← Master Index
Vol. 13 Module 13.1 Lecture

Basic Prompting

Prompting Techniques

How This Lesson Fits the Module & Volume

Volume 12 closed with specialization via weights—adapters, LoRA, QLoRA, prefix tuning, and prompt tuning. Those methods change (or prepend) parameters so a frozen backbone behaves like a specialist.

Volume 13 opens the complementary lever: discrete prompting—natural-language instructions that steer the same model at inference time without touching weights. This lecture is the map for Module 13.1. Everything that follows—zero-shot, one-shot, few-shot, chain-of-thought, tree-of-thoughts, self-consistency, reflection, and role prompting—is a craft pattern on top of the basics introduced here.

Learning Objectives

By the end of this lesson, students should be able to:

  • Contrast PEFT/adapters (train-time specialization) with prompting (inference-time control).
  • Name the core parts of a production prompt: task, context, constraints, format, and success criteria.
  • Write a clear, specific instruction that states audience, length, and output shape.
  • Separate system-level policy from user-level task wording (preview of later lectures).
  • Spot vague prompts and rewrite them into testable specifications.
  • Choose when to prompt first versus when to fine-tune or add adapters.
Definition

Basic prompting is the practice of steering a language model with carefully written natural-language text—instructions, context, and format rules—so the model produces useful, reliable outputs without changing its trained weights.

Two Layers of Control

After Volume 12 you already know how to specialize a model by training small packs of parameters. Prompting is the application layer sitting above that stack: same API call, different text in the context window.

LayerWhat you changeWhen it runsTypical cost
Full FT / SFTMany or all weightsTrain timeHigh compute & storage
PEFT adapters / LoRATiny parameter packsTrain timeLow storage; still needs data
Soft prompt / prefix tuningLearned continuous tokensTrain timeTiny packs; context tax
Discrete promptingReadable text onlyInference timeTokens + iteration time

Rule of thumb: prompt first for format, tone, and light task shaping; reach for PEFT when prompting cannot close a reliable quality gap or when you need a durable specialist shared across many calls.

Anatomy of a Strong Prompt

Task

  • What to do (verb + object).
  • Who the audience is.
  • What “done” looks like.

Context

  • Facts the model must use.
  • Source text, schema, or policy.
  • What to ignore.

Constraints & Format

  • Length, tone, banned content.
  • Structure (bullets, JSON, table).
  • Explicit “if unknown, say so.”

Weak vs Strong Prompt

Vague prompts force the model to invent missing requirements. Specific prompts make failures measurable—essential later in prompt evaluation.

# Weak Summarize this article. # Strong Summarize the article below for a busy product manager. Constraints: - Exactly 5 bullets - Each bullet <= 20 words - No quotes; paraphrase only - If a claim is speculative in the source, mark it (speculation) Article: {{ARTICLE_TEXT}}

A Practical Template

You are helping with {{DOMAIN}}. Goal: {{CLEAR_VERB_PHRASE}}. Input: {{PASTED_OR_RETRIEVED_CONTEXT}} Requirements: 1. {{AUDIENCE_AND_TONE}} 2. {{LENGTH_OR_STRUCTURE}} 3. {{MUST_INCLUDE_OR_EXCLUDE}} 4. If information is missing, say "Insufficient information" instead of guessing. Output format: {{EXAMPLE_SHAPE_OR_SCHEMA}}

System vs User (Preview)

Chat APIs often split messages into roles. Put durable policy and persona in the system prompt; put the changing task and documents in the user prompt. Module 13.1 returns to that split in detail after the core techniques.

1. Clarify

Task + success criteria

2. Ground

Paste or retrieve facts

3. Constrain

Format, tone, limits

4. Iterate

Test failures, tighten text

Strengths and Tradeoffs

Strengths

  • No training pipeline; ship in minutes.
  • Inspectable and editable by non-ML staff.
  • Composes with any PEFT-specialized base.

Tradeoffs

  • Uses context tokens every call.
  • Brittle if left vague or contradictory.
  • Cannot teach brand-new knowledge as reliably as SFT on domain data.
Common Misconception

“Prompting replaces fine-tuning.” They solve different problems. Prompting controls behavior for this request. Adapters and SFT change default behavior across many requests. Production systems often use both: a lightly adapted model plus carefully engineered prompts, later wrapped with guardrails.

Knowledge Check

  1. Short Answer: What does Volume 13 add that Volume 12 adapters do not? Answer: Inference-time discrete (text) control without changing weights.
  2. True/False: Basic prompting requires updating model parameters. Answer: False.
  3. Multiple Choice: The best first step for a vague product ask is usually: (a) full FT, (b) clarify task/format in a prompt, (c) train from scratch. Answer: (b).
  4. Short Answer: Name three parts of a strong prompt. Answer: Task, context, and constraints/format (audience/success criteria also acceptable).
  5. True/False: Soft prompt tuning and typing a natural-language prompt are the same technique. Answer: False—one learns continuous embeddings; the other is discrete text.
  6. Multiple Choice: Durable persona/policy belongs mainly in: (a) system prompt, (b) random user message only, (c) the tokenizer vocab. Answer: (a).
  7. Short Answer: Why is “Summarize this” a weak prompt? Answer: It omits audience, length, format, and success criteria.
  8. True/False: Prompting can be used on top of a LoRA-adapted model. Answer: True.
  9. Multiple Choice: Prefer PEFT over prompting alone when: (a) you need a durable specialist the prompt cannot reliably achieve, (b) you only need five bullets once, (c) you lack a keyboard. Answer: (a).
  10. Short Answer: What should the model do when required facts are missing? Answer: State insufficient information instead of guessing (if instructed).

Key Takeaways

  • Prompting is application-layer control; adapters/PEFT are train-time specialization.
  • Strong prompts specify task, context, constraints, and output format.
  • Rewrite vague asks into testable specifications before adding complexity.
  • Next: Zero Shot—solving tasks with instructions alone.
Trainer’s Guide

Hands-on idea: Give students one messy business email and three rewrite targets (PM bullets, legal risk list, customer reply). Compare outputs from a one-line prompt versus the strong template.

Discussion prompt: When would you ship a LoRA adapter instead of iterating on prompts for another week?

Recap: Basic prompting turns goals into precise, checkable instructions. Continue with Zero Shot.