Receipts
Live · No athlete identifiers

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.

Predictions logged
0
Every Scout call is timestamped and saved
Predictions graded
0
We grade after the outcome lands
Verified commits
0
Self-reported with NLI screenshot
Drift alerts sent
0
When a coach's reply-likelihood moves

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.

Calibration by category

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.

CategoryGradedCorrectHit rate
No graded predictions yet. The first results will appear here within ~1 week of athletes logging outcomes.
What we track behind the scenes
  • 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.

Honest by default

See where Prospecta families actually landed.

The outcomes feed is fully anonymized — schools, divisions, states only. No athlete names, no scores, no marketing varnish.

View the outcomes feed

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.