Prompt Generator V2 — KERNEL Framework

KERNEL at a Glance

Workflow

Step 0: Determine Mode

Step 1: Understand Intent

1. What's the single goal? — If multiple goals detected, suggest splitting into a prompt chain
2. What does success look like? — Specific, verifiable criteria (numbers, formats, concrete deliverables)
3. What should it NOT do? — Constraints and exclusions

Step 2: Apply KERNEL

Step 3: Generate the Prompt

## Context
[Background information the AI needs. Keep minimal — only what's necessary to understand the task. Include domain, audience, and relevant technical context.]

## Task
[One clear, specific goal. Start with an action verb. This is the single sentence that passes the K-test.]

## Constraints
- [What to do — specific, measurable behaviors]
- Do NOT [negative constraint 1]
- Do NOT [negative constraint 2]
- [Additional bounds: length, format, libraries, scope limits]

## Output Format
[Exact structure of the expected output. Include: format (markdown, JSON, code), length bounds, sections/headers if applicable, delimiters.]

## Verification
[How to check success — specific criteria that make the E-principle concrete. Think: "I'll know this worked when..."]

• Examples — When output quality depends on seeing patterns (2-3 examples: basic + edge case)
• Input — When the prompt processes structured data (describe format, required fields)
• Chain — When the task was split, show how prompts connect

Step 4: Verify with KERNEL Checklist

• K: Can I describe this prompt's goal in one sentence?
• E: At least 2 measurable success criteria?
• R: No temporal references, no version-ambiguous terms?
• N: Exactly one deliverable per prompt?
• E: At least 2 explicit "do NOT" constraints?
• L: Follows Context → Task → Constraints → Format structure?
• No vague virtue words ("good", "helpful", "detailed") without concrete definition
• No contradictions (e.g., "be concise" + "cover everything")
• All implicit assumptions made explicit

Step 5: Deliver and Iterate

• Show each prompt in the chain, numbered
• Explain how outputs feed into subsequent prompts
• Suggest which prompts can run in parallel vs sequential

Prompt Chaining

• Has a single clear goal (passes all KERNEL checks independently)
• Produces output that feeds cleanly into the next prompt
• Can be verified independently before moving to the next step

1. Design data models (output: schema)
2. Generate endpoint specifications (input: schema → output: OpenAPI spec)
3. Implement endpoints (input: OpenAPI spec → output: code)
4. Write tests (input: code + spec → output: test suite)

Failure Modes