حواجز الحماية المعمارية

في هذا الدرس

place guardrails in the architecture so they hold even when the prompt is bypassed.

الموضوعات المخطط لها

• Prompt injection: untrusted text (a customer message, a web page, a document) tries to steer the model. Treat all model input as untrusted and output as untrusted.
• Data leakage: limit what the model can see by access-controlled retrieval using the end user's permissions, plus output filters.
• Excessive agency: give the assistant the minimum tools, read-only by default, with confirmation or human approval for actions like refunds.
• Put controls in code and infrastructure: input and output filtering, schema validation of tool calls, allowlists, rate limits, and scoped credentials. Prompts alone are not a control.
• Layer them: no single guardrail is relied on.