Agent Trust Lab promotes the depth of independent evidence, not a product quality score. Promotion is derived from the longitudinal observation database and is attached to monitored MCP Trust Profiles at read time. Static profile grade, static coverage and ownership status are not mutated by this process.
| Level | Status | Minimum samples | Minimum span |
|---|---|---|---|
| L0 | NO_EVIDENCE | 0 | 0h |
| L1 | POINT_IN_TIME | 1 | 0h |
| L2 | REPEATED_OBSERVATION | 3 | 8h |
| L3 | MULTI_DAY_OBSERVATION | 7 | 24h |
| L4 | LONGITUDINAL_OBSERVATION | 42 | 168h |
| L5 | MATURE_LONGITUDINAL_OBSERVATION | 180 | 720h |
A new runtime evidence epoch begins when independently observed MCP protocol, server identity/version, tool count, or deterministic tool-schema hash changes. Maturity is recalculated from the new epoch so pre-change observations cannot silently certify the new runtime state.
Repository HEAD changes are recorded but do not reset the runtime epoch by themselves, because repository HEAD is not proven to be the exact deployed artifact.
Promotion measures evidence depth and duration. A failed initialize request still contributes to evidence maturity; it is reflected separately in observed outcome metrics. This prevents the system from conflating “we have observed it repeatedly” with “it performs well.”
| Status | Minimum samples per side | Minimum span per side |
|---|---|---|
| EARLY_PRE_POST | 1 | 0h |
| OBSERVED_PRE_POST | 2 | 0h |
| REPEATED_PRE_POST | 3 | 8h |
| MULTI_DAY_PRE_POST | 7 | 24h |
Pre/post evidence reports association around a detected runtime change. It never makes a causal claim.
/api/evidence-promotion-policy — policy and thresholds./api/evidence-promotion — one or all monitored MCP promotion states./api/profile — monitored MCP profiles include derived_evidence.transport_promotion./api/change-impact — observational pre/post metrics.