WGUl D685l Final Exam (Latestl 2026/l
2027l Update)l Practicall Applicationsl ofl
Promptl Engineeringl Review|l 100%l
Verifiedl Questionsl &l Answersl |l Gradel A
Q:l Howl doesl providingl examplesl changel AIl performance?
Answer:
Givingl examplesl helpsl thel AIl understandl exactlyl whatl youl want,l makingl itl lessl
confusedl andl morel consistent.
Q:l Whatl arel thel fourl componentsl ofl al structuredl prompt?
Answer:
Role,l Task,l Context,l andl Constraints.
Q:l Whenl shouldl youl usel iterativel refinement?
Answer:
Whenl thel firstl promptl doesn'tl givel youl exactlyl whatl youl want,l andl youl needl tol tweakl
itl step-by-stepl tol improvel thel output.
Q:l Whatl wasl thel mainl observationl froml usingl zero-shotl prompts?
Answer:
Thel responsesl werel decentl butl feltl tool generic.
Q:l Howl didl thel few-shotl promptl improvel thel responses?
,Answer:
Byl providingl clearerl instructionsl aboutl thel desiredl tone,l makingl itl morel punchy,l
reassuring,l andl results-focused.
Q:l Whatl isl thel benefitl ofl usingl iterativel prompting?
Answer:
Itl allowsl forl back-and-forthl feedbackl tol refinel thel outputl stepl byl step,l leadingl tol al
morel accuratel andl usefull finall result.
Q:l Whatl isl anl examplel ofl al zero-shotl prompt?
Answer:
Al promptl thatl asksl forl messagingl withoutl providingl anyl examplesl orl additionall details.
Q:l Whatl didl thel iterativel refinementl processl helpl achieve?
Answer:
Itl helpedl fine-tunel thel copyl andl madel thel finall resultl morel accurate.
Q:l Whatl wasl thel outcomel ofl usingl few-shotl prompts?
Answer:
Responsesl becamel closerl tol whatl wasl neededl duel tol clearerl guidance.
Q:l Whatl isl thel mainl advantagel ofl structuredl prompts?
Answer:
Theyl helpl clarifyl thel user'sl intent,l leadingl tol morel relevantl AIl responses.
,Q:l Whatl didl thel iterativel methodl allowl thel userl tol do?
Answer:
Itl allowedl thel userl tol fine-tunel everythingl insteadl ofl settlingl forl somethingl closel
enough.
Q:l Whatl wasl thel initiall resultl ofl thel zero-shotl prompt?
Answer:
Itl providedl al decentl answerl butl lackedl specificity.
Q:l Howl canl structuredl promptsl affectl AIl interactions?
Answer:
Theyl makel interactionsl morel reliablel andl alignedl withl userl intent.
Q:l Whatl isl al keyl benefitl ofl thel iterativel refinementl technique?
Answer:
Itl enablesl graduall improvementl ofl responsesl throughl feedback.
Q:l Whatl didl thel userl findl mostl effectivel inl theirl promptingl experience?
Answer:
Thel iterativel methodl workedl bestl forl refiningl thel output.
Q:l Whatl isl thel rolel ofl contextl inl structuredl prompts?
Answer:
Contextl providesl backgroundl informationl thatl thel AIl needsl tol generatel accuratel
responses.
, Q:l Howl dol textl promptsl differl froml imagel prompts?
Answer:
Textl promptsl telll thel AIl whatl tol talkl about,l whilel imagel promptsl telll itl whatl tol show;l
textl canl bel morel general,l butl imagel promptsl needl clearl visuall details.
Q:l Whatl isl hallucinationl inl AI?
Answer:
Hallucinationl isl whenl thel AIl confidentlyl givesl informationl thatl isn'tl real.
Q:l Whatl isl biasl inl AI?
Answer:
Biasl occursl whenl thel AIl leansl unfairlyl towardl al viewpointl orl stereotype.
Q:l Whatl metricsl canl improvel promptl evaluation?
Answer:
Metricsl likel accuracy,l creativity,l andl ethicsl helpl judgel whetherl al promptl isl effectivel
andl allowl forl adjustmentsl tol improvel clarityl andl safety.
Q:l Whatl wasl thel focusl ofl thel comparisonl betweenl ChatGPTl andl CanvaAI?
Answer:
Thel focusl wasl onl structurall differences,l outputl effectiveness,l andl ethicall considerationsl
inl representingl donor-conceivedl childrenl andl LGBTQ+l families.
Q:l Howl didl ChatGPT'sl promptl designl differl froml CanvaAI's?
Answer:
2027l Update)l Practicall Applicationsl ofl
Promptl Engineeringl Review|l 100%l
Verifiedl Questionsl &l Answersl |l Gradel A
Q:l Howl doesl providingl examplesl changel AIl performance?
Answer:
Givingl examplesl helpsl thel AIl understandl exactlyl whatl youl want,l makingl itl lessl
confusedl andl morel consistent.
Q:l Whatl arel thel fourl componentsl ofl al structuredl prompt?
Answer:
Role,l Task,l Context,l andl Constraints.
Q:l Whenl shouldl youl usel iterativel refinement?
Answer:
Whenl thel firstl promptl doesn'tl givel youl exactlyl whatl youl want,l andl youl needl tol tweakl
itl step-by-stepl tol improvel thel output.
Q:l Whatl wasl thel mainl observationl froml usingl zero-shotl prompts?
Answer:
Thel responsesl werel decentl butl feltl tool generic.
Q:l Howl didl thel few-shotl promptl improvel thel responses?
,Answer:
Byl providingl clearerl instructionsl aboutl thel desiredl tone,l makingl itl morel punchy,l
reassuring,l andl results-focused.
Q:l Whatl isl thel benefitl ofl usingl iterativel prompting?
Answer:
Itl allowsl forl back-and-forthl feedbackl tol refinel thel outputl stepl byl step,l leadingl tol al
morel accuratel andl usefull finall result.
Q:l Whatl isl anl examplel ofl al zero-shotl prompt?
Answer:
Al promptl thatl asksl forl messagingl withoutl providingl anyl examplesl orl additionall details.
Q:l Whatl didl thel iterativel refinementl processl helpl achieve?
Answer:
Itl helpedl fine-tunel thel copyl andl madel thel finall resultl morel accurate.
Q:l Whatl wasl thel outcomel ofl usingl few-shotl prompts?
Answer:
Responsesl becamel closerl tol whatl wasl neededl duel tol clearerl guidance.
Q:l Whatl isl thel mainl advantagel ofl structuredl prompts?
Answer:
Theyl helpl clarifyl thel user'sl intent,l leadingl tol morel relevantl AIl responses.
,Q:l Whatl didl thel iterativel methodl allowl thel userl tol do?
Answer:
Itl allowedl thel userl tol fine-tunel everythingl insteadl ofl settlingl forl somethingl closel
enough.
Q:l Whatl wasl thel initiall resultl ofl thel zero-shotl prompt?
Answer:
Itl providedl al decentl answerl butl lackedl specificity.
Q:l Howl canl structuredl promptsl affectl AIl interactions?
Answer:
Theyl makel interactionsl morel reliablel andl alignedl withl userl intent.
Q:l Whatl isl al keyl benefitl ofl thel iterativel refinementl technique?
Answer:
Itl enablesl graduall improvementl ofl responsesl throughl feedback.
Q:l Whatl didl thel userl findl mostl effectivel inl theirl promptingl experience?
Answer:
Thel iterativel methodl workedl bestl forl refiningl thel output.
Q:l Whatl isl thel rolel ofl contextl inl structuredl prompts?
Answer:
Contextl providesl backgroundl informationl thatl thel AIl needsl tol generatel accuratel
responses.
, Q:l Howl dol textl promptsl differl froml imagel prompts?
Answer:
Textl promptsl telll thel AIl whatl tol talkl about,l whilel imagel promptsl telll itl whatl tol show;l
textl canl bel morel general,l butl imagel promptsl needl clearl visuall details.
Q:l Whatl isl hallucinationl inl AI?
Answer:
Hallucinationl isl whenl thel AIl confidentlyl givesl informationl thatl isn'tl real.
Q:l Whatl isl biasl inl AI?
Answer:
Biasl occursl whenl thel AIl leansl unfairlyl towardl al viewpointl orl stereotype.
Q:l Whatl metricsl canl improvel promptl evaluation?
Answer:
Metricsl likel accuracy,l creativity,l andl ethicsl helpl judgel whetherl al promptl isl effectivel
andl allowl forl adjustmentsl tol improvel clarityl andl safety.
Q:l Whatl wasl thel focusl ofl thel comparisonl betweenl ChatGPTl andl CanvaAI?
Answer:
Thel focusl wasl onl structurall differences,l outputl effectiveness,l andl ethicall considerationsl
inl representingl donor-conceivedl childrenl andl LGBTQ+l families.
Q:l Howl didl ChatGPT'sl promptl designl differl froml CanvaAI's?
Answer:
