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...
#205: Building reactive Python notebooks with Marimo
Pybites Podcast
53 minutes
1 month ago
#205: Building reactive Python notebooks with Marimo
Marimo is redefining what a Python notebook can do—bringing structure, version control, and interactivity together. In this episode, we chat with Akshay Agrawal, co-founder and CEO of Marimo, about how their reactive Python notebook fixes hidden state, keeps outputs in sync, and makes reproducible, reviewable code the norm. Akshay shares Marimo’s origin story, how its reactive DAG turns notebooks into clean, Git-friendly tools, and why teams are ditching Jupyter-to-Streamlit pipelines for sim...
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...
