AI & ML covers how learning systems are built, evaluated, and operated — from classic supervised models through large language models to the agent tooling that turns models into day-to-day engineering leverage. The unifying theme across all three branches: the model is rarely the hard part. Data quality, evaluation discipline, guardrails, and monitoring decide whether a system works in production, and that engineering work looks remarkably similar whether the model is a gradient-boosted tree or a frontier LLM.

Questions

When should you reach for classic ML instead of an LLM API?

• Classic ML wins when the task is a well-defined prediction with labeled data: classification, regression, ranking — millisecond latency and near-zero per-request cost at scale
• LLMs win when the task involves open-ended language understanding or generation, training data is scarce, or iteration speed matters more than unit cost
• A common production pattern: prototype with an LLM to validate the product, then distill the stable, high-volume part into a small fine-tuned model
• Key tradeoff: classic ML trades upfront data and training effort for cheap, fast, predictable inference; LLMs trade per-call cost and latency for flexibility and zero training

Why does evaluation discipline matter more than model choice?

• Without held-out evaluation, every model swap, prompt change, or retraining run is a guess — improvements cannot be distinguished from noise or regressions
• Production failures are dominated by data and distribution problems (drift, leakage, segment regressions), which only evaluation and monitoring catch — not by raw model capability
• A weaker model with solid evaluation and a feedback loop improves over time; a stronger model without them silently degrades
• This is why every branch of this section has its own evaluation pages: ML Evaluation and the general LLM Evaluation, which RAG and agents specialize in RAG Evaluation and Agent Evaluation

References

• Rules of Machine Learning (Google for Developers) — Google’s practical guide to ML engineering, including when to use ML versus simpler approaches.
• Building Effective Agents (Anthropic Engineering) — the canonical guidance on choosing the simplest agentic pattern that solves the problem.
• Hidden Technical Debt in Machine Learning Systems (NeurIPS 2015) — the classic paper on why the model is a small fraction of a production ML system.
• AI Risk Management Framework (NIST) — vendor-neutral framework for managing AI risk across the lifecycle.