In the pack: ChatGPT, Claude & Gemini Custom Instructions Examples
Test Each Settings Layer in Fresh Chats
Prompt
The standing instructions I have set: {{STANDING_INSTRUCTIONS}}
The tasks I most often ask for: {{TYPICAL_TASKS}}
My assistant: {{MAIN_TOOL}}
Design a test that isolates my instructions from my memory.
1. Write six test prompts: four typical tasks from my list, one task where my instructions should NOT apply (to see if they leak), and one that tries to make the assistant break one of my rules.
2. For each, give observable pass signs and fail signs (for example "first sentence is the answer", "no emoji").
3. Tell me how to run each prompt in two fresh chats: one with my settings as they are, and one with memory or personalization switched off for that chat using the control {{MAIN_TOOL}} offers for that. If you are not sure which control exists in my version, say so and tell me to check the vendor's help page.
4. Give a way to read the results: which failures mean a line is vague, which mean two settings conflict, and which mean the line belongs elsewhere.
Format: numbered tests with Pass signs / Fail signs, then the run procedure, then the reading guide. Do not run the tests yourself.
Customize this prompt
Fill in the variables below to personalize this prompt:
Model Settings
Recommended Models
Temperature
Max Tokens
Additional Notes
About this prompt
“Test Each Settings Layer in Fresh Chats” is a free prompt for ChatGPT in the Prompt Engineering category, 213 words long, added to The Prompt Index on November 18, 2026 by The Prompt Index. Copy it with the button above, paste it into ChatGPT or any other AI chat assistant, and send it.
It has 3 placeholders to fill in first:
{{STANDING_INSTRUCTIONS}}, {{TYPICAL_TASKS}}, {{MAIN_TOOL}}.
Use the “Customize this prompt” fields to personalise it before you copy.
Recommended models: ChatGPT, Claude, Gemini.
0 upvotes, sent to an AI tool 0 times, viewed 5 times.
Browse all Prompt Engineering prompts, the AI prompt database or use the AI prompt finder to search every prompt.