Instruction

As explained in Coding with AI

A directive that specifies an action or response an artificial-intelligence model should produce.

An instruction tells an artificial-intelligence model what action or response to produce. Clear, direct language generally improves results and reduces errors. section 9.2

Write instructions that:

• Use simple language and avoid unnecessary jargon. section 9.2
• State the desired action or response directly, using active wording. section 9.2
• Break complex tasks into manageable steps. section 9.2
• Supply relevant context and concrete examples alongside the instruction. section 9.2

A practical instruction

Give the existing project as context, then ask: “Add the requested feature. Explain the changes briefly, divide the work into steps, and show the resulting code.” If the response misses the goal, continue the conversation and clarify the request. section 9.2

Figure 9.3 A good prompt starts with great context (usually provided by the tool). This includes your existing project. Next, you add good examples and clear instructions. The process is very similar to communicating verbally with a human.

Use the prompt anatomy diagram to see how context, examples, and clear instructions work together. section 9.2

How Coding with AI covers it

How deep it goes

Defines clarity, directness, simple language, and task breakdown, but does not descend into model internals.

Examples

Uses existing project context, concrete examples, conversational clarification, and stepwise task requests.

What it assumes

Assumes basic human communication skills while teaching context, clarity, specificity, and examples for LLM interactions.

What you can do after

Apply it to write clearer prompts and improve model responses through clarification and task decomposition.

How it connects

Connects instructions with prompt engineering, context, examples, LLMs, and IDE tools.

liveBookmanning.com

Read Coding with AI on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Prompt Engineering in PracticeAn instruction is a directive within a prompt that specifies the task the model should perform.
• 

  liveBookmanning.com
  Building LLM Applications with DSPyText within a prompt that directs a language model’s behavior or specifies how it should perform a task.
• 

  liveBookmanning.com
  LLMs in ProductionThe instruction component of a prompt is the task-specific directive that specifies what the language model should do.
• 

  liveBookmanning.com
  The Art of AI Product DevelopmentA prompt instruction is the task specification that tells a model what operation to perform.

Compare how 5 books explain instruction →

Related concepts

• constraintcontrasts with · A constraint is a condition or rule that restricts the permissible states, values, actions, or solutions in a system or problem.
• promptpart of · An input, typically containing instructions or context, supplied to an artificial-intelligence model to guide or elicit its output.
• system promptincludes · A system prompt is a high-priority instruction or context supplied to an AI model to establish its role, task, behavioral guidance, or constraints.
• agent skillincludes · An agent skill is a reusable package of instructions, capabilities, or supporting resources that guides an AI agent in performing a task or workflow.
• COPROconfigured by · COPRO is a DSPy prompt-optimization technique that iteratively generates and evaluates alternative prompt instructions to improve their performance.
• MIPROv2produced by · MIPROv2 is a DSPy optimizer that searches for effective instructions and demonstrations for language-model programs using performance feedback and a Bayesian proposal model.

This explainer was generated by Manning's knowledge graph from the text of Coding with AI. The section links point to the parts of the book it draws on.