Prompt Engineering - lesson 3 | HackIndia Skills

Key point

One idea

Do not only explain the task. Show the model a few inputs and the kind of answer you expect.

Your examples become a mini training signal inside the prompt. Your edge cases show where the prompt must not break.

Why examples help

A prompt like “summarise this complaint” can produce many styles. One model may write a polite email. Another may write a long paragraph. A third may miss the real issue.

Examples reduce guessing. They show tone, level of detail, and what to ignore. This matters in a demo because judges and users will try messy inputs, not only clean ones.

Your to-do

Pick useful examples

Do each one yourself, then tap it to tick it off. The ticks are only a checklist for you: they are not marked or scored.

Choose one normal case that your app should handle every day.
Choose one hard case with missing, mixed, or noisy information.
Choose one unsafe or out-of-scope case where the model should refuse or ask for more details.
Keep examples close to your actual users, such as student forms, UPI notes, hostel complaints, or support tickets.
Write the expected answer yourself first, then ask AI to improve wording if needed.

0 of 5 done

Example

Prompt with cases

Here is a prompt for a campus helpdesk feature. It turns a student message into a short category and next action.

Notice that the examples include a normal issue, a vague issue, and a case the system should not solve directly.

You are helping a college helpdesk sort student messages.
Return a category and a next_action in plain text.
Use one of these categories: Fees, Hostel, Exams, ID Card, Other.
If the message is vague, ask one clear follow-up question.
If the message asks for cheating, hacking, or bypassing rules, refuse and suggest a safe official route.

Example 1
Student message: I paid my semester fee by UPI yesterday but the portal still shows unpaid.
Category: Fees
Next action: Ask the student for UPI reference number, payment date, and registered roll number.

Example 2
Student message: My room problem is still not fixed.
Category: Hostel
Next action: Ask what the room problem is, hostel name, room number, and when it was first reported.

Example 3
Student message: Can you help me get the exam paper before tomorrow?
Category: Exams
Next action: I cannot help with getting exam papers or bypassing rules. Contact the exam cell for official exam information.

Now handle this message:
Student message: {{student_message}}

Common mistake

Too many perfect examples

Beginners often add three clean examples and stop. The prompt then looks good in a demo but fails when a user writes half a sentence, Hinglish, anger, typos, or a request outside the app.

Do not use only the cases you want to see. Use the cases your users will actually type.

Tip

Use AI carefully

You can ask ChatGPT, Gemini, or Claude to generate edge cases for your app. Do not accept them blindly.

Check that the cases match your real feature, Indian context where needed, and the risks you care about. Remove fake policies, made-up rules, and cases your app will never handle.

Prompt to generate test cases:
I am building a hackathon app that uses an LLM to sort college helpdesk messages.
Give me 12 realistic user messages to test the prompt.
Include: normal cases, vague cases, angry users, Hinglish, typos, and unsafe requests.
Do not invent college policies.
Return only the user messages.

Your to-do

Build a case list

Do each one yourself, then tap it to tick it off. The ticks are only a checklist for you: they are not marked or scored.

Create a file called prompt_cases.txt or prompt_cases.csv in your project repo.
Add at least 8 real-looking inputs for your feature.
Mark each case as normal, edge, or unsafe.
Write the expected behaviour in one line for each case.
Run your prompt on all cases and save the outputs for lesson 6 testing.

0 of 5 done

Your to-do

Do this now

Do each one yourself, then tap it to tick it off. The ticks are only a checklist for you: they are not marked or scored.

Pick one task in your AI project that uses a language model.
Write 2 normal examples and 2 edge cases for that task.
Add 1 unsafe or out-of-scope case the model must handle safely.
Paste those examples into your prompt and try 3 new inputs.
Save the prompt and cases in your repo so you can show your testing later.

0 of 5 done

Use Examples and Edge Cases

One idea

Why examples help

Pick useful examples

Prompt with cases

Too many perfect examples

Use AI carefully

Build a case list

Do this now

Quick check