In this episode, we talk with Aaron Jorgensen about how JobHive came to life - starting as a small résumé-parsing experiment and gradually growing into a structured, AI-supported interview workflow. Aaron explains how the system handles voice capture, transcription, prompts, and AI avatars, and why he moved toward a multi-agent approach instead of relying on one model to do everything. We dig into what “fair scoring” actually means, how cross-checking evaluators and confidence levels work, an...
All content for Pybites Podcast is the property of Julian Sequeira & Bob Belderbos and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
In this episode, we talk with Aaron Jorgensen about how JobHive came to life - starting as a small résumé-parsing experiment and gradually growing into a structured, AI-supported interview workflow. Aaron explains how the system handles voice capture, transcription, prompts, and AI avatars, and why he moved toward a multi-agent approach instead of relying on one model to do everything. We dig into what “fair scoring” actually means, how cross-checking evaluators and confidence levels work, an...
#199: Charlie Marsh on ty, uv, and the Python tooling renaissance
Pybites Podcast
53 minutes
5 months ago
#199: Charlie Marsh on ty, uv, and the Python tooling renaissance
Charlie Marsh returns to Pybites to introduce ty —Astral’s bold new take on Python type checking. Built from the ground up for speed and developer experience, ty is both a command-line tool and language server, powered by Rust's Salsa framework. We dive into how it enables lightning-fast incremental analysis, smarter diagnostics inspired by Rust, and a reimagined type-checking workflow for modern Python projects. Charlie also shares how Astral is tackling broader ecosystem challenges al...
Pybites Podcast
In this episode, we talk with Aaron Jorgensen about how JobHive came to life - starting as a small résumé-parsing experiment and gradually growing into a structured, AI-supported interview workflow. Aaron explains how the system handles voice capture, transcription, prompts, and AI avatars, and why he moved toward a multi-agent approach instead of relying on one model to do everything. We dig into what “fair scoring” actually means, how cross-checking evaluators and confidence levels work, an...
