case study · 2025

Rubricate

An agentic AI voice-interview and evaluation platform — the entire platform, built solo — that vets domain experts at scale with adaptive voice interviews backed by a full automated evaluation pipeline. The expert network behind Dataclap.

Adaptive real-time voice

Interview mode

Automated rubrics

Scoring

Source → onboard

Funnel coverage

01the problem

What needed solving

Vetting domain experts at scale is a bottleneck: every candidate needs a real conversation with someone qualified to judge them, and that doesn't scale. Screening was consuming expert time that should have gone to actual work, and consistency between interviewers was impossible to guarantee.

02approach

How I built it

01

Built agentic AI voice interviews that adapt in real time — follow-up questions are generated from what the candidate actually said, not read from a fixed script.

02

Designed an automated evaluation pipeline with explicit scoring rubrics, so every candidate is judged against the same defined criteria.

03

Engineered the real-time voice loop for low enough latency that turn-taking feels like a natural conversation rather than a form.

04

Built automation workflows covering the full funnel — sourcing, screening, evaluation and expert onboarding.

05

Owned architecture, backend and the real-time data pipelines end to end.

03outcome

Where it landed

Rubricate runs in production as the expert network behind Dataclap, conducting adaptive voice interviews at a volume that would be impossible to staff manually, with consistent rubric-based scoring across every candidate. The voice AI, the evaluation pipeline and every workflow around them are one platform, built end to end by one engineer.

// stack

Agentic AIVoice AILLM EvalsPythonAutomation

// next step

Have a project like this?

Book a 15-minute call and walk me through it. I'll tell you honestly what it would take and whether I'm the right fit.