Lead scoring
Ranking prospects by fit and timing so effort flows to the likeliest buyers — anything from a P1–P4 bucket system to a weighted model over ICP fit and signals.
The failure mode is scoring theater: a precise-looking number over inputs nobody validated. Honest scoring starts crude — fit (does the ICP match?) times timing (is there a live signal?) — and earns complexity only when outcome data justifies it. The most valuable output isn't the top of the ranking; it's the explicit SKIP bucket, because every skipped bad-fit invite protects acceptance rate, which protects the whole seat.
LinkedBoost is the LinkedIn MCP for Claude — agent-run outreach with enforced limits and a human trigger on every send. See how it works →