Vanishing Gradients Episode 64: Data Science Meets Agentic AI with Michael Kennedy (Talk Python)
62 snips
Dec 3, 2025 In this discussion, Michael Kennedy, a seasoned Python developer and educator known for his insights on AI and software practices, tackles the myth of complexity in tech. He shares how to simplify production Python systems, emphasizing the importance of the 'Docker barrier' for cost-effective self-hosting. The conversation explores how Agentic AI is shifting development mindsets and enhancing efficiency. Michael also stresses the value of struggling through learning and the need for complementary skills in navigating the evolving tech landscape.
AI Snips
Chapters
Books
Transcript
Episode notes
Simplicity Beats Complex Cloud Architectures
- We've been sold a story of unnecessary complexity for deploying apps and services.
- Michael Kennedy argues simpler, focused stacks often cut cost and management by orders of magnitude.
Talk Python Runs Fast On A $30 Server
- Michael built Talk Python's website to serve heavy database-driven pages with 10–20ms responses.
- He runs it for around $30/month with only minutes of downtime annually to show simple setups can be highly reliable.
Two-Stage Data Science Workflow
- Data science workflows naturally split into exploration then production stages.
- Keep notebook-style exploration, then refactor into engineered code when the problem and requirements crystallize.
