Fetch
GET https://palatineai.site/projects.json. Read stats.updated first — if your last conclusions are newer than the feed, nothing has changed.Screen
Use the cookbook recipes to cut 120 rows down to a view: a category, a token-watch screen, a signal leaderboard.
Shortlist
Keep projects whose totals and signal shape match your thesis. Calibration for the current feed (range 74.75–83.75):
| Threshold | Meaning today |
|---|---|
total >= 80 | Top tier — 19 of 120 projects |
total >= 78 | Strong — 44 of 120 |
noToken >= 8 && socialActivity >= 7 | Token-watch candidates with real audiences |
tokenStatus == "Possible token/funding signal" | Already moving — 3 of 120 |
Deep-research
The feed is a map, not the territory. For each shortlisted project, open
website and x, check GitHub activity yourself, and verify the team ships. Several website values are empty strings — fall back to the x profile.Log a decision
Close every evaluation with one of four verbs:
Suggested log line (one JSON object per evaluation, append-only):Pinning
| Verb | Meaning |
|---|---|
TRACK | Promising; re-check on next dataset update. |
CONTACT | Reach the team (partnership, investment, hiring). |
BUY/WATCH | Token-relevant; watch for launch or entry. |
SKIP | Reasoned no. Log why, so future runs don’t repeat the work. |
datasetUpdated makes decisions auditable against the feed version that produced them.
