PROMPTING TECHNIQUE #06
Instructional Prompts
Give AI clear step-by-step instructions for completing complex tasks
What Are Instructional Prompts?
Instructional prompts break down tasks into explicit, sequential steps that guide AI through complex processes. Instead of asking AI to figure out what needs to be done, you tell it exactly how to do it, step by step.
Think of these as recipes for AI: just as a recipe specifies "first mix dry ingredients, then add wet ingredients, then fold gently," instructional prompts specify the exact sequence and method AI should follow. This technique is especially powerful for standardizing outputs or replicating specific workflows.
The key difference from other techniques is the explicit procedural nature: you're not just describing what you want, you're prescribing how to achieve it. This level of control produces consistent, predictable results.
Why Instructional Prompts Work
AI processes instructions sequentially, activating patterns for each step before moving to the next. When you provide explicit instructions, you're creating a structured path through AI's pattern space that reduces ambiguity and increases consistency.
Each step in your instructions becomes context for the next step, building a coherent chain of pattern activations. This is especially effective because AI can't plan ahead or strategize autonomously, but it excels at following explicit procedures where each action is clearly defined.
The sequential nature also helps manage AI's context window: instead of trying to figure out everything at once, AI can focus on executing one well-defined step at a time, then move to the next with the previous step's output as context.
✓ When To Use Instructional Prompts
- Tasks requiring consistent outputs across multiple runs
- Complex workflows where sequence matters
- Quality control situations where deviations would be problematic
- Training others on a specific process or approach
- Converting human procedures into AI-executable steps
✗ When To Skip Instructional Prompts
- Simple tasks where instructions would be overkill
- Creative work where rigid structure limits quality
- Exploratory analysis where you want AI to find patterns
- When you're unsure of the best approach yourself
- Tasks where flexibility and adaptation are more important than consistency
5 Instructional Prompt Templates
Template 1: Multi-Step Process
Best for: Complex tasks that naturally break into distinct phases
Follow these steps in order to [accomplish goal]:
Step 1: [First action]
- [Specific detail about how to do this]
- [What to include/exclude]
Step 2: [Second action]
- [Build on Step 1's output]
- [Specific requirements]
Step 3: [Third action]
- [Final transformation or synthesis]
- [Quality checks]
Provide your final output as [format].
Examples:
• "Follow these steps to write a product description: Step 1: List all technical specs. Step 2: Convert each spec into a customer benefit. Step 3: Combine benefits into 3-paragraph description."
• "Follow these steps to analyze this meeting transcript: Step 1: Extract all action items with owners. Step 2: Categorize by urgency (High/Medium/Low). Step 3: Format as a prioritized bullet list."
• "Follow these steps to debug this code: Step 1: Identify the error message and line number. Step 2: Explain what the code is attempting to do. Step 3: Suggest the fix with corrected code."
• "Follow these steps to write a product description: Step 1: List all technical specs. Step 2: Convert each spec into a customer benefit. Step 3: Combine benefits into 3-paragraph description."
• "Follow these steps to analyze this meeting transcript: Step 1: Extract all action items with owners. Step 2: Categorize by urgency (High/Medium/Low). Step 3: Format as a prioritized bullet list."
• "Follow these steps to debug this code: Step 1: Identify the error message and line number. Step 2: Explain what the code is attempting to do. Step 3: Suggest the fix with corrected code."
Template 2: Quality-Controlled Output
Best for: When output quality and format are critical
Create [output type] following these requirements:
Content Instructions:
1. [Content requirement 1]
2. [Content requirement 2]
3. [Content requirement 3]
Format Instructions:
- [Structural requirement 1]
- [Structural requirement 2]
Quality Checks:
Before submitting, verify:
✓ [Criterion 1]
✓ [Criterion 2]
✓ [Criterion 3]
Examples:
• "Create a LinkedIn post following these requirements: Content: 1) Start with a hook question, 2) Share one specific insight, 3) End with clear CTA. Format: Keep under 150 words. Quality Checks: ✓ No jargon ✓ One clear takeaway ✓ Professional tone"
• "Create an email response following these requirements: Content: 1) Acknowledge their concern, 2) Explain the solution, 3) Provide next steps. Format: 3 short paragraphs. Quality Checks: ✓ Empathetic tone ✓ Action items clear ✓ Timeline specified"
• "Create a product FAQ following these requirements: Content: 1) 5 most common questions, 2) Clear 2-3 sentence answers. Format: Q&A pairs with bold questions. Quality Checks: ✓ Addresses concerns ✓ No technical jargon ✓ Actionable answers"
• "Create a LinkedIn post following these requirements: Content: 1) Start with a hook question, 2) Share one specific insight, 3) End with clear CTA. Format: Keep under 150 words. Quality Checks: ✓ No jargon ✓ One clear takeaway ✓ Professional tone"
• "Create an email response following these requirements: Content: 1) Acknowledge their concern, 2) Explain the solution, 3) Provide next steps. Format: 3 short paragraphs. Quality Checks: ✓ Empathetic tone ✓ Action items clear ✓ Timeline specified"
• "Create a product FAQ following these requirements: Content: 1) 5 most common questions, 2) Clear 2-3 sentence answers. Format: Q&A pairs with bold questions. Quality Checks: ✓ Addresses concerns ✓ No technical jargon ✓ Actionable answers"
Template 3: Conditional Instructions
Best for: Tasks where the approach depends on specific conditions
First, determine [classification criteria].
If [Condition A]:
- [Specific action 1]
- [Specific action 2]
If [Condition B]:
- [Alternative action 1]
- [Alternative action 2]
If [Condition C]:
- [Third alternative action 1]
- [Third alternative action 2]
Then, [final common step for all conditions].
Examples:
• "First, determine the customer's issue type. If technical problem: Escalate to support team with ticket number. If billing question: Check account status then provide itemized explanation. If feature request: Log in CRM and send acknowledgment. Then, follow up within 24 hours."
• "First, determine document complexity. If under 5 pages: Use Template A with standard formatting. If 5-20 pages: Use Template B with table of contents. If over 20 pages: Use Template C with executive summary. Then, apply brand style guide to all versions."
• "First, determine lead score. If score above 80: Schedule immediate call with senior rep. If score 50-80: Send personalized email sequence. If score below 50: Add to nurture campaign. Then, update CRM with next action date."
• "First, determine the customer's issue type. If technical problem: Escalate to support team with ticket number. If billing question: Check account status then provide itemized explanation. If feature request: Log in CRM and send acknowledgment. Then, follow up within 24 hours."
• "First, determine document complexity. If under 5 pages: Use Template A with standard formatting. If 5-20 pages: Use Template B with table of contents. If over 20 pages: Use Template C with executive summary. Then, apply brand style guide to all versions."
• "First, determine lead score. If score above 80: Schedule immediate call with senior rep. If score 50-80: Send personalized email sequence. If score below 50: Add to nurture campaign. Then, update CRM with next action date."
Template 4: Iterative Refinement
Best for: Outputs that need progressive improvement through multiple passes
Create [output type] using this iterative process:
Draft 1: [Initial requirements]
- Focus on [core element]
- Don't worry about [secondary elements]
Draft 2: Improve Draft 1 by:
- Adding [enhancement 1]
- Refining [enhancement 2]
Draft 3: Polish Draft 2 by:
- Checking for [quality criterion 1]
- Ensuring [quality criterion 2]
Provide your final Draft 3 as the complete output.
Examples:
• "Create a product description using this iterative process: Draft 1: List all features in bullet points. Draft 2: Convert each feature into a customer benefit with specific examples. Draft 3: Polish Draft 2 by checking that tone is conversational and removing any jargon."
• "Create a presentation outline using this iterative process: Draft 1: Create basic structure with main topics only. Draft 2: Add 3 supporting points under each main topic. Draft 3: Polish Draft 2 by ensuring logical flow and adding transition phrases."
• "Create a job posting using this iterative process: Draft 1: List role responsibilities and requirements. Draft 2: Add company culture elements and growth opportunities. Draft 3: Polish Draft 2 by making language more engaging and adding specific examples."
• "Create a product description using this iterative process: Draft 1: List all features in bullet points. Draft 2: Convert each feature into a customer benefit with specific examples. Draft 3: Polish Draft 2 by checking that tone is conversational and removing any jargon."
• "Create a presentation outline using this iterative process: Draft 1: Create basic structure with main topics only. Draft 2: Add 3 supporting points under each main topic. Draft 3: Polish Draft 2 by ensuring logical flow and adding transition phrases."
• "Create a job posting using this iterative process: Draft 1: List role responsibilities and requirements. Draft 2: Add company culture elements and growth opportunities. Draft 3: Polish Draft 2 by making language more engaging and adding specific examples."
Template 5: Validation Checklist
Best for: Critical outputs where errors could have serious consequences
[Primary instruction for creating the output]
Before finalizing, validate against this checklist:
Content Validation:
□ [Criterion 1]
□ [Criterion 2]
□ [Criterion 3]
Format Validation:
□ [Requirement 1]
□ [Requirement 2]
Compliance Validation:
□ [Standard 1]
□ [Standard 2]
Only submit output after all checkboxes can be marked complete.
Examples:
• "Write a legal disclaimer. Before finalizing, validate: Content - Covers liability, warranty, jurisdiction. Format - Under 150 words, plain language, no ambiguous terms. Compliance - Matches our standard template, reviewed for clarity."
• "Create a data privacy email. Before finalizing, validate: Content - Explains what data, why collected, how protected. Format - Scannable structure, clear headers, contact info included. Compliance - GDPR compliant, opt-out mechanism, retention policy stated."
• "Generate a financial report summary. Before finalizing, validate: Content - All figures match source data, trends explained, discrepancies noted. Format - Currency symbols consistent, decimals aligned, dates standardized. Compliance - Matches company reporting format, footnotes included."
• "Write a legal disclaimer. Before finalizing, validate: Content - Covers liability, warranty, jurisdiction. Format - Under 150 words, plain language, no ambiguous terms. Compliance - Matches our standard template, reviewed for clarity."
• "Create a data privacy email. Before finalizing, validate: Content - Explains what data, why collected, how protected. Format - Scannable structure, clear headers, contact info included. Compliance - GDPR compliant, opt-out mechanism, retention policy stated."
• "Generate a financial report summary. Before finalizing, validate: Content - All figures match source data, trends explained, discrepancies noted. Format - Currency symbols consistent, decimals aligned, dates standardized. Compliance - Matches company reporting format, footnotes included."
Pro Tips for Instructional Prompts
- Number your steps: "Step 1", "Step 2" creates clear structure that AI follows reliably
- Use action verbs: Start each instruction with verbs like "Create", "Analyze", "Extract", "Convert" for clarity
- Include negative instructions: "Do not include X" or "Avoid Y" prevents common mistakes
- Specify output format: Always end with "Provide output as [format]" to control structure
- Test and refine: Run your instructions once, see what breaks, then add clarifications for next time
Understanding the Fundamentals
Instructional prompts work because of core AI principles:
- Sequential Pattern Activation: Each instruction activates specific patterns, then the next instruction builds on that context, creating a guided path through AI's capabilities
- Context Window Management: Breaking tasks into steps helps AI manage its limited context window by focusing on one well-defined objective at a time
- Reduced Ambiguity: Explicit instructions eliminate interpretation variability, producing consistent results across multiple runs of the same prompt
Want to understand these concepts more deeply? Our Making AI Make Sense series breaks down how AI actually works.
Need Help Implementing AI in Your Business?
These templates teach techniques. We help you apply them to your specific business challenges.
Eau Claire AI - Your path to AI, made clear.