方寸 Portal

AI Engineer Portal

Your personal operating system for career transition.

Private mode

Exercise

Render a safe prompt template from user input

Build a template renderer that separates trusted system instructions from untrusted user input and outputs a final prompt payload.

Prompt Formatting / easy / Step 1 of 5

Practice stage

Prompt boundary discipline

Hint

Treat prompt construction like request composition: trusted instructions, untrusted user input, and context blocks should stay separate.

Next drill
Build a structured prompt template with system/user role separation
Success criteria
  • - Separates system, user, and context cleanly
  • - Avoids string chaos and hidden assumptions
  • - Would scale to a real LLM feature
Review checklist
  • - Did I preserve trusted versus untrusted boundaries?
  • - Would this format survive longer prompts and more context?
  • - Can another engineer review the structure quickly?
Related lessons
Prompt, context, tools, and memoryGuardrails and structured outputs

Practice

Generate a variation

Generate a new exercise variation to deepen understanding or practice a related concept.

Attempt history

Recent submissions

Before you submit, decide what a strong answer should make obvious to the reviewer.

No attempts yet.