ChatGPT
ChatGPT is strongest when the answer has a shape you can name in advance: JSON, a table, a function signature, a sequence of tool calls. Custom instructions and project files persist your rules across a conversation, so most of what people paste into every message belongs there instead. Long inputs are handled well, but the model follows the most recent instruction more eagerly than the first one, so keep the binding rules near the end of a long prompt.
Models
ChatGPT prompts
All 3- Universal
Write a SQL query from a plain question
Produces one query against a schema you provide, and asks a question instead of guessing when the schema is ambiguous.
- Universal
Extract structured data as JSON
A strict extraction prompt that returns valid JSON only, with nulls for missing fields instead of invented values.
- Universal
Strict code review of a diff
A review prompt that reports only what would break in production, gives the smallest fix for each finding, and is allowed to say the diff is fine.
Configuration files
All 4- Universal
Editor rules for a Django project
A rules file that pins the Django and Python versions, the app layout and the things an assistant should never regenerate.
- Universal
System prompt for a support triage bot
A system prompt for classifying incoming support messages into a fixed set of routes, with an explicit escape for the unclear ones.
- ChatGPT
ChatGPT custom instructions for technical work
A custom instructions pair that removes preamble, keeps answers checkable and stops confident guessing.
- ChatGPT
AGENTS.md for a TypeScript repo
A project file for coding agents that names the commands, the boundaries and what must never be touched automatically.
Guides
- Universal
Moving your rules into a config file
How to stop repeating the same instructions in every message, and what belongs in a system prompt against what belongs in the task.