Mental models, prompting, verification, personal systems

Prompting as Task Design

Good prompting is less about magic phrases and more about designing a task clearly. This module teaches users to provide context, goals, constraints, examples, output shape, and evaluation criteria so the model can work inside a useful frame.

Deep dive summary

What this module actually teaches.

Passage 1Good prompting is less about magic phrases and more about designing a task clearly. This module teaches users to provide context, goals, constraints, examples, output shape, and evaluation criteria so the model can work inside a useful frame.

Passage 2Learners practice prompts for analysis, writing, planning, critique, extraction, comparison, and decision support. The module emphasizes iterative refinement and shows why asking the model to critique assumptions often beats asking for a final answer immediately.

Passage 3By the end, students can create prompts that are reusable, inspectable, and aligned with real work outcomes. They also learn when prompting is not enough and a workflow, retrieval system, or expert review is needed.

Learning operating system

Module prerequisites, concepts, outcomes, and artifacts

Prerequisites

  • Comfort using a chat-based AI assistant

Key concepts

  • task framing
  • context packing
  • examples
  • constraints
  • output formats
  • critique loops
  • prompt reuse

Target audience

  • Knowledge workers, students, managers, and teams using AI assistants for daily work.

Outcomes

  • Write prompts that specify context, goals, and acceptance criteria
  • Use critique and iteration to improve output quality
  • Recognize when a task needs more than prompting

Artifacts

  • prompt design checklist
  • reusable prompt patterns
  • task-to-prompt worksheet

Code example

Real patterns, ready to copy into your editor.

A code reference card that frames this module's concepts in real syntax. Copy any example to study it or adapt it directly in your own editor.

Copy-ready snippets
curriculum/fd-prompting-as-task-design.tsts
1type ModuleBrief = {2  track: string;3  difficulty: string;4  keyConcepts: string[];5  reviewGate: 'human-review-required';6};7 8export const moduleBrief: ModuleBrief = {9  track: 'Foundations',10  difficulty: 'Foundational',11  keyConcepts: [12    'task framing',13    'context packing',14    'examples',15    'constraints',16    'output formats',17  ],18  reviewGate: 'human-review-required',19};