Stop Saying 'Make This Better'

The most common prompting mistake that leads to generic, robotic responses — and the exact 4-part structure that fixes it.

01 / THE MISTAKE

WHY TRADITIONAL PROMPTING FAILS

When you tell an AI 'make this better', it has zero reference frame. It guesses what you value (brevity? formality? humor? complexity?) and gives you bland corporate-speak.

02 / THE 4-PART FRAMEWORK

STRUCTURE YOUR PROMPT FOR PEAK ACCURACY

1. ROLE

Who the AI is pretending to be (e.g. 'Senior Staff Architect at Stripe')

2. CONTEXT

Why this task exists and who the audience is (e.g. 'Writing an internal post-mortem for executive leadership')

3. CONSTRAINTS

What NOT to do (e.g. 'No buzzwords, keep under 250 words, prioritize technical failure metrics')

4. EXAMPLES

One before/after snippet demonstrating the exact tone you expect

03 / READY-TO-USE PROMPT TEMPLATECOPY & ADAPT

“Act as a Lead Technical Editor at an engineering publication. Rewrite this 3-paragraph explanation of database indexing for junior software developers. Keep the language direct and punchy. Eliminate all adjectives like 'seamless' or 'revolutionize'. Include one real-world analogy involving a library card catalog.”

WHY IT WORKS: LLMs navigate probability distributions. Constraints narrow the probability space to the top 1% of high-signal vocabulary.

SARVESH'S WORKFLOW RECOMMENDATION

Save this template in a text snippet expander so you can summon it with `;prompt`.