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 paragraphConcrete 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.
Expanded operator notes for this AI workflow
The useful question is not whether the product has more features than the alternative. It is whether the product makes a repeated decision easier to make correctly. Start by writing the decision in plain language: who needs to act, what evidence they need, what can go wrong, and what a satisfactory result looks like. This short statement becomes the boundary for the workflow. It also gives you a way to stop adding features that do not improve the outcome.
A realistic baseline
Record the current process for ten representative cases. For each case, capture the starting signal, the time until a person begins work, the time spent, the number of corrections, and the final business result. Do not use only the fastest case or the most difficult case. A median and a range reveal whether the process is consistently slow or merely unpredictable. Both problems can be addressed, but they need different fixes.
Suppose a team handles 240 cases each month. Each case takes 18 minutes, and the loaded hourly cost is $42. The direct monthly labor estimate is 240 × 18 ÷ 60 × $42, or $3,024. If a tool costs $180 and saves 30% of the time while adding 90 minutes of review each week, the first estimate is about $725 of gross monthly capacity before quality effects. That is a hypothesis, not a promise. Confirm it by measuring real cases for at least two cycles.
The baseline should include quality. Count duplicate records, incorrect classifications, missed follow-ups, reversals, and customer complaints. A process that becomes faster but creates one expensive mistake can have negative value. When the cost of a mistake is unknown, use a conservative range and make the uncertainty visible to the person approving the project.
Design the handoff
Every handoff needs a sender, a receiver, a timestamp, and a definition of done. If the receiver cannot tell whether the item is ready, the workflow will create messages rather than progress. Add a short status vocabulary and use it everywhere: waiting for input, ready for review, approved, blocked, and complete are usually enough for a first version.
Keep the original input beside the transformed output. This is especially important when a system summarizes, classifies, enriches, or rewrites information. A reviewer should be able to compare the result with the source without searching through several applications. The comparison may add seconds to a routine case, but it makes errors easier to correct and training easier to improve.
Define an escalation threshold. For example, routine items can pass when all required fields are present and the confidence check is above the agreed level. Items with a missing field, an unusual value, or a sensitive attribute go to a named owner. The threshold should be written down rather than left as intuition, because written rules can be reviewed and improved.
Worked example with exceptions
Imagine that a team receives 60 requests each week. Forty-five are routine, ten need one clarification, and five involve a decision that must remain with a manager. A sensible first workflow handles the 45 routine requests, creates a clarification queue for the ten, and leaves the five manager cases untouched except for a reminder. It does not pretend that every request has the same risk.
After four weeks, the team should compare the three groups. If routine requests are completed 40% faster with no quality loss, keep that rule. If the clarification queue keeps growing, improve the intake form rather than adding more reminders. If managers receive too many false escalations, adjust the threshold with examples from real cases. This approach treats exceptions as information about the process, not as evidence that the users failed.
Write down one example of a correct automatic result, one example that needs review, and one example that must stop. These examples are more useful in training than a long list of abstract rules. Review them whenever the audience, product, policy, or data source changes.
Security and continuity
Apply the smallest useful permission set. A reporting workflow rarely needs the ability to delete customer records, and a reminder workflow rarely needs full access to every project. Separate read, write, and administrative permissions where the product allows it. Review access when a person changes role and at least once per quarter for a critical system.
List the data that leaves the primary system. Include copied fields, generated text, attachments, identifiers, and logs. Remove fields that are not needed. If a vendor retention policy is unclear, do not use sensitive production data during the pilot. A clean test dataset makes the experiment slower at first but reduces the cost of an unexpected disclosure.
Prepare a manual fallback that can run for one working day. It should name the queue, the owner, the temporary form, and the reconciliation step used when the system returns. Test it at a quiet time. Recovery plans that exist only in a document are often missing a permission, an export, or a person who knows how to run them.
Review the economics after launch
At day 30, compare actual usage with the adoption assumption. At day 60, compare cycle time and correction rate with the baseline. At day 90, compare the business measure and the full cost, including review and maintenance. Keep a note about what changed outside the workflow, such as seasonality, staffing, or a new offer. That context prevents the team from assigning every movement to the tool.
Use a stop rule. If the workflow has low adoption, no measurable quality improvement, or more maintenance than the team can support, pause it and investigate. Removing a weak workflow protects attention for a stronger one. A successful operating model contains both launches and retirements.
Finally, share the result with the people who do the work. Show the baseline, the current measure, the remaining exceptions, and the next decision. People adopt systems they can understand. A short, honest review builds more trust than a celebration based only on the number of tasks processed.
Expanded FAQ
What is the best first metric? Start with the delay or effort that motivated the project, then pair it with quality. Cycle time alone can reward rushed work; quality alone can hide a process that nobody can sustain. A paired metric shows the trade-off.
Should every exception be automated later? No. Some exceptions are valuable precisely because they receive attention. Automate a case only after you understand why it is exceptional, how often it occurs, and what the consequence of a wrong decision would be.
How much documentation is enough? Enough for a trained colleague to explain the trigger, input, output, owner, failure path, and rollback without the original builder. A one-page procedure plus a short decision log is often sufficient for a small workflow.
What if the team cannot agree on the baseline? Stop and resolve the measurement definition before buying more software. Different definitions of “complete” or “qualified” will create apparent disagreement that no dashboard can fix.
When should the workflow be reviewed? Review weekly during the pilot, monthly for the first quarter, and quarterly after it is stable. Trigger an extra review after a major data-source, policy, staffing, or audience change.
How should a leader communicate the change? Explain the problem, the boundary, the human role, the expected benefit, and the way to report an error. Avoid claiming that the system is perfect. People are more willing to use a tool that has an honest correction path.
This expansion is designed to be used with the main guide above. Apply the same discipline to the next workflow: define the decision, measure the baseline, keep the exception path visible, and review the business result before expanding scope.