Choose the Right Prompt Pattern

Choose the Right Prompt Pattern

AI & Prompt Engineering for Everyone Β· double-click any text to add a note Β· hover dotted terms for definitions
Tutorial 3 of 17 Absolute Beginner No-code

1 Course position and tonight’s promise

Learner and guide discuss pick patterns from evidence, not fashion..
Pick patterns from evidence, not fashion.

Day 3 completes Module 1. Tonight you will diagnose ten fictional failed requests, select the prompt pattern that fixes each one, verify the revised request, and save a named Pattern Selector Card for your challenge portfolio.

Promise: you will choose a pattern because it addresses a visible failure—not because it sounds advanced.

2 What you will learn and why it matters

Learner and guide discuss a pattern guides work; verification decides trust..
A pattern guides work; verification decides trust.
  • Distinguish zero-shot, few-shot, persona, grounded, chained, self-critique, and multimodal prompts.
  • Ask for short, verifiable working instead of hidden reasoning.
  • Select a pattern for a visible failure symptom.
  • Keep inputs safe and compare claims with sources and requested format.
  • Complete the Module 1 assessment with direct remediation links.

A prompt pattern is a reusable structure. It can improve clarity and consistency, but it cannot make a model truthful or make unsafe data safe.

3 A familiar situation: diagnose before you choose

Learner and guide discuss diagnose the symptom before selecting a pattern..
Diagnose the symptom before selecting a pattern.

Fictional sample values: Ravi has ten failed requests for a community notice, homework planner, club poster, and photo caption. Each failure has a different symptom. Predict the pattern before revealing it; do not use real names, student records, or client files.

Failure symptom Predict the missing pattern
The notice ignores the supplied meeting date. Grounded prompt
The planner layout changes each time. Format and negative constraints
The poster tone is too formal for children. Persona prompt
The photo caption guesses who is shown. Multimodal prompt with a no-inference boundary
Prediction question: is the failure about missing examples, role, evidence, output shape, stages, review, or image/file context?

4 Simple explanation, then accurate vocabulary

Learner and guide discuss use the right structure for the observed gap..
Use the right structure for the observed gap.

A prompt pattern is a repeatable request structure for a particular task. Zero-shot gives instructions without examples; few-shot adds a small set of labelled examples. A persona prompt names a useful role and audience. A grounded prompt limits the response to supplied, inspectable material.

Term Plain meaning Accurate meaning
zero-shot Ask without showing an example. An instruction completed from the current request without in-prompt demonstrations.
few-shot Show a few examples first. An instruction accompanied by example input/output pairs to demonstrate a desired mapping or format.
persona prompt Ask from a stated helpful role. A framing instruction that sets perspective, audience, tone, or priorities; it does not create real credentials.
grounded prompt Ask from provided evidence. A request constrained to supplied source material, with unsupported gaps marked or declined.
Patterns are instructions, not guarantees. Verify facts, links, extracted text, calculations, and answer keys independently.

5 Zero-shot and few-shot prompting

Learner and guide discuss examples teach shape, not truth..
Examples teach shape, not truth.

Use zero-shot when the task is simple and the format is clear: “Turn these three approved facts into two bullets.” Use few-shot when a short, safe example shows a style or classification rule that words alone leave ambiguous. Examples must be accurate, labelled, and small enough to inspect.

Failure Pattern Before → after
Labels vary Few-shot “Classify requests” → show two fictional labelled examples, then ask for the third.
Simple rewrite Zero-shot “Rewrite this approved sentence in plain English, 20 words maximum.”
Example contains a mistake Do not copy it Correct the example or use explicit rules and source checks.

6 Persona prompts

Learner and guide discuss a role frames tone; evidence frames truth..
A role frames tone; evidence frames truth.

A persona prompt gives a practical viewpoint, not a fictional identity to impersonate. Say “Act as a clear communications editor for volunteer families,” then give the audience, task, approved facts, format, and limits. Never claim professional qualification or use it as medical, legal, or financial advice.

Persona pattern with boundaries
Role: Act as a [HELPFUL ROLE] for [AUDIENCE].
Task: Create [ARTIFACT] from the approved facts below.
Context: [SAFE FACTS / SOURCE NOTES].
Format: [STRUCTURE AND LENGTH].
Constraints: Do not invent credentials, facts, or advice.
Verification: Mark claims I must check.

7 Step-by-step and verifiable working

Learner and guide discuss ask for checkable evidence, not private reasoning..
Ask for checkable evidence, not private reasoning.

Do not request private reasoning or hidden chain-of-thought. Instead, ask for concise, verifiable working: a short plan, visible assumptions, calculations you can reproduce, source quotes or links you can inspect, and a checklist of claims to confirm.

Unsafe or unhelpful request Better request
Show every hidden thought. Give a short numbered plan, stated assumptions, and sources or calculations I can check.
Solve it somehow. List the supplied facts used, show the formula, and flag missing information.
If evidence is missing, stop and find a source or do a manual check; repeated blind retries do not create evidence.

8 Grounded prompts

Learner and guide discuss grounding exposes missing evidence..
Grounding exposes missing evidence.

A grounded prompt clearly separates source material from the requested output. It says what may be used, what to do when the source is silent, and how to mark uncertainty. It is useful for a community notice where date, venue, and contact method must come from supplied approved notes.

Grounded notice pattern
Use only the approved fictional source notes below.
Create a 70-word notice for [AUDIENCE].
Include date, venue, and contact only when present in the notes.
If a required detail is absent, write [NEEDS CONFIRMATION].
Return a claim-to-source checklist for human review.

9 Format and negative constraints

Learner and guide discuss specify both the desired shape and safe exclusions..
Specify both the desired shape and safe exclusions.

Format makes the output testable: headings, fields, length, table columns, or file type. Negative constraints state exclusions: do not invent achievements, do not name people in a photo, do not give advice, and do not use private data. Explain the permitted alternative when a constraint blocks an action.

Symptom Constraint or format fix
Unusable wall of text Return three labelled bullets, 18 words each.
Invented award Use supplied facts only; mark gaps [NEEDS CONFIRMATION].
Sensitive upload request Use fictional sample data; do not upload private records.
Caption guesses identity Describe visible objects only; do not identify people.

10 Prompt chaining

Learner and guide discuss small checked stages prevent error spread..
Small checked stages prevent error spread.

Prompt chaining breaks a complex job into small, reviewable stages. For a club notice: extract approved facts → draft headings → write the notice → check claims → export. Review each stage before passing its output onward, or an early mistake can spread.

Stage Human checkpoint
1. Extract facts Compare every date, name, and number with source notes.
2. Select pattern Choose grounded, persona, or format support from the symptom.
3. Draft Check audience, tone, headings, and length.
4. Verify Mark unsupported claims or privacy issues blocked.
5. Save Export the named prompt, result, and reflection.
Blocked state: if a stage contains sensitive data or an unsupported claim, return to that stage. Do not continue the chain.

11 Self-critique

Learner and guide discuss self-review finds gaps; humans verify facts..
Self-review finds gaps; humans verify facts.

Self-critique asks the tool to compare its draft with a supplied checklist. It can reveal missing headings or an over-length response, but it is not independent verification. You still compare factual claims with sources and make the final decision.

Self-critique pattern
Check this draft against the checklist: [AUDIENCE, FORMAT, LENGTH, APPROVED FACTS, CONSTRAINTS].
Return a two-column table: issue found / exact revision needed.
Do not claim a fact is verified unless it appears in the supplied source notes.
Then wait for my approval before rewriting.

12 Multimodal prompts

Learner and guide discuss more input types require clearer boundaries..
More input types require clearer boundaries.

A multimodal prompt combines more than one input type, such as text and an image. Give the image’s purpose, your task, and limits on inference. For the fictional poster photo, ask for a caption describing visible objects only; do not infer identities, locations, health, or private facts.

Input Safe request Human check
Fictional poster image + text Describe visible colours and objects in one caption; do not identify people. Compare caption with the image.
Permitted document excerpt + text Extract stated date and venue only; quote the lines used. Compare extracted fields with original.
Sensitive school record Do not upload. Use invented sample rows. Keep private data outside the tool.

13 Interactive process model: select, test, verify

Learner and guide discuss choose from the failure, then prove the fix..
Choose from the failure, then prove the fix.

The failure card is the learner’s fictional request; the selector is the pattern decision; the improved-prompt card is the actual instruction; the response card is the tool operation; the gate is human safety, source, and format review; the last card is the saved Pattern Selector Card. This simplified picture does not expose hidden provider instructions or private reasoning.

🎬 Failure symptom to verified pattern
Predict the right pattern before each step. Try a choice to compare outcomes. Under reduced motion, states update without travel. Sensitive data or unsupported claims become Blocked and return to the exact correction stage.
Failure symptom Not started → working
➜
Pattern selector zero/few-shot, grounded, chain…
➜
Improved prompt needs review
➜
Verification gate safety + source + format
➜
Pattern Selector Card verified → ready
Static before Static after
Write a notice about our meeting. Use only these approved fictional notes. Draft a 70-word notice for volunteers. If date or venue is absent, write [NEEDS CONFIRMATION]. Return a claim-to-source checklist.

14 Facilitator-led live demonstration: one pattern mismatch

Learner and guide discuss match the pattern to the failure, not its appearance..
Match the pattern to the failure, not its appearance.

Start with the fictional notice that invents a meeting date. Intentionally choose few-shot because examples feel helpful. Show why that is a mismatch: examples can demonstrate layout, but they cannot supply an absent date. Diagnose the visible evidence gap and switch to the grounded pattern.

  • Use New chat or the current equivalent with fictional source notes.
  • Run the mismatched few-shot request and identify the unsupported date.
  • Replace it with the grounded notice pattern and [NEEDS CONFIRMATION].
  • Compare every visible claim, heading, and word count against the notes.
  • Save the before/after and state why the selected pattern changed.

15 Your Pattern Selector Card: ten failed requests

Learner and guide discuss keep the diagnosis with the prompt..
Keep the diagnosis with the prompt.
Fictional failure Best first pattern
No example of desired classification Few-shot
Simple approved rewrite Zero-shot
Wrong tone for audience Persona prompt
Missing source support Grounded prompt
Layout varies Format and negative constraints
Complex task loses details Prompt chaining
Draft misses its checklist Self-critique plus human verification
Image caption guesses identity Multimodal with no-inference constraint
Private file is requested Block; use safe sample/no-upload route
Fluent claim has no evidence Grounded prompt and manual source check

Save this as “Day 3 — Pattern Selector Card.” For each of your ten rows, keep the symptom, selected pattern, revised prompt, verification evidence, and one-line reflection.

16 Learner lab: build your own safe pattern selector

Learner and guide discuss diagnose, select, verify, revise, save..
Diagnose, select, verify, revise, save.
  1. Prepare ten fictional failed requests or use the provided Pattern Selector Card.
  2. Predict the failure category before looking up a pattern.
  3. Run one safe first attempt with approved facts only.
  4. Select and apply a pattern; state audience, output, limits, and verification.
  5. Check facts, links, extracted data, and requested format manually.
  6. Revise one mismatch, export/save, reopen, and add a one-line reflection.
Checkpoint Evidence to show
Safe inputs Fictional, redacted, or minimum approved context.
Pattern decision Symptom and selected pattern are named.
Clear request Audience, output, limits, and review are stated.
Verification Claims checked against a source or manual method.
Revision Before/after and visible reason.
Saved artifact Named selector card reopens correctly.
Tool-neutral path: use any permitted text or image-capable tool. Interfaces change; look for current controls such as New chat, Attach, or Export. No-upload path: diagnose the fictional cases on paper.

17 Behind the scenes, limitations, safety, and verification

Learner and guide discuss patterns improve direction, not safety or truth by themselves..
Patterns improve direction, not safety or truth by themselves.
  • A pattern is an instruction structure, not a model capability guarantee.
  • Few-shot examples can introduce bias or mistakes; verify them before reuse.
  • A persona does not create qualifications, current knowledge, or authority.
  • Grounding is only as complete and accurate as the supplied source.
  • Self-critique is generated review, not independent fact-checking.
  • Images and files may carry personal, confidential, or misleading information.
Never upload Aadhaar/PAN, banking credentials, passwords, medical records, employer-confidential material, or unnecessary personal data. AI explanations are not legal, medical, or financial advice. Check current provider limits, watermarks, retention, and commercial rights in official terms.

18 Common confusion, errors, troubleshooting, and best practices

Learner and guide discuss troubleshoot the missing structure or evidence..
Troubleshoot the missing structure or evidence.
Symptom Likely cause Safe fix
Fluent draft is wrong Pattern mistaken for evidence Stop and compare each claim with an authoritative source.
Few-shot output copies a bad example Example was inaccurate or over-weighted Correct/remove the example; use an explicit rule and source check.
Tone is wrong Persona/audience is absent Name the audience, role, tone, and format.
Result has invented details No grounding or negative constraint Use approved source notes only; mark gaps.
Complex task drifts One oversized prompt Split into chained stages with checkpoints.
Private content is requested Unsafe file/image context Block it; use fictional or redacted sample data.
Tool feature is limited/watermarked Plan or rights limit Check official terms; choose a permitted alternative.
Work disappears No export Save a named artifact and reopen it.
  • Best practice: choose the smallest pattern that solves the visible problem.
  • Best practice: keep source notes and draft language separate.
  • Trainer tip: ask “What evidence proves this pattern fixed the stated symptom?”

19 Takeaways

Learner and guide discuss select, check, revise, and save..
Select, check, revise, and save.
  • Choose a prompt pattern from the visible failure symptom.
  • Zero-shot and few-shot solve different clarity needs; examples must be accurate.
  • Persona, format, grounding, chaining, self-critique, and multimodal inputs each need limits and human review.
  • Never use a pattern as proof; verify facts and protect sensitive data.
  • Keep the ten-case Pattern Selector Card, revised prompts, evidence checklist, and reflection.

Module 1 is complete when you can explain why a pattern fit a failure, what evidence you checked, and what you revised.

20 What comes next

Learner and guide discuss carry the pattern choice into a real artifact..
Carry the pattern choice into a real artifact.

Next is Topic 04—Design Invitations, Greetings, and Restored Photos. You will use the Pattern Selector Card to choose safe, respectful prompts for a real creative artifact while checking permissions, watermarking, and commercial rights in current official terms.

  • Reopen your Pattern Selector Card.
  • Keep fictional source notes ready for practice.
  • Write one safe creative task and the pattern you predict it needs.

19 Knowledge check—submit before feedback

Pick an answer for each question, then press Check answer. (Notes are disabled in this tab.)

1. When is few-shot prompting most useful?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Few-shot examples can demonstrate a desired pattern, but they must be safe and accurate. Review #zero-shot-and-few-shot-prompting.

2. A notice invents a meeting date. Which pattern addresses the core failure?

βœ… Correct!
❌ Not quite β€” the correct answer is .
The failure is missing evidence. A grounded prompt exposes absent details and requires source checking. Review #grounded-prompts.

3. What should replace a request for hidden reasoning?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Ask for visible, verifiable evidence rather than private reasoning. Review #step-by-step-and-verifiable-working.

4. What is safest for a photo caption with unknown people?

βœ… Correct!
❌ Not quite β€” the correct answer is .
A multimodal prompt needs a clear no-inference boundary; visual input is not proof of identity or private facts. Review #multimodal-prompts.

5. A long task keeps losing details. What is the best first adjustment?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Small checked stages prevent an early error spreading. Review #prompt-chaining.

20 Exercises—attempt before reveal

Try answering each question yourself before expanding the model answer.

1. Modify: Change audience or one negative constraint in a selected pattern. Record what changed. Reveal after attempting.
A strong answer identifies a visible change in tone, vocabulary, format, or excluded content while retaining approved facts and a verification step.
2. Extend: Add a source checklist or second safe input to one pattern. Reveal after attempting.
A strong checklist covers privacy, output format, each factual claim, source/links/calculations, and a saved/reopened result.
3. Apply: Use the selector on one real, non-sensitive task. Reveal after attempting.
A strong response names the symptom, pattern, audience, approved context, format, limits, source check, revision, and saved artifact.
4. Optional challenge: Teach the selector to someone and capture their question—not personal data. Reveal after attempting.
Record a general question, a concise evidence-based response, and the exact pattern or verification stage it concerns.

21 Quick-review cards

Click a card to reveal the back.

Zero-shot
A request with no in-prompt example; use it for a clear simple task.
Few-shot
A request with a few accurate examples that demonstrate a mapping or format.
Grounded prompt
A request limited to supplied inspectable material, with unsupported gaps marked.
Prompt chaining
A complex task split into small reviewed stages.
Self-critique
A generated checklist-based review that still needs independent human verification.

22 Facilitator and interview Q&A

1. Explain prompt patterns simply.
They are reusable request shapes. Pick one because it fixes a visible problem, then check the result with evidence.
2. Demonstrate the ten-case workflow.
Show the fictional failure, name its symptom, select the smallest suitable pattern, build the revised prompt, compare output to source and format, revise, and reopen the saved selector.
3. Diagnose a weak grounded result.
Check whether the source was incomplete, the boundary was unclear, or claims were not compared manually; mark missing details instead of inventing them.
4. Identify a privacy and accuracy risk.
A confidential membership file is a privacy risk; an invented meeting date is an accuracy risk. Block the upload and the claim at their exact stages.
5. Adapt a pattern for another audience.
Keep approved facts and safety boundaries, then change the persona, tone, vocabulary, format, and verification needs; show before/after evidence.

23 Glossary

zero-shot
Simple: ask without showing an example. Technical: instruction completion without in-prompt demonstrations. Page: /Tutorials/ai-for-everyone-03-choose-the-right-prompt-pattern
few-shot
Simple: show a few examples first. Technical: instruction with example input/output pairs demonstrating a desired mapping or format. Page: /Tutorials/ai-for-everyone-03-choose-the-right-prompt-pattern
persona prompt
Simple: ask from a stated helpful role. Technical: framing instruction that sets perspective, audience, tone, or priorities without creating credentials. Page: /Tutorials/ai-for-everyone-03-choose-the-right-prompt-pattern
grounded prompt
Simple: ask from supplied evidence. Technical: response constrained to inspectable source material, with unsupported gaps marked or declined. Page: /Tutorials/ai-for-everyone-03-choose-the-right-prompt-pattern
prompt chaining
Simple: split work into checked steps. Technical: sequential prompts whose intermediate outputs are reviewed before the next stage. Page: /Tutorials/ai-for-everyone-03-choose-the-right-prompt-pattern
self-critique
Simple: ask for a checklist review. Technical: generated comparison of output against criteria; it is not independent verification. Page: /Tutorials/ai-for-everyone-03-choose-the-right-prompt-pattern
multimodal
Simple: use more than one input type. Technical: a request combining modalities such as text, image, audio, or document content. Page: /Tutorials/ai-for-everyone-03-choose-the-right-prompt-pattern

24 Module 1 assessment—Safe AI Foundations

Pick an answer for each question, then press Check answer. (Notes are disabled in this tab.)

1. When is few-shot prompting most useful?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Few-shot examples can demonstrate a desired pattern, but they must be safe and accurate. Review #zero-shot-and-few-shot-prompting.

2. A notice invents a meeting date. Which pattern addresses the core failure?

βœ… Correct!
❌ Not quite β€” the correct answer is .
The failure is missing evidence. A grounded prompt exposes absent details and requires source checking. Review #grounded-prompts.

3. What should replace a request for hidden reasoning?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Ask for visible, verifiable evidence rather than private reasoning. Review #step-by-step-and-verifiable-working.

4. What is safest for a photo caption with unknown people?

βœ… Correct!
❌ Not quite β€” the correct answer is .
A multimodal prompt needs a clear no-inference boundary; visual input is not proof of identity or private facts. Review #multimodal-prompts.

5. A long task keeps losing details. What is the best first adjustment?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Small checked stages prevent an early error spreading. Review #prompt-chaining.

6. Which pattern uses a stated helpful viewpoint but does not make the tool qualified?

βœ… Correct!
❌ Not quite β€” the correct answer is .
A persona frames response style and priorities; it does not create credentials. Review #persona-prompts.

7. What should a grounded prompt do when a required source detail is missing?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Missing evidence must remain visible. Review #grounded-prompts.

8. What is a good negative constraint for image captioning?

βœ… Correct!
❌ Not quite β€” the correct answer is .
A clear exclusion prevents unsupported sensitive inferences. Review #format-and-negative-constraints.

9. What is the review point in prompt chaining?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Human checkpoints prevent errors spreading through the chain. Review #prompt-chaining.

10. What can self-critique help identify?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Self-critique can compare a draft with provided criteria, but facts still need independent checks. Review #self-critique.

11. What is the safest response to a watermark or export limitation?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Respect visible limits and current official terms. Review #best-practices.

12. What proves a Pattern Selector Card is ready?

βœ… Correct!
❌ Not quite β€” the correct answer is .
Completion needs observable safety, pattern, verification, revision, and saved-work evidence. Review #learner-lab.

πŸ—’ My Notes