L
LLLOS.ai
Career
L
◆ AI Learning · Hard rule

Where should a developer put rules about not sharing private information in an AI prompt?

Proprietary constraints must not be in the main part of a prompt. All strict rules belong in a separate section. This section must be at the end of the prompt. It must clearly state that certain things should never be outputted.

By Pawan Nayar · from the LLOS AI Learning record

The rule

Proprietary constraints must not be in the main part of a prompt.

All strict rules belong in a separate section. This section must be at the end of the prompt. It must clearly state that certain things should never be outputted.

A developer must not put private rules in the main text of an AI prompt. These rules are called proprietary constraints. All very important rules must go in their own section. This section should be at the very end of the prompt. The developer must clearly state that the AI model should never output these specific items.

A developer creates a prompt for an AI model. The prompt asks the AI model to summarize a document. The document contains company secrets. The developer puts a sentence in the middle of the prompt saying, 'Do not mention project X.' The AI model might ignore this rule. It might include project X in its summary. Instead, the developer should put a section at the end. This section should say, 'NEVER MENTION: Project X, Client Y, Budget Z.' This makes the rule clear to the AI model.

Words you'll need

Resolved from this lesson's own record — real definitions, not invented for this page.

Prompt Design

Writing instructions that get the AI to do what you want

System Prompt

The instructions you give the AI before asking questions

Safety Guidelines

Rules built into AI to prevent harmful outputs

Guardrails

Safety rules that keep AI from doing bad things

Questions people ask

More from the same record, pulled by shared topic — not written new for this page.

How can an AI model accurately follow user instructions?

An AI model needs clear and complete instructions. The user must state the desired outcome precisely.

Why did the AI model include its instructions in the answer?

The AI model saw special formatting in the instructions. This formatting made the instructions look like important text.

How should a developer structure a prompt to prevent an AI model from making specific mistakes?

A developer should put absolute constraints at the very end of a prompt. These constraints are golden rules.

Why did an AI model fail to follow many instructions, even if the instructions were good?

A developer gave an AI model many rules for generating text. The rules included specific styles, content bans, and structural requirements.

What to remember

Proprietary constraints must not be in the main part of a prompt. All strict rules belong in a separate section. This section must be at the end of the prompt. It must clearly state that certain things should never be outputted.