Prompt Engineering 101: The Patterns That Actually Work

Prompt engineering is not a job title. It’s a skill — the way “Excel formulas” was a skill in 2010. It separates people who use AI from people who operate AI.

This lesson covers the seven prompt patterns that show up in every serious workflow. Memorize the names. Mix them as needed. You don’t need any of the snake-oil “20 secret prompts that will 10x your income” lists — you need these primitives.

1. Role + Context + Task (RCT)

The foundation. Every prompt you write should hit all three.

ROLE: You are a senior B2B SaaS pricing consultant.
CONTEXT: My startup sells dev tools to mid-market companies (50–500 engineers).
ARR is $1.2M, growing 12% MoM. Current price: $49/seat/month.
TASK: Propose three pricing structures we could A/B test next quarter,
with the hypothesis each one is meant to prove.

This pattern alone outperforms 90% of “creative” prompts.

2. Few-shot examples

Show, don’t explain. When you want a specific format, paste two or three perfect examples.

Convert these meeting notes into a Linear ticket.

Example 1:
Notes: "Login button on iOS doesn't work after the last release"
Ticket: { title: "iOS login button non-functional post v2.1", priority: "P0", labels: ["bug","ios"] }

Example 2:
Notes: "Should we add dark mode? Customers keep asking"
Ticket: { title: "Add system-wide dark mode", priority: "P2", labels: ["feature","ui"] }

Now convert:
Notes: "Free trial users not converting; checkout page slow"

The model will match your format exactly.

3. Chain-of-thought (CoT)

For complex reasoning, force the model to think step by step before answering. Two words at the end work magic: “Think step by step.”

For harder problems, add structure:

Walk through your reasoning in this order:
1. What is the actual question being asked?
2. What information do I have / not have?
3. What are the possible interpretations?
4. What's the best answer given the uncertainty?
Then give the final answer.

This single pattern improves math, planning, and analysis tasks by 20–40%.

4. The constraint stack

Don’t say “be concise.” Stack hard constraints:

Output rules:
- Maximum 120 words
- No adjectives stronger than "good"
- No em dashes
- No bullet points
- One concrete number per paragraph

Concrete constraints produce concrete output.

5. The persona attack

Use multiple personas to stress-test an idea.

I'm going to share a business idea. Then critique it three times:
1. As a skeptical VC
2. As a happy customer who just bought it
3. As a competitor planning to crush us
End with the single biggest risk and the single biggest opportunity.

This pattern is worth a $5,000 consultant in 30 seconds.

6. Self-critique loop

Make the model grade its own work, then improve it.

Step 1: Write the first draft.
Step 2: Critique your draft as if you were a hostile editor.
Step 3: Rewrite the draft incorporating the critique.
Only show me step 3.

The output is markedly better than the model’s first attempt.

7. Output contract

Lock the schema. Especially valuable for downstream tooling.

Return ONLY valid JSON matching this schema:
{
  "summary": "string, max 280 chars",
  "key_insight": "string",
  "action_items": [{"owner": "string", "task": "string", "due": "YYYY-MM-DD"}],
  "confidence": 0.0 to 1.0
}
No prose. No markdown fences. Just the object.

How to learn this for real

Read this once. Pick one pattern. Use it three times today. Tomorrow, pick a second pattern. By next week these will be muscle memory.

The deeper lesson: prompts are not magic spells. They’re specifications. The clearer the spec, the better the build. Treat them like you’d treat a Jira ticket for the most junior engineer on your team.