Prompt Engineering - lesson 2 | HackIndia Skills

Key point

Context is input

The model cannot read your product, database, college form, or user intent unless you pass the right parts in the prompt.

Good context gives the model the facts it must use, the rules it must follow, and the limits it must not cross.

What to include

Think of context as the minimum packet a smart intern needs to do the task correctly.

For an AI feature, that packet usually has four parts: user goal, relevant data, product rules, and output audience.

Your to-do

Build a context packet

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.

State the user’s current goal in one sentence.
Add only the data needed for this decision or response.
Include app rules that must never be guessed, like pricing, eligibility, refund terms, or safety limits.
Name the audience, such as first-year student, recruiter, shop owner, or support agent.
Mention what the model should ignore if the user asks for something outside the task.

0 of 5 done

Common mistake

Too much context

Beginners paste the full PDF, full chat history, or whole database row. This makes the prompt slower, harder to debug, and easier to confuse.

Do not add context because it feels useful. Add it because the answer would be wrong without it.

Tip

Keep two layers

Use stable context for rules that rarely change. Use task context for the current user case.

This makes testing easier. When a prompt fails, you can see whether the problem is the rule layer or the case data.

Example

Mess menu helper

Suppose your hackathon project helps hostel students choose a meal from a mess menu. The model should not invent items or prices.

Your prompt can pass a small context object instead of the full menu app.

SYSTEM CONTEXT
You help students choose from the hostel mess menu.
Use only the menu items provided in TASK CONTEXT.
Do not invent food items, prices, discounts, or nutrition facts.
If the menu does not contain a suitable option, say so.
Keep the answer under 80 words.

TASK CONTEXT
User goal: Find a vegetarian dinner option under ₹80.
Audience: College student in a hostel.
Date: Tuesday dinner.
Menu items:
- Veg thali, ₹70, vegetarian
- Egg curry rice, ₹85, non-vegetarian
- Paneer roll, ₹95, vegetarian
- Lemon rice, ₹60, vegetarian

USER MESSAGE
I want something filling and veg, but not expensive.

What to check

After the model replies, check whether every claim came from the context. If it mentions a discount, calorie count, or item not listed, your prompt allowed guessing.

Also check whether the model used the user goal. A technically correct answer can still be bad if it ignores budget, date, language, or audience.