Library › Cybersecurity AI › Software developers
Ask the right security questions about a new service
- For Software developers
- You practice Giving the right context
- Time about 5 minutes
About this exercise
You're reviewing a design doc for a new webhook service. Write exactly 4 numbered questions for the author, each naming a specific component from the doc and asking about a trust boundary the doc leaves open. Skip anything the doc already answers. Plain text, under 110 words.
Common mistakes when you ask AI for this
- Generic questions. The AI asks 'Have you considered authentication?' without pointing at a component. Try: Say: "Each question names a component from the doc."
- Asking what's answered. The AI asks about TLS and rate limits, which the doc already settles. Try: Add: "Skip anything in 'What's decided'."
- Missing the open items. Without being pointed at the gaps, the AI spreads questions over everything. Try: Ask: "Focus on the trust boundaries the doc leaves open."
- Questions plus essays. The AI adds a paragraph of explanation under each question. Try: Be exact: "Exactly 4 numbered questions, each under 20 words."
- Letting markdown in. AI adds bold and headings by default, and in the doc comments they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."
What a strong prompt includes
- Asks for specific components
- Targets the open items
- Skips settled items
- Says exactly how many
- Asks for plain text
Related exercises
- Add input validation to a Java method with exact messages (Coding AI · Software developers)
- Add type hints that still run on Python 3.8 (Coding AI · Software developers)
- Announce a discount-approval process change in three bullets (Sales AI · Managers and team leads)
- Announce a hybrid work policy change with clear actions (Writing AI · HR and recruiting)
- Announce a new weekend rotation in three clear rules (Productivity AI · Managers and team leads)