Prompt Spray
BTC

The Spray Strategy Guide — Multi-Prompt, Multi-Model Testing

How to design prompt variations, run multi-model comparisons, and systematically find the best AI output.

The Strategy Guide 🎯

Systematic variation beats random hope.


Designing Prompt Variations

The key to effective spraying is varying one dimension at a time so you can attribute quality differences to specific changes.

Variation 1: Framing

Same question, different frame changes the response style:

FramePromptOutput Tendency
Expert"As a senior data scientist, explain..."Technical, detailed
Teacher"Explain to a university student..."Educational, structured
Journalist"Write a news article about..."Concise, quote-heavy
Consultant"Advise a client on..."Strategic, actionable
Sceptic"Challenge the assumption that..."Critical, balanced

Variation 2: Structure

Same content request, different format instruction:

  • "Write a paragraph about X"
  • "Create a bullet-point summary of X"
  • "Build a comparison table of X"
  • "Draft an FAQ about X"
  • "Write X as a step-by-step guide"

Variation 3: Constraints

Same question with different tightness:

Constraint LevelExample
Loose"Tell me about renewable energy"
Medium"Explain the top 5 renewable energy sources for UK homes"
Tight"Compare solar panels vs heat pumps for a 3-bed semi in Manchester, budget under £10k, including ROI timeline"

Multi-Model Comparison Strategy

When to Use Which Model

TaskBest First ChoiceBest Second ChoiceWhy
Long-form writingClaudeChatGPTClaude handles nuance and tone better
Code generationChatGPT / CopilotClaudeChatGPT has deeper code training
Factual researchPerplexityGeminiBoth have search grounding
Creative/brainstormChatGPTClaudeChatGPT is more willing to be creative
Data analysisChatGPT (Code Interpreter)GeminiCode execution matters
SummarisationClaudeGeminiClaude handles long contexts well

The Three-Model Sprint

For important tasks, run the same prompt through three models simultaneously:

  1. Send to Claude, ChatGPT, and Gemini
  2. Read all three outputs (2-3 minutes)
  3. Pick the best overall
  4. Use the best output as a base and iterate in that model

Total time: 5 minutes. Quality improvement over single-model: typically 25-40%.


Temperature Spraying

Temperature controls randomness in AI outputs. Most people leave it at default. Spraying across temperature settings reveals surprising quality differences.

TemperatureOutput CharacterBest For
0.0-0.3Conservative, predictable, factualCode, data, factual writing
0.4-0.7Balanced (default range)General content, business writing
0.8-1.0Creative, varied, surprisingBrainstorming, creative writing
1.0-1.5Wild, unpredictable, occasionally brilliantIdeation, creative exploration

Run the same prompt at 0.3, 0.7, and 1.0. You will see three notably different outputs. Pick the one that best suits your purpose.


Evaluating Spray Results

The Quick Evaluation Matrix

For each output, score 1-5 on four dimensions:

DimensionWhat to Evaluate
AccuracyAre the facts correct? Claims verifiable?
RelevanceDoes it answer what was actually asked?
QualityIs it well-written, well-structured, clear?
UsefulnessCan you use this directly with minimal editing?

Total score out of 20. The winner is usually clear within 30 seconds of scanning.


Cost Management

Spraying costs more than single-shot — but less than most people think.

StrategyCost per Task (API)Cost per Task (Subscription)
Single shot$0.01-0.05Included
3-model spray$0.03-0.15Included (if subscribed to all 3)
3-variant x 3-model$0.09-0.45Included

For subscription users (ChatGPT Plus, Claude Pro, Gemini Advanced), spraying is essentially free — you are paying flat rate regardless. There is no cost reason not to spray on subscriptions.