Constructing and Judging Modern Agentic Workflows

10/07/2026 58 min Episodio 302

Listen "Constructing and Judging Modern Agentic Workflows"

Descargar episodio Ver en sitio original

Episode Synopsis

How can you improve your LLM agent systems through specification enrichment? What are the advantages of having an LLM act as a judge within an agent system? This week on the show, Senior IEEE Member and Quality Engineer Suneet Malhotra joins us to discuss building and evaluating agentic architecture.

More episodes of the podcast The Real Python Podcast

Navigating Silent Failures in AI: Strategies for Effective Oversight 21/08/2026

Improving NumPy Performance on Free-Threaded Python 14/08/2026

Programmatically Developing LLM Prompts With DSPy 07/08/2026

Should You Understand Your Entire Python Codebase? 31/07/2026

Configuring a Versatile LLM Harness & Scraping the Web With Scrapy 24/07/2026

Free-Threaded Python's History & uv in Production 17/07/2026

Running Python Locally in a Sandbox 03/07/2026

Maintaining Your Python Developer Instincts While Using LLM Tools 26/06/2026

EuroPython 2026: Celebrating 25 Years 12/06/2026

Reducing the Size of Python Docker Containers 05/06/2026

Ver todos los episodios

Latest episodes