🏠 Home
Modules
📘 Module 01 📘 Module 02 📘 Module 03 📘 Module 04 📘 Module 05 📘 Module 06 📘 Module 07 📘 Module 08 📘 Module 09 📘 Module 10 📘 Module 11 📘 Module 12 ❓ FAQ 🚪 Sign Out
Module 01 of 12  ·  Hello Pharma AI Upskilling Program

Foundations of Prompt Engineering

Understand what actually happens when you write a prompt.

📋 Official Content ⏱️ ~25 min read ✏️ Exercise included
📚 5 sections
🏢 Hello Pharma
🎯 5 objectives
⚕️

Hello Pharma AI Upskilling Program

This module is part of Hello Pharma's internal AI capability-building programme, designed to help every team member work with AI professionally and responsibly.

Official Content

🎯 Learning Objectives

  • Understand the difference between a question and a prompt
  • Learn how LLMs predict rather than understand
  • Identify why prompts fail and how to fix them
  • Distinguish casual prompt writing from professional prompt engineering
  • Bust the 5 most common myths about AI prompting

1. What Is a Prompt (Beyond 'a Question')

Most people treat prompts like Google searches — short, keyword-driven, hoping the AI figures it out. That works for trivial tasks and fails for professional work.

❌ How Most People Think

A prompt is just a question. Example: "Explain GMP." — like walking into a factory saying "Tell me about quality." You'll get something, but never what you actually need.

✅ What a Prompt Really Is

A prompt is instructions + context + expectations.

You are a pharmaceutical quality consultant. Explain GMP to a new production supervisor with 2 years of shop-floor experience. Focus on practical implications, not regulations. Limit to 5 bullet points.

What Changed?

  • Assigned a role — pharmaceutical quality consultant
  • Defined the audience — supervisor with shop-floor experience
  • Controlled depth — practical, not regulatory
  • Shaped the output — 5 bullet points maximum

2. How LLMs Think: Tokens, Probability & Context Windows

LLMs are prediction engines, not knowledge databases. When you type "The capital of France is…" your phone predicts "Paris". LLMs work the same way — at massive scale.

⚠️ Critical Mental Model

AI does not know the answer. It predicts the most likely next token given everything you've told it. Clear, precise prompts produce better predictions.

Tokens

  • "validation" — leads in one direction
  • "process validation" — significantly different output path
  • "cleaning validation in injectables" — very specific, very different result

Context Window: Order Matters

❌ Conflicting Order
Write a technical explanation of tablets. Make it simple for school students.
✅ Clear Order
Write a simple explanation of tablets for school students. Avoid technical terminology.

3. Why Prompting Works (and When It Fails)

Imagine telling a colleague: "Prepare a report." vs "Prepare a 1-page summary for the CEO highlighting key risks and recommendations." AI responds identically to this dynamic.

❌ Conflicting Instructions
Write a detailed but short explanation. Make it technical but easy for everyone. Use expert language but avoid complexity.

The AI doesn't know which instruction to prioritise. Result: generic, diluted output that satisfies nothing.

Common Failure Modes

  • Vague task — "Write something about quality"
  • No audience — depth and tone become guesses
  • Conflicting constraints — diluted, compromised output
  • No format specified — unstructured text that's hard to use immediately

4. Prompt Engineering vs Prompt Writing

AspectPrompt WritingPrompt Engineering
ApproachConversational, ad-hocDeliberate, structured
QualityVariable, inconsistentPredictable, repeatable
IterationRandom retriesSystematic refinement
ReusabilityOne-offTemplates & libraries
AnalogyTalkingBriefing
💡 The Shift

Prompt writing is hoping. Prompt engineering is designing. One is a conversation — the other is a specification.

5. Common Myths and Misconceptions

Myth 1: Longer Prompts Are Always Better

❌ Long but bad

3 vague paragraphs with no role, format, or audience.

✅ Short but precise
You are a regulatory auditor. Identify compliance risks. Respond in bullet points.

Myth 2: AI Understands Intent

"Make this strong" — Strong how? Aggressive? Persuasive? Technical? The model will guess. Often wrongly. Never assume the AI knows what you mean.

Myth 3: Fancy Language Improves Output

// ❌ Sounds impressive, works poorly "Elucidate the multifactorial paradigms..." // ✅ Clear and effective "Explain the key factors clearly."

Myth 4: One Perfect Prompt Exists

  • First output → 70% right
  • After one refinement → 85% right
  • After critique loop → 95% usable

Prompting is iteration, not magic.

✏️ Module 01 Exercise

Take any topic from your daily pharma work. Write the worst possible one-sentence prompt. Then rebuild it by adding: (1) a role, (2) a defined audience, (3) depth constraints, and (4) an output format. Compare both outputs side by side.

🔑 Key Takeaways

  • AI predicts — it does not understand
  • The clearer your instructions, the better the prediction
  • A prompt is a brief, not a question
  • Conflicting instructions produce diluted output
  • Prompting is iteration — expect to refine
  • Better models reward better prompts exponentially more