Prompt construction
Iteration, context selection, and prompt comparison
Revise a request based on observed failures and compare outputs against the same task requirements.
Lesson 6 of 6 in the recommended order · About 25 min (estimate)
On this page
Practical AI glossary — terms and common confusions
- Model
- A learned component used to produce a result.
A drafting model is one part of a letter app; it is not the whole app.
- Application
- The software experience around components and services.
A letter app adds accounts, storage, and a Send button.
- Prompt
- Instructions and input supplied for a task.
“Summarize this notice in two bullets” specifies a task and shape, not a truth guarantee.
- Token
- A unit a model processes; it need not be a whole word.
A tokenizer can split a name into pieces; count using the actual system.
- Context
- Information available for the current request.
An earlier attachment may be absent even when its filename is visible.
- Training
- Adjusting a model using examples.
A training log differs from a conversation correction.
- Inference
- Using a trained model to produce a result.
Drafting another sentence does not by itself prove retraining.
- Retrieval
- Selecting material to supply to a task.
A retrieved notice still needs a relevance and date check.
- Embedding
- A numerical representation used to compare or organize items.
A similar search match is a candidate, not proof of the same meaning.
- Tool
- A function an application can call.
A calendar lookup can be read-only; finding an event is different from creating one.
- Agent
- Software that can choose and carry out steps toward a goal.
An agent still needs bounded permissions and checked action receipts.
- Hallucination
- Plausible generated content that is unsupported or false.
An invented opening time needs evidence or removal, even when phrased confidently.
- Evaluation
- Checking results against stated criteria.
Twenty checked examples establish a bounded result, not universal reliability.
- Multimodal
- Working with more than one kind of input or output.
A photo plus text does not prove every small label in the photo was read correctly.
Outcome
Choose a justified prompt revision while preserving current facts, useful constraints, and honest test scope.
Why it matters
Revise a request based on observed failures and compare outputs against the same task requirements.
Concept
Treat iteration as a small experiment. Keep the task and evaluation criteria visible, identify the observed failure, and change the relevant instruction or supplied context. A longer prompt is not automatically better; it can carry obsolete instructions or irrelevant facts.
Compare candidates on the same cases and requirements. Record what changed and what remains untested. One attractive result is evidence about that result, not proof that a prompt is universally superior. When a creative task includes fixed facts, preserve them while varying tone or ideas. When an attachment fails, repair the missing input before comparing whole-document performance.
Worked example
A fictional poster draft omitted an accessibility contact. The next prompt adds that required field and retains the approved date and location. Compare both outputs against the same checklist. If the revised output includes the contact but invents a venue, it has not passed; a partial improvement should not erase a new defect.
Before you check
Create a short comparison record: unchanged task, observed failure, one targeted revision, result against each criterion, and remaining uncertainty. Use the supplied outputs rather than an external account.
Practice and fresh transfer
The packets below are fictional and contain the facts needed for these cases. External references are optional background. Judge each response independently: it may be supported, contradicted, or unresolved. Select the passages needed to justify your judgment and write why the distinction matters before revealing feedback.
Assess the response
Use Accept when all material claims are supported. Use Revise when a supplied fact or requirement is contradicted. Use Evidence is insufficient when a key fact cannot be established either way. If a response contains both an unknown and a direct contradiction, choose Revise and explain both problems. Conflicting claims with no established authority remain insufficient; a claim does not become a governing fact merely because a source asserts it.
Some responses are fully supported. Others need correction or more evidence. Judge each on its sources; do not edit a correct answer just to change it.
Your written notes stay in this page and disappear when you leave. Only a self-reviewed completion can be saved to your learning account. These practice checks do not establish independent proficiency.
Practice
Case 1
Consider a fictional revision plan after an omitted field.
Source packet
- Source 1
- Brief: Poster must contain date, room, and access contact.
- Source 2
- Review: Draft A contains the correct date and room but omits the supplied access contact.
Response to assess
Add an explicit access-contact requirement, retain date and room, then check all three fields again.
Practice
Case 2
Consider a fictional claim about two prompt trials.
Source packet
- Source 1
- Trial record: Prompt A and B were each tried once on one invitation task. B matched that task’s rubric; A omitted a date.
- Source 2
- Scope: No other tasks or repeated trials were evaluated.
Response to assess
Prompt B is proven best for every writing task.
Fresh transfer
Case 3
Consider a fictional creative brief assembled from current and old notes.
Source packet
- Source 1
- Final brief: Use a calm tone and the title “Open Studio.” This replaces the earlier launch title.
- Source 2
- Archived note: Earlier title was “Big Reveal.” It is superseded.
Response to assess
Use the title “Open Studio” and a calm tone; exclude the superseded title from the active brief.
Fresh transfer
Case 4
Consider a fictional comparison after a failed attachment load.
Source packet
- Source 1
- Trial receipt: Prompt A received all five report pages. Prompt B received only the title because extraction failed.
- Source 2
- Evaluation goal: Compare prompts for accurate whole-report summaries.
Response to assess
B’s shorter summary proves it is the better whole-report prompt.
Save your self-review
Completion records that you reviewed the cases. Your explanation and transfer performance need a facilitator to establish independent learning.
Sign in with your learning-center account to save completion.
Review the explanation for every case before saving.
Summary and next step
Apply the checklist to a new task. Preserve supported content, explain any change with evidence, and name what remains unresolved. Saving records self-review, not independently demonstrated proficiency. A facilitator must assess the explanation and fresh transfer for human learning evidence.