Skip to content

References: Prompt Engineering Foundations

  1. Prompt engineering - Wikipedia - Offers an accessible overview of Prompt engineering, including definitions, methods, examples, limitations, and related concepts. This foundation helps students reason carefully about writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  2. Large language model - Wikipedia - Offers an accessible overview of Large language model, including definitions, methods, examples, limitations, and related concepts. Its examples help students evaluate evidence for writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  3. Instructional design - Wikipedia - Offers an accessible overview of Instructional design, including definitions, methods, examples, limitations, and related concepts. It supplies useful context for decisions about writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  4. Prompt Engineering for Generative AI - James Phoenix and Mike Taylor - O'Reilly Media - Covers prompt structure, context, examples, evaluation, reliability, retrieval, and practical patterns for major generative-AI tasks. Its sustained treatment supports work on writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  5. Design for How People Learn (2nd ed.) - Julie Dirksen - New Riders - Explains objectives, audience needs, context, feedback, practice, constraints, and clear instruction design through accessible examples. Its cases illuminate tradeoffs involved in writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  6. Prompt Engineering Guide - OpenAI - Presents practical techniques for writing clear instructions, supplying relevant context, using examples, structuring tasks, and improving model reliability through iteration. Its methods give teams a starting point for writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  7. Structured Outputs - OpenAI - Shows how schema-constrained generation can produce predictable fields and types while clarifying validation, refusals, supported schema features, and failure handling. Its comparisons clarify choices involved in writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  8. Working with Evals - OpenAI - Introduces test data, evaluation criteria, graders, repeated runs, and comparison workflows for measuring model behavior instead of relying on impressions. Its framework strengthens responsible work on writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  9. Building Effective Agents - Anthropic - Distinguishes workflows from agents and illustrates routing, parallelization, orchestration, evaluation, tool design, and appropriate control of system complexity. Its examples show how evidence informs writing clear, bounded, testable prompts with roles, context, constraints, and outputs.

  10. Generative AI Profile - NIST - Extends the AI Risk Management Framework with generative-AI risks and suggested actions concerning confabulation, bias, privacy, information integrity, and human oversight. Its implementation advice helps teams practice writing clear, bounded, testable prompts with roles, context, constraints, and outputs.