The five principles from the last lesson cover most everyday prompting. This lesson covers named, more deliberate techniques used in professional and technical work — the same ones companies use when building AI-powered products, not just chatting casually.
You give the AI a task with no examples, relying entirely on what it already learned during training. This works well for common, familiar tasks:
Classify the following customer reviews as Positive, Negative, or Neutral:
"The product arrived quickly but the packaging was damaged."
"Absolutely love this! Best purchase I've made."
"It's okay, nothing special."Zero-shot fails more often on unusual or highly specific tasks — that's exactly when the next technique helps.
You provide 2–5 example input/output pairs before the real task, showing the model the exact pattern you want:
Translate English to formal Bengali:
English: "Please submit your application by Friday."
Bengali: "অনুগ্রহ করে শুক্রবারের মধ্যে আপনার আবেদন জমা দিন।"
English: "The meeting has been rescheduled to 3 PM."
Bengali: "সভাটি বিকেল ৩টায় পুনর্নির্ধারিত হয়েছে।"
English: "We regret to inform you that your application was unsuccessful."
Bengali:Use few-shot whenever the model keeps giving inconsistent results or the wrong format — showing examples is far more reliable than describing the format in words.
Telling the model to think step by step before answering dramatically improves accuracy on reasoning, maths, and logic:
Without "think step by step" (often wrong):
Q: A train leaves City A at 8 AM going 80 km/h, another leaves City B
at 10 AM going 100 km/h, and the cities are 1,400 km apart. When do
they meet?
A: [model often guesses wrong]
With "think step by step" (much more accurate):
Q: [same question]
Think step by step. Show each calculation.
A: Step 1: By 10 AM, the first train has travelled 80 × 2 = 160 km...
[model proceeds correctly]One Phrase, Consistently Better Answers
Add "think step by step" or "show your working" to any prompt involving reasoning, maths, code debugging, or logical deduction — it consistently and noticeably improves the answer.
A system prompt is an instruction given to the AI before the actual conversation begins, setting its role, personality, and constraints. In a normal chat interface, you can simulate one by putting detailed instructions right at the start of the conversation:
You are an expert full-stack web developer. You write clean, secure,
well-commented code. You always:
1. Follow standard security best practices
2. Validate all user input
3. Use parameterised queries for any database code
4. Explain what each code block does in a short comment
5. Point out security issues in any code I show you
Respond only in code plus a brief explanation. No lengthy introductions.The underlying AI model is identical either way — the system prompt is what turns a generic assistant into a specialised tool. This is exactly how companies build AI-powered products: a customer-service bot, a coding assistant, and a writing coach can all be the same base model with a different system prompt.
Professional workflows often need AI output in a specific format another tool can actually use — not free-flowing prose. Ask for it explicitly:
Extract the following information from this customer complaint email
and return it as valid JSON only, with no other text:
Email: "Dear support, I ordered a blue kurta (order #A12345) on
15 June but received a red one. Please replace it immediately.
My contact is name@email.com."
Return this exact structure:
{
"order_number": "",
"issue_type": "",
"product": "",
"customer_email": "",
"priority": "low/medium/high"
}This turns an AI assistant from a chat tool into a data-processing step that can feed directly into other software — genuinely useful the moment you're combining AI with any other tool or workflow.
Sometimes it's just as important to say what you don't want: "explain this without using any technical jargon," or "list ideas, but don't include anything that requires a budget." Stating a constraint directly is often more reliable than hoping the model infers it.
A Security Topic, Not Just a Prompting Trick
One more advanced topic — prompt injection, where malicious text hidden inside content an AI processes tries to hijack its instructions — is a real security concern for anyone building AI-powered tools, not just a prompting technique. It's covered properly in this section's lesson on AI security.
You now have a genuinely professional prompting toolkit. The next two lessons put all of this to work on one of AI's most visible capabilities: generating images.