References: Prompt engineering, "Learn to Spell"

Source material

Source curriculum (structural mirror, cited as further study):
• Full Stack Deep Learning, "LLM Bootcamp" (Spring 2023):
    Learn to Spell: Prompt Engineering
  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 (the prompt-engineering
toolkit). 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: Learn to Spell: Prompt Engineering by Charles Frye, Sergey Karayev, and Josh Tobin. The session this lesson mirrors. The recorded version walks the same toolkit with worked examples on real tasks.

Going deeper

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

Anthropic’s prompt engineering documentation. Provider-specific guidance for Claude (system prompts, XML tags, prefilling, chain-of-thought) with concrete examples. The closest match in style to the discipline this lesson recommends; equivalents exist for every major provider, but Anthropic’s is unusually well-organized.
Anthropic’s “Use XML tags” prompt-engineering page. A focused argument for the delimiters technique from this lesson, with the rationale and examples that make it stick. Cross-applicable to other providers (the principle is what matters; the tag style adapts).
OpenAI’s “Six strategies for getting better results” guide. The other major provider’s take on the same toolkit, useful both as a sanity-check on convergence and as a reference if you target multiple providers.

Adjacent topics

Where this connects inside the track and the wider curriculum.

LLM foundations for production (lesson 2). The system prompt + user message split, temperature, and the productive limits referenced here come from lesson 2; prompt engineering is the first deliberate move against them.
Augmented language models (lesson 4). Phase 2 opens with retrieval and tool use, both of which produce more text that ends up in the prompt; the prompt-engineering discipline here is what makes the augmented prompt usable.
LLMOps (lesson 7). Prompt versioning and the 20-50 example test set are the seed of an LLMOps practice; lesson 7 grows them into observability, evaluation in production, and regression-testing the prompt across model upgrades.
Track 14 lesson 7 (The main NLP tasks). The using-side companion for many of the prompt patterns here (the prompt that wraps a pipeline() task; the few-shot conventions; the structured-output discipline).