Evaluating LLM applications
Build test sets, grade outputs with code, people and model-based graders, and catch regressions before your users do.
Large language models, embeddings and building applications with them.
Build test sets, grade outputs with code, people and model-based graders, and catch regressions before your users do.
How LLM agents call tools in a loop, how to design tools they use well, and how to keep agents safe and reliable.
Turn text into vectors, build a semantic search index, and ground an LLM's answers in your own documents.
How LLMs work, how to write prompts that get reliable results, and how to check what comes back.
Hugging Face's free course on large language models and NLP with the Transformers, Datasets and Tokenizers libraries.
A free course on building AI agents: tools, reasoning loops, frameworks and evaluation.
Andrew Ng on how generative AI works, what it's good for, and how to use it in work and business.
50 in this topic
The building blocks of a good prompt — context, task, constraints and format — with before-and-after examples.
Generative AI 2 min read 24 Jul 2026
Showing a model a few examples of the input and output you want is often clearer than describing it. How to choose good examples.
Generative AI 2 min read 23 Jul 2026
How to get JSON and other machine-readable output reliably from a language model, and how to validate it.
Generative AI 2 min read 22 Jul 2026
What hallucination is, why it happens, and practical ways to reduce and catch it.
Generative AI 2 min read 21 Jul 2026
How RAG grounds a language model's answers in your own documents, the components involved, and where it goes wrong.
Generative AI 2 min read 20 Jul 2026
Embeddings turn text, images and other data into vectors where similar meanings sit close together. How they work and what they're used for.
Generative AI 2 min read 19 Jul 2026
How vector indexes find the nearest embeddings quickly, the main options, and when you don't need one.
Generative AI 2 min read 18 Jul 2026
How to split long documents so search finds the right passage — chunk size, overlap, structure and metadata.
Generative AI 2 min read 17 Jul 2026
How to pick an LLM for your use case: quality, cost, speed, context length, privacy and licence.
Generative AI 2 min read 16 Jul 2026
The trade-offs between models you can download and run yourself and models accessed through a provider's API.
Generative AI 2 min read 15 Jul 2026
What temperature, top-p and other sampling parameters do, and sensible settings for different tasks.
Generative AI 1 min read 14 Jul 2026
How to measure the quality of language model outputs with test sets, code checks, human review and model-based grading.
Generative AI 2 min read 13 Jul 2026
What makes an LLM an agent, how the tool-use loop works, and when an agent is the right design.
Generative AI 2 min read 12 Jul 2026
How attackers manipulate language models through crafted inputs, and the layered defences that reduce the risk.
Generative AI 2 min read 11 Jul 2026
How to get useful help from AI coding tools while keeping code correct, secure and maintainable.
Generative AI 2 min read 10 Jul 2026
How text-to-image models turn noise into pictures, what controls the output, and the legal and ethical questions to consider.
Generative AI 2 min read 9 Jul 2026
Models that understand and generate across text, images, audio and video — what they can do and how to use them.
Generative AI 2 min read 8 Jul 2026
Practical ways to cut token costs: model choice, prompt size, caching, batching and routing.
Generative AI 2 min read 7 Jul 2026
How system prompts set a model's role, rules and tone for a whole conversation, and how to write ones that hold up.
Generative AI 2 min read 6 Jul 2026
Why letting a model work through a problem improves answers, and how dedicated reasoning models change prompting.
Generative AI 2 min read 5 Jul 2026