"Today, we're talking about building real AI products with foundation models. Not toy demos, not vibes. We'll get into the boring dashboards that save launches, evals that change your mind, and the shift from analyst to AI app builder. Our guide is Hugo Bowne-Anderson, educator, podcaster, and data scientist, who's been in the trenches from scalable Python to LLM apps. If you care about shipping LLM features without burning the house down, stick around."
"Hugo Bowne-Anderson returns to Talk Python To Me for his third appearance, bringing a wealth of experience from the evolution of the Python data science ecosystem. Hugo's journey spans academic research in biology, math, and physics at Yale University to becoming a key figure in data science education and developer relations. He played a pivotal role at DataCamp working on curriculum and education, then moved on to work with significant projects like Dask at Coiled with Matt Rocklin, and Metaflow at Outerbounds (originally from Netflix)."
Foundation models and LLMs are changing how data teams build products by turning text-in/text-out models into structured outputs and application features. Operational engineering matters: reliable dashboards, evaluative experiments, and careful rollout practices prevent catastrophic launches. AI-assisted coding tools are becoming standard parts of developer workflows. Teams must shift from being pure analysts to AI app builders who integrate models, handle evaluation, and maintain systems. Practical skills include scalable Python, product-focused evaluation, and building maintainable ML/LLM infrastructure. Organizations benefit from education, developer relations, and cross-functional collaboration to ship, monitor, and iterate on LLM-powered features.
Read at Talkpython
Unable to calculate read time
Collection
[
|
...
]