Ideas, experiments,
and lessons in AI.
Practical insights on machine learning, generative AI, and building systems that work.
Beyond the demo: building RAG for production
From data ingestion to evaluation, learn how to build a production-ready retrieval-augmented generation system.
Latest from the workbench
Choosing the right embedding model
A practical guide to embedding models, including trade-offs, evaluation methods, and retrieval quality.
Deploy your first ML API with FastAPI
Turn a model into a production-ready API with validation, testing, and containerization.
What model accuracy doesn’t tell you
Go beyond a single number. Explore evaluation metrics, test sets, and practical failure analysis.
Fine-tuning vs. prompting: where to start
Understand the trade-offs between prompting and fine-tuning, and when to use each approach.
A cleaner Python project structure
A maintainable project structure for machine learning, with packaging, configuration, and testing.
Monitoring models after deployment
Practical strategies for monitoring performance, detecting drift, and setting useful alerts.