Anthropic separates workflows, which follow a fixed path, from agents, which choose the next tool call. Start only when you can tell that the job is finished.
Home/Explainers
The idea, in plain language.
Tokens, prompts, documents, and agents. Each guide answers one question first.
The short answer comes before the detail.
/ Explainers
AI explainers for the Model Context Protocol, RAG, hallucinations, prompts, and agents, with the sources attached.

What is RAG? How AI answers using your documents
What is RAG? The 2020 paper paired a generator with a Wikipedia index. A document search in front of a chatbot is related, and it still needs a check.

RAG vs fine-tuning: better knowledge or different behavior?
RAG vs fine-tuning: retrieval supplies current facts, and fine-tuning changes behavior. Choose from the failure you actually see.

Prompt engineering guide: start with a clear brief
A prompt engineering guide for real tasks: name the job, the source, the constraints, and the output. Then test one change at a time.

What are AI tokens, and why are they not the same as words?
Tokens are the units a model receives and generates.

What are text embeddings? A short guide to meaning as vectors
A text embedding represents text as a numerical vector.

Vector search explained: nearest does not always mean relevant
Vector search finds stored vectors close to a query vector under a chosen distance or similarity measure.

A bigger context window does not guarantee a better answer
A context window limits the information a model can work with during a request.

AI temperature explained: a sampling setting, not an accuracy dial
Temperature changes the probabilities used when sampling a model’s next token.

Top-p explained: limit the candidate tokens before sampling
Top-p, also called nucleus sampling, keeps a set of likely next tokens whose combined probability reaches a threshold.

Training vs inference: learning weights and using a model
Training adjusts model parameters using data and an optimization process.

Fine-tuning explained: when examples should change the model
Fine-tuning keeps training a pretrained model on examples of the behavior you want. It is a poor substitute for a document the model should look up.

Smaller AI models, less memory: what quantization trades away
Quantization stores or computes model values at reduced numerical precision.

Mixture of experts explained: many specialists, selective work
A mixture-of-experts model stores many expert blocks and uses a router so each token runs only some of them. Total size and active compute are different numbers.

Multimodal AI explained: a model can accept more than text
Multimodal systems work with more than one type of input or output, such as text and images.

Reading the text is not the same as understanding the document
OCR extracts text from an image or scanned document.

When a document tries to give your AI instructions
Prompt injection attempts to steer a model through untrusted input, such as a document or tool result.

Structured AI output: valid JSON is only the first check
Structured output constrains a response to a specified format or schema.

Streaming AI responses: show progress before the answer is complete
Streaming delivers parts of a generated response as they become available.

Batch AI processing: use asynchronous jobs for non-urgent work
Batch processing groups requests into an asynchronous job.

