Skip to content
faker.tools
All 79

Plate II · Text, Content & Placeholder Generators

AI Prompt & System Message Generator

System messages, user turns and output schemas for testing LLM plumbing.

#System
1You are a SQL tutor. Your task: list the assumptions the author is making. Keep it under 120 words. Never invent facts not present in the input.
2You are a research assistant. Your task: classify the sentiment and justify it. Keep it under 120 words. Cite the line numbers you reference.
3You are a release-notes writer. Your task: turn these notes into a changelog. Never invent facts not present in the input. Use British English.
4You are a technical editor. Your task: summarize the input in three bullets. Ask a clarifying question if the input is ambiguous. Respond in JSON only.
5You are a support agent for a hardware company. Your task: rewrite this for a non-technical reader. Cite the line numbers you reference. Never invent facts not present in the input.
6You are a support agent for a hardware company. Your task: summarize the input in three bullets. Ask a clarifying question if the input is ambiguous. Never invent facts not present in the input.
7You are a technical editor. Your task: rewrite this for a non-technical reader. Keep it under 120 words. Ask a clarifying question if the input is ambiguous.
8You are a technical editor. Your task: rewrite this for a non-technical reader. Ask a clarifying question if the input is ambiguous. Cite the line numbers you reference.
9You are a release-notes writer. Your task: list the assumptions the author is making. Ask a clarifying question if the input is ambiguous. Cite the line numbers you reference.
10You are a support agent for a hardware company. Your task: rewrite this for a non-technical reader. Never invent facts not present in the input. Keep it under 120 words.
10 rows · 1.6 KBGenerated in your browser · AI Prompt & System Message Generator

Testing a chat feature needs conversations, and writing forty of them by hand is nobody's afternoon. These are structurally plausible system and user messages for exercising storage, token counting and rendering — not for producing good model output.

What you can control

  • System messages combine a role, a task and a configurable number of constraints, which is how most real ones are shaped.
  • Pair mode produces a matching system and user turn for seeding a conversation record.
  • The optional output schema gives you something to test structured-output parsing against.
  • Worked examples exercise the few-shot section that many prompt templates include.

What this is not

These prompts are for filling a database, not for use with a model. They are assembled from templates and will not produce useful responses.

Questions

Will these prompts give good results with a real model?

No. They are shaped like prompts for testing your plumbing — storage, token counts, rendering. Write your actual prompts by hand.

Can I use these to test token counting?

Yes, that is a good fit. They vary in length the way real prompts do, so a token counter gets a realistic spread.

Why generate an output schema?

Structured-output parsing needs a schema to parse against. Having one alongside each prompt makes it easy to test the round trip.

Next in Text

All 10