References: Augmented language models

Source material

Source curriculum (structural mirror, cited as further study):
• Full Stack Deep Learning, "LLM Bootcamp" (Spring 2023):
    Augmented Language Models
  Instructors: Charles Frye, Sergey Karayev, and Josh Tobin
  Course page: https://fullstackdeeplearning.com/llm-bootcamp/
  Lecture videos: publicly available on the Full Stack Deep Learning
    YouTube channel
  License: bootcamp materials are published free to view but no explicit
    license (Creative Commons or otherwise) is published; lecture videos
    are on YouTube under standard terms.
  Required attribution: "Based on the structure of the Full Stack Deep
    Learning LLM Bootcamp (Spring 2023), by Charles Frye, Sergey Karayev,
    and Josh Tobin (fullstackdeeplearning.com/llm-bootcamp). This is an
    independent structural mirror in original prose; it reproduces no
    course materials, and Full Stack Deep Learning does not endorse it."
This lesson mirrors the structure of the corresponding bootcamp session (RAG and tool use).
Clawdemy's lessons are original prose that follows the pedagogical arc of
the bootcamp. Because the source publishes no explicit license, we cite
it as a recommended companion and reproduce none of its materials.

Watch this next

• Full Stack Deep Learning, LLM Bootcamp: Augmented Language Models by Charles Frye, Sergey Karayev, and Josh Tobin. The session this lesson mirrors. The recorded version walks the same patterns with the bootcamp’s worked examples.

Going deeper

A short, durable list. Each link is a specific next step, not a generic pile.

• “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks” by Lewis et al. (2020). The paper that introduced RAG as a method; useful for the original motivation even though production patterns have moved on since.

• Anthropic’s tool use documentation. Provider-specific reference for the tool-use API used in this lesson; the four-step shape from the lesson maps directly onto the docs’ examples.

• The Chroma documentation, “Embeddings” guide. The simplest self-hosted vector store with clean docs; pair it with this lesson to actually build a tiny RAG pipeline against a folder of your own documents.

Adjacent topics

Where this connects inside the track and the wider curriculum.

• Prompt engineering, “Learn to Spell” (lesson 3). The discipline that wraps retrieved context: how the prompt presents chunks and citations decides whether the model uses them well.

• LLM foundations for production (lesson 2). The three productive limits (context / cost / latency) are the constraints every RAG and tool-use decision lives against.

• Project walkthrough (lesson 5). The next lesson reads a real application end-to-end so the moving parts here have a worked-example shape.

• Agents (lesson 10). The tool-use loop here is the seed of agent behavior: model decides, tool runs, model continues, repeat.

• Track 14 lesson 11 (Curating high-quality datasets). The using-side companion for the “good data matters more than more data” principle that applies to retrieval as much as to training.