Use lessons 01–04 or equivalent skills before this exercise. You can revisit them from the lesson list.
A spreadsheet or calculator; optional local Python. Text-only AI can explain a plan but cannot establish that calculations ran.
Start with the idea
Show when uncertain assumptions could change the decision.
Calculate a range instead of choosing only the optimistic estimate. State which inputs are assumptions. If the range crosses from benefit to extra work, identify what to measure next.
Sensitivity analysis: Checking how the result changes when an assumption changes.
See the example and check your understanding
A made-up teaching example
Twenty weekly requests at eight minutes each give a 160-minute baseline. Assumed assisted effort of five to nine minutes gives 100 to 180 minutes. That spans saving sixty minutes to adding twenty.
Ask yourself
Does this planning range prove that time will be saved?
Show the explanation
No. Measure actual checking and correction effort. An assumption range is not a measured statistical confidence interval.
Start with these checks
- State assumed inputs.
- Show both favorable and unfavorable cases.
- Name the next measurement needed.
Use the different practice case below and check every requirement in its full instructions.
Full learning objectives
- Separate observations from assumptions.
- Calculate conditional scenarios.
- Avoid unsupported forecasts or precision.
Captions appear here during playback.
Communicate uncertainty and decision sensitivity
Show when uncertain assumptions could change the decision.
Video playback is unavailable. Read the descriptive transcript below, go directly to practice, or open the video file.
Source-based teaching example · Fictional data · Reviewed 2026-10-03. Microsoft Mark · locally synthesized. On a small screen, use fullscreen for diagram details or read the transcript.
Read the descriptive transcript
0:00 · What you will learn
Show when uncertain assumptions could change the decision.
What appears on screen
Show when uncertain assumptions could change the decision.
0:05 · The idea
Calculate a range instead of choosing only the optimistic estimate. State which inputs are assumptions. If the range crosses from benefit to extra work, identify what to measure next.
What appears on screen
Calculate a range instead of choosing only the optimistic estimate. State which inputs are assumptions. If the range crosses from benefit to extra work, identify what to measure next.
0:21 · One useful term
Sensitivity analysis. Checking how the result changes when an assumption changes.
What appears on screen
Checking how the result changes when an assumption changes.
0:29 · A worked example
Twenty weekly requests at eight minutes each give a 160-minute baseline. Assumed assisted effort of five to nine minutes gives 100 to 180 minutes. That spans saving sixty minutes to adding twenty.
What appears on screen
Twenty weekly requests at eight minutes each give a 160-minute baseline. Assumed assisted effort of five to nine minutes gives 100 to 180 minutes. That spans saving sixty minutes to adding twenty.
0:47 · Your turn to think
Does this planning range prove that time will be saved? Pause and decide before continuing.
What appears on screen
Does this planning range prove that time will be saved? Pause the video if you need more time.
1:03 · Why this answer works
No. Measure actual checking and correction effort. An assumption range is not a measured statistical confidence interval.
What appears on screen
No. Measure actual checking and correction effort. An assumption range is not a measured statistical confidence interval.
1:14 · Check 1
State assumed inputs.
What appears on screen
State assumed inputs.
1:19 · Check 2
Show both favorable and unfavorable cases.
What appears on screen
Show both favorable and unfavorable cases.
1:25 · Check 3
Name the next measurement needed.
What appears on screen
Name the next measurement needed.
1:30 · Now try a different case
Open the lesson and try its different practice case. Use every check in the full task. Watching alone does not mark the lesson complete.
What appears on screen
Open the lesson Try the new case Check and revise The full task and its requirements are in the linked lesson.
Watching explains the example. Complete the lesson practice to check what you can do. Explore all visual lessons →
The method
Distinguish observed values, estimates, assumptions and unknowns in your output. A scenario answers “if these assumptions hold”; it is not a prediction. Ask AI to identify which assumptions drive the result, then compute conditional alternatives with a deterministic tool. Keep source and calculation records.
Match precision to evidence. A model-generated confidence score is not a calibrated statistical interval. Formal inference needs a justified design, assumptions and appropriate methods; this lesson uses arithmetic scenarios, not significance testing. Explain whether the decision changes across plausible supplied values and what measurement would reduce uncertainty.
Choose your model, harness and offline route
Text-only assistant
Use supplied text. Ask for a plan or draft; do not claim browsing, code execution or file access that was unavailable.
Tool-enabled application or harness
Record which tools actually run, allowed files and actions, approval boundaries and observable results. Tools are optional unless the task needs them.
Local or cloud deployment
Inspect inference, retrieval, connectors, logs and storage separately. Use only authorized environments for real data; training fixtures are fictional.
Higher-capability or frontier model
Evaluate the exact task and configuration. Capability does not supply missing evidence or grant permission. No provider ranking or guarantee is implied.
Offline alternative
Use the supplied inputs and inspect the worked example manually. Builder exercises use local deterministic Python. No paid account or live model call is required.
Record the exact product/model label when available, tools actually used, inputs, permitted actions, observed output and checks. Live accounts or APIs may have external costs; they are optional and are not used by this page.
Read the general workflow guide →Worked example
Supplied input
Fictional planning scenario: 20 requests per week; baseline 8 minutes each; assumed assisted total effort 5 to 9 minutes per request. These are planning assumptions, not measured outcomes.
A checked result
Baseline 160 min/week. Conditional assisted effort 100–180. Difference ranges from saving 60 to adding 20 minutes. Measure actual review and correction effort before adopting.
Why this works
The uncertainty crosses the “saves time” boundary. A single optimistic estimate would hide a relevant decision risk.
Try a different case
Independent assumptions: 30 items/week; baseline 6 minutes/item; assisted effort 4–7. Calculate the range and write a conditional decision note with a measurement plan.
Download this task and checklist →Interactive practice / Fictional fixture
Calculate a conditional effort range
Use the supplied independent case above. Check the bounded decisions, then review your written artifact against the full acceptance criteria.
Everything runs in this browser. No AI model is called and no work is uploaded. Bounded checks cover specific facts and rules. Your writing is not graded: you review it yourself. Practice never marks a lesson complete automatically.
Explain that effort could fall by 60 or rise by 30 minutes; propose a useful pilot measure.
Try the task, run the checks, then revise. Checks are teaching feedback, not an instructor grade.
Observed browser simulation
This trace comes from the bounded local checker. It is not a Python run, model result or production tool execution.
Keep or restore your work
Drafts are not saved automatically. Save only fictional practice data. A browser draft may be lost if storage is cleared; download a copy to keep it.
Your steps
- Calculate baseline and both scenario endpoints.
- State assumptions separately from observations.
- Identify a pilot measure that would resolve the decision.
Check your work
- Baseline 180; assisted 120–210 min/week.
- Difference ranges from saving 60 to adding 30 minutes.
- Do not describe the range as a measured confidence interval.
After your attempt: review notes and a common mistake
A defensible note says the workflow may save or add effort under the supplied assumptions. A pilot should measure total usable-output effort and quality, not only generation time.
Different wording or a different justified decision can pass. Check your work against every requirement; these notes are not an automated grade.
Explain your approach
At what assisted effort does this scenario break even?
Keep your artifact, one correction or decision, its evidence and one remaining limitation. Nothing on this page sends or uploads your work.
Check your understanding
Choose an answer to see feedback. This is a knowledge check, not instructor assessment.
Review your independent practice
Complete the supplied task before recording progress. Use the acceptance criteria and reveal the review notes after your attempt. Keep your artifact yourself; nothing is uploaded.
Not yet self-reviewed. Completion stays in this browser and does not issue a badge.
Optional deeper study
Explore the related general-course lesson → This opens the existing canonical lesson; it is optional depth, not another copy of this focused task.
Revision 2026-10-03. Fictional examples, not observed provider results. Knowledge checks and completion records are self-study aids.