CV screening that passes a bias audit
Assistive candidate analysis with documented fairness testing — shortlisting 45% faster with a human accountable for every rejection.
Where they started
PeopleGrid wanted to help recruiters handle application volume, but NYC Local Law 144 and client legal teams meant any automated screening required documented bias auditing. Their previous vendor could not produce it.
What we did
- 1
Designed the system as strictly assistive: it surfaces and structures evidence but never rejects a candidate.
- 2
Removed name, age, address and other proxy signals before analysis.
- 3
Built a fairness evaluation harness measuring selection-rate parity across protected attributes on every release.
- 4
Produced audit documentation mapping directly to Local Law 144 requirements.
- 5
Required a recorded human decision with reasoning for every rejection.
The outcome
Shortlisting time fell 45% while passing independent bias audit. Fairness metrics are published to clients each quarter.
Other case studies
Cutting support volume by half with grounded retrieval
A national operator's support assistant answered 19% of queries correctly. Rebuilding the retrieval layer took it to 54% without changing the model.
HealthcareClinical documentation support that clinicians actually trust
Structured note drafting deployed entirely inside the hospital VPC, cutting documentation time 41% with every output clinician-reviewed.
FintechAutomating KYC review without losing the audit trail
Document extraction and verification cut manual KYC review 62% while making every decision reproducible for regulators.
Let's talk about what you're building
Tell us the problem. We'll tell you honestly whether AI is the right tool, and what it would take.