Evidence · first-party tested
Leaks location text into a task item, returning 'Pune did testing and bug fixing' as a responsibility instead of keeping the task text cleanly separated.
✗ FailedHrFlow →
A poorly structured, inconsistently formatted resume for John Kumar with mixed date styles, weak sectioning, and noisy extra content to simulate real-world ATS input.
The observation
Leaks location text into a task item, returning 'Pune did testing and bug fixing' as a responsibility instead of keeping the task text cleanly separated.
Criterion: Noise in output · Scenario: Messy real-world resume — John Kumar (group: resume-parsing-benchmark)
Query this
get_evidence({
tool: "hrflow",
scenario: "resume-parsing-benchmark"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Free with attribution.
Same input, other tools
Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com