, including our misses.
We grade ourselves in public.
Most recruiting tools tell you what to do and never check whether they were right. Prospecta logs every Scout prediction, grades it against the outcome, and shows the tally here. If we're wrong, you'll see it.
How this will fill in
Predictions logged
Immediately — every Scout brief is parsed into discrete, gradable claims and timestamped before the outcome is known.
Graded
As outcomes land — a nightly job compares predictions against verified replies and commits. Hits and misses both count.
Verified commits
As athletes upload NLIs or signing announcements, each commit gets a verified badge and the school name unlocks.
How we grade Scout
Prediction ledger
Every weekly brief Scout writes is parsed into discrete, gradable claims (reply likelihood, coach fit, roster gap, offer timing). Each one is timestamped before any outcome is known.
Outcome grading
A nightly job matches predictions against verified commitments and replies. Hits and misses are both counted — no quietly burying the misses. Athletes can also mark predictions correct or missed manually.
Drift detector
Reply-likelihood scores are snapshotted weekly. When the score moves outside the expected band — coaching change, timing window, etc. — you get a drift alert with the before/after.
Hit rate is graded predictions only. Empty rows mean we haven't accumulated enough outcomes yet — they'll fill in here as athletes log results.
| Category | Graded | Correct | Hit rate |
|---|---|---|---|
| No graded predictions yet. The first results will appear here within ~1 week of athletes logging outcomes. | |||
- Coaches tracked across athletes0
- Reply-likelihood snapshots0
- Graded predictions0
- Verified commits0
All counts are aggregates only. We never expose which athlete is tracking which coach, or any individual prediction.
Coach Twin's reply-rate calls are probability claims, not yes/no bets — a well-calibrated 15% prediction is expected to be "wrong" 85% of the time. So we group predictions by the band we called, then show the observed reply rate for that band once at least 10 outcomes have landed. Calibrated means the observed rate matches the predicted band.
| Predicted band | Outcomes logged | Replies | Observed reply rate |
|---|---|---|---|
| Under 5% | 0 | 0 | collecting outcomes (0 of 10) |
| 5–10% | 0 | 0 | collecting outcomes (0 of 10) |
| 10–20% | 0 | 0 | collecting outcomes (0 of 10) |
| 20% and up | 0 | 0 | collecting outcomes (0 of 10) |
When a family logs a commit, we compare the tier Scout projected in the Reality Report against the tier the athlete actually landed at. Same tier = accurate. One tier off = near miss. More than one = miss. Nothing is deleted.
No graded division-tier calls yet. Each logged commit fills a row.
Outcomes closed without commitment
0Recruiting cycles that ended without a commitment — counted, not hidden. A ledger that only shows wins isn't a ledger.
See where Prospecta families actually landed.
The outcomes feed is fully anonymized — schools, divisions, states only. No athlete names, no scores, no marketing varnish.
Methodology: Scout writes weekly briefs that include numeric and categorical claims. Each claim is stored as a row before the outcome is known. A nightly job compares stored claims against verified outcomes (commit reports, dated reply receipts, NLI screenshots) and updates hit/miss counts. Reply-likelihood scores are recomputed weekly from deterministic signals (sport, staff size, contact timing, recent activity) and snapshotted so drift is detectable. No predictions are ever deleted to improve the score.