Adaptive skill practice — find your level, get sharper.
AI & LLMs practice
Build with language models — RAG, prompting, evals
Work effectively with large language models — tokens and tokenization, context windows, embeddings and vector search, prompting (zero/few-shot, system prompts, chain-of-thought), sampling controls (temperature/top-p), RAG vs fine-tuning, evaluation (benchmarks, LLM-as-judge), hallucination and prompt injection, and tool/function calling. Durable concepts for building with LLMs; specific model facts are noted as version-sensitive. Part of the Developer track.
• Meets you at your level — never too easy, never too hard.
• Adapts every question to how you’re doing.
• Tracks your level over time. Skill practice, not a test.
All exam, test, and product names and trademarks are the property of their respective owners and are used here for identification and reference only. Keentune is independent study practice — not affiliated with, authorized, or endorsed by any of these organizations.