Few-Shot Text Classification with Scikit-LLM
Scikit-LLM bridges LLMs and scikit-learn for few-shot text classification. Classify new text accurately with just a handful of labeled examples.
Data Science
Building a Human-in-the-Loop AI Refund Agent with LangGraph
Learn how to build a LangGraph refund agent that pauses for human approval before executing financial actions using interrupt() checkpoints.
Ten GitHub Projects Built with Jev Decision Models
Jev turns agent decisions into typed outputs with probabilities. Here are ten GitHub repositories showing practical ways to build with it.
10 Solved Generative AI Projects to Build Your Portfolio
A curated guide to 10 solved AI projects spanning machine learning to generative AI, with tools, learning outcomes, and source code links.
Tool Calling vs. Code Execution for AI Agents
Learn how tool calling and code execution differ as agent action primitives, and when to choose each based on cost, latency, and accuracy.
RAG vs. Fine-Tuning for Domain Adaptation: When to Use Which
RAG and fine-tuning solve different problems. Learn the mechanical difference, see working code examples, and use a six-point framework to decide.
MLOps vs LLMOps vs AgentOps: How AI Operations Have Evolved
MLOps, LLMOps, and AgentOps solve different operational problems. Learn how observability evolves as AI systems move from prediction to action.
Why You Think Like a Bayesian But Were Taught Like a Frequentist
We're wired to reason like Bayesians but trained as frequentists. Here's why that gap exists and what it means for how we understand probability.
Dynamic Agent Skills: Resolving Facts at Call Time
Static agent skills are caches with no invalidation. Here's an architecture that separates authored procedure from live fact resolution.
From RAG to Agentic AI: Building Intelligent Enterprise Systems
Three generations of enterprise AI retrieval systems—from hybrid RAG to agentic architectures—and the engineering principles that make them work in production.
GPT-6 Astra Explained: Features, Benchmarks, and Comparisons
OpenAI's GPT-6 Astra adds computer use, persistent memory, and document generation. Here's what changed, the benchmark numbers, and where caveats apply.
A Practical Introduction to Bayesian Neural Networks in Python
Standard neural networks output single predictions with no uncertainty. Bayesian Neural Networks fix this by replacing point weights with probability distributi