Evidence · first-party tested
It struggled to make interactions observable: a lookup failure was not surfaced transparently, and the approval interaction left no saved log or audit trail once the session ended.
⚠ StruggledPickaxe →
The observation
It struggled to make interactions observable: a lookup failure was not surfaced transparently, and the approval interaction left no saved log or audit trail once the session ended.
Criterion: Observability ·
Query this
get_evidence({
tool: "pickaxe"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Free with attribution.
Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com