System Prompt
A system prompt is a set of high-priority instructions. It sets an AI product’s role, limits, tools, and rules for replies.
Another example
A support agent learns which account actions need confirmation. It also learns when a person must take over.
Main parts
- 01User intent and context
- 02Model or tool decision
- 03Grounded result and fallback
Use it when
Use it for steady product behavior that shouldn't change with each user message.
Do not use it when
Never put secrets in a prompt or assume written instructions can enforce security by themselves.
Name used in code
system / developer message Before you ship
Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback.
Outcome: Use or evaluate System Prompt to make AI behavior measurable and tied to evidence. User context: A support agent learns which account actions need confirmation. It also learns when a person must take over. AI method or concept: System Prompt. Why it fits: Use it for steady product behavior that shouldn't change with each user message. Do not use it when: Never put secrets in a prompt or assume written instructions can enforce security by themselves. AI requirements: Define the input and source evidence. Set model and tool permissions. Use versioned evaluation data and measures. Define failure, decline-to-answer, privacy, speed, and cost limits. Operational safeguards: Keep a clear trace and hide sensitive log data. Show users a safe fallback. Mark steps that need human review. Define how to roll back the model or prompt. Acceptance criteria: Record baseline and target measures on a versioned evaluation set. Test edge cases and hostile inputs. Verify fallback, monitoring, permissions, and rollback. Evidence and limits (evidence boundary): No single official standard controls the whole term. Its meaning may change across teams, platforms, or frameworks. Unknowns to confirm: Target task, model and version, evaluation owner, source data, risk limit, tool permissions, and production fallback.
Check this request
Review the current use of System Prompt. Definition: A system prompt is a set of high-priority instructions. It sets an AI product’s role, limits, tools, and rules for replies. Release checks: Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback. Before changing code, report the evidence you found, gaps, severity, and the smallest safe fix.