Verify the evidence
Questions, scope, and search plans
Turn a broad request into answerable questions and identify the evidence each answer would need.
Lesson 1 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
Why it matters
Turn a broad request into answerable questions and identify the evidence each answer would need.
Concept
Begin with the decision the research should inform. Separate factual questions from preferences and define the relevant place, period, and population. “Which workshop is best?” is incomplete until best has criteria. A search plan should say which evidence could answer each question and where uncertainty may remain.
Use a small source ledger: question, source identifier, relevant passage, date or version, and limitation. Search results are leads to inspect. Several pages repeating the same announcement may be one underlying source. The Cedar workshop scenario continues through later document, data, and capstone lessons; each packet states its own facts so it can also stand alone.
Worked example
Cedar is choosing a workshop time. “Prove evenings are best” presupposes the answer. A better question is “Among the 24 invited volunteers, what preferences were recorded, how many replied, and what venue times are available?” A preference survey and venue schedule answer different parts. Neither alone proves the best choice.
Cedar continuity note: these lessons use separate snapshots—room selection, booking pending, booking confirmed, and later attendance review. Survey responses are preferences, not attendance. Each supplied packet identifies the facts for its own task; do not import a later snapshot into an earlier decision.
Before you check
Draft a three-row research plan with Question, Evidence needed, and Limitation. Include one question the supplied packet cannot answer. Do not browse or collect real participant information.
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 the proposed response for this fictional Cedar work task. Use the supplied packet and stated requirements.
Source packet
- Source 1
- Brief: Choose between morning and evening using volunteer preferences and venue availability.
- Source 2
- Available packets: A preference survey and a venue schedule; neither has yet been analyzed.
Response to assess
Check preference counts in the survey and available times in the venue schedule before recommending a session.
Practice
Case 2
Consider the proposed response for this fictional Cedar work task. Use the supplied packet and stated requirements.
Source packet
- Source 1
- Brief: Compare two orientation formats using stated access needs and costs; no format has been selected.
- Source 2
- Question draft: The researcher prefers video sessions.
Response to assess
Research only evidence proving that video is the best format.
Fresh transfer
Case 3
Consider a fictional claim about the number of independent sources.
Source packet
- Source 1
- Provenance record: Pages A, B, and C reproduce the same organizer announcement verbatim.
- Source 2
- Announcement: It describes a planned event, not observed attendance.
Response to assess
The three pages provide three independent measurements of attendance.
Fresh transfer
Case 4
Consider a fictional scope note for a neighborhood survey.
Source packet
- Source 1
- Survey brief: Ask the 40 invited residents about the Saturday session this month.
- Source 2
- Limit: Visitors and residents who were not invited are outside this survey.
Response to assess
The survey concerns this month’s Saturday session among invited residents; it does not represent all possible visitors.
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.