Use lessons 01–03 or equivalent skills before this exercise. You can revisit them from the lesson list.
A browser and text editor. Live source discovery needs browsing; all supplied exercises also work offline.
Start with the idea
Write a briefing with facts, advice and limits clearly separated.
Say what the evidence establishes first. Then state what you recommend and why. Mark conditions and proposed review steps rather than presenting them as completed approval.
Finding: What the evidence supports, distinct from your recommendation.
See the example and check your understanding
A made-up teaching example
One workshop has favorable feedback from eleven of fourteen respondents. Staffing supports one repeat session. A repeat pilot can be proposed, but broader demand and efficiency gains are not established.
Ask yourself
Can the recommendation be presented as proven organization-wide benefit?
Show the explanation
No. Keep it conditional and name what the next session should measure before another decision.
Start with these checks
- Separate findings from recommendations.
- Keep limits and unknowns visible.
- Label proposed review as proposed.
Use the different practice case below and check every requirement in its full instructions.
Full learning objectives
- Choose a structure for the reader’s decision.
- Distinguish observed findings from proposed action.
- Revise without losing caveats or changing meaning.
Captions appear here during playback.
Write a briefing that separates findings from recommendations
Write a briefing with facts, advice and limits clearly separated.
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
Write a briefing with facts, advice and limits clearly separated.
What appears on screen
Write a briefing with facts, advice and limits clearly separated.
0:07 · The idea
Say what the evidence establishes first. Then state what you recommend and why. Mark conditions and proposed review steps rather than presenting them as completed approval.
What appears on screen
Say what the evidence establishes first. Then state what you recommend and why. Mark conditions and proposed review steps rather than presenting them as completed approval.
0:20 · One useful term
Finding. What the evidence supports, distinct from your recommendation.
What appears on screen
What the evidence supports, distinct from your recommendation.
0:28 · A worked example
One workshop has favorable feedback from eleven of fourteen respondents. Staffing supports one repeat session. A repeat pilot can be proposed, but broader demand and efficiency gains are not established.
What appears on screen
One workshop has favorable feedback from eleven of fourteen respondents. Staffing supports one repeat session. A repeat pilot can be proposed, but broader demand and efficiency gains are not established.
0:45 · Your turn to think
Can the recommendation be presented as proven organization-wide benefit? Pause and decide before continuing.
What appears on screen
Can the recommendation be presented as proven organization-wide benefit? Pause the video if you need more time.
1:03 · Why this answer works
No. Keep it conditional and name what the next session should measure before another decision.
What appears on screen
No. Keep it conditional and name what the next session should measure before another decision.
1:11 · Check 1
Separate findings from recommendations.
What appears on screen
Separate findings from recommendations.
1:17 · Check 2
Keep limits and unknowns visible.
What appears on screen
Keep limits and unknowns visible.
1:22 · Check 3
Label proposed review as proposed.
What appears on screen
Label proposed review as proposed.
1:27 · 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
Use a briefing structure that serves the decision: question, supported findings, options, recommendation, limitations and next evidence. Draft from your checked ledger. Tell the assistant the audience and output constraints, but do not ask it to fill gaps to make the report look complete.
A recommendation can be reasonable without being proven. Explain its assumptions and the conditions under which you would change it. During editing, compare the new draft with the ledger; a concise rewrite can silently drop a condition or convert “may” into “will.” Ask for an edit summary, not private reasoning, and check substantive changes yourself.
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 evidence: one small workshop received favorable feedback from 11/14 respondents. Staffing exists for one repeat session. Demand outside that session and delay reduction are unmeasured.
A checked result
Finding: favorable feedback among respondents. Recommendation: one repeat session with a defined feedback and attendance check. Limit: evidence does not establish broader demand or efficiency gains. Next decision: continue only after reviewing the new results.
Why this works
A bounded trial follows from feasibility and limited evidence; it is not presented as a demonstrated organization-wide benefit.
Try a different case
Independent fixture: two of three volunteer teams requested an instruction sheet; a coordinator can review one draft. Write a 150-word briefing recommending or declining a limited trial.
Download this task and checklist →Interactive practice / Fictional fixture
Compose your decision briefing
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.
Describe the supplied observations without inventing impact.
Trial or decline can be justified. State assumptions, limitations and what would change your decision.
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
- Draft findings, recommendation, assumptions and a review checkpoint.
- Audit every factual sentence against the supplied evidence.
- Shorten the briefing while preserving the scope and uncertainty.
Check your work
- Do not claim organization-wide demand or measured savings.
- Name the coordinator review as a proposed step, not completed approval.
- Make the recommendation conditional and understandable.
After your attempt: review notes and a common mistake
A plausible near miss says “the organization needs this sheet.” The fixture supports interest from two sampled teams, not a universal need. Either trial or decline can pass if justified by the stated evidence.
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
Which edit would most easily distort your recommendation?
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.