You're reviewing code that builds an LLM prompt by inserting user-supplied text directly into the system instructions, then acts on the model's reply. What risks do you raise?

Question

Answer

Stay specific. One example, told well, beats three told fast. Make your decisions visible — what you chose between. End on what changed, for whom.

You're reviewing code that builds an LLM prompt by inserting user-supplied text directly into the system instructions, then acts on the model's reply. What risks do you raise?

Practice more