Context and Grounding — Free AI Learning Track

How to make models answer from trusted sources.

The Context and Grounding track answers one question: how do you make a model answer from trusted sources instead of its own memory? A base model knows only its training data, and most production failures trace back to the model missing information it was never given.

Three modules cover the discipline. How RAG Works explains retrieval-augmented generation end to end, from chunking and embeddings through hybrid search, re-ranking, and citation, plus the division of labor between retrieval and fine-tuning. Context Engineering 101 treats the context window as a scarce resource and teaches the techniques that keep long-running work coherent: compaction, structured note-taking, sub-agents, and progressive disclosure. Context Engineering vs Prompt Engineering draws the line between wording a request and architecting the information a model receives, through the four pillars of memory, retrieval, state, and tool access.

Together, the modules shift your attention from how a prompt is phrased to what the model can actually see, which is where reliable systems are won.

Modules in this track

How RAG Works (4 min)

Retrieval-augmented generation is the standard pattern for grounding AI answers in trusted source material.

A base language model knows only what it was trained on. Retrieval-augmented generation solves that limitation by fetching relevant documents at query time and injecting them into the prompt before the model generates its answer. The system has two halves: an offline ingestion pipeline that chunks documents, embeds them, and stores them in a vector database, and an online retrieval pipeline that embeds the query, finds the most similar chunks, re-ranks them, and passes them to the model alongside the user's question. The model then generates a grounded answer with verifiable citations.

Context Engineering 101 (4 min)

The hardest problem in production AI is not phrasing the question. It is deciding what information the model should see at each step.

Context engineering is the discipline of managing the information a model has at the moment it generates a response. Context includes the system prompt, conversation history, examples, tool outputs, retrieved documents, and any data the model can see. The context window is finite. Dumping more information into it often makes answers worse because models bias attention toward the start and end of the window. Good context engineering curates and composes the minimum useful information at each step, compresses what is stale, preserves what is durable in external notes, and splits work across sub-agents when a single context gets overwhelmed.

Context Engineering vs Prompt Engineering (4 min)

A failed AI feature is almost always an architecture failure, not a wording failure.

Prompt engineering is the craft of writing a static instruction: role, examples, constraints, chain-of-thought triggers. It is useful, but it hits a ceiling the moment the model lacks information that was not in the prompt. Context engineering is the programmatic assembly of everything the model receives at inference time. It handles memory, retrieval, state, and tool access as a coordinated system. A prompt is a script handed to an improv actor. Context is the entire stage, props, and briefing dossier assembled before the actor speaks.

Part of the free AI Learning Hub by Shahzad Asghar. The whole track takes about 12 minutes and is free to read with no account required.