We Built an AI Recruiter Coach in 6 Hours (Plus Claude Cowork in Real Time)

2026-02-01

Download

Can you really build serious internal AI tools in a few hours — and should everyone on your team be doing it?In Episode 29 of Built This Week, Sam Nadler and Jordan Metzner break down an internal AI product they built at Ryz Labs called ScreenEval — a recruiter screen analysis and coaching tool built in under six hours using Claude Code, Supabase, and AWS.We start with a live demo. Sam walks through how ScreenEval ingests recruiter screen transcripts, evaluates can...

Can you really build serious internal AI tools in a few hours — and should everyone on your team be doing it?

In Episode 29 of Built This Week, Sam Nadler and Jordan Metzner break down an internal AI product they built at Ryz Labs called ScreenEval — a recruiter screen analysis and coaching tool built in under six hours using Claude Code, Supabase, and AWS.

We start with a live demo. Sam walks through how ScreenEval ingests recruiter screen transcripts, evaluates candidates, scores recruiter performance, and provides concrete coaching feedback — all without overriding human judgment. The real unlock is turning messy interview transcripts into searchable, structured hiring data across the entire organization.

From there, we test Claude Cowork live — Anthropic’s new interface designed to make building accessible to non-technical users — and compare it to running Claude Code directly in the terminal. We discuss where Cowork shines, where terminal-based workflows still win, and why managing multiple AI agents is becoming a core skill.

We wrap with AI news, including Anthropic’s massive funding round, pricing changes, and why enterprise-focused AI tooling is pulling spend away from other platforms.

No hype.
No abstractions.
Just what actually happens when you put AI to work inside a real company.

New episodes every Friday.

================================================================================

TIMESTAMPS

(0:00) Why internal AI tools matter more than external products
(0:55) Episode 29 kickoff and overview
(1:45) Why Ryz Labs built ScreenEval
(3:30) Live demo: recruiter screen transcript analysis
(6:15) Candidate evaluation vs recruiter coaching
(9:10) What recruiters miss in fast screening calls
(11:40) AI feedback that doesn’t override human judgment
(14:00) Searching transcripts instead of resumes
(17:20) Manager dashboards and recruiter performance analytics
(21:10) How long it actually took to build ScreenEval
(23:30) The full stack: Claude Code, Supabase, AWS
(25:45) Why Anthropic models power everything
(27:30) Claude Cowork explained
(29:15) Building a new product live with Cowork
(32:40) Cowork vs Claude Code in the terminal
(36:00) Managing multiple AI agents at once
(39:30) Anthropic’s funding round and market momentum
(42:15) Why we’re shifting spend away from other AI tools
(45:10) AI inside organizations: efficiency without layoffs
(48:30) What every team should be building next
(50:45) Final thoughts and closing