Build the Copilot Brief Sheet
Copilot does not know your business until you tell it. The same column can mean three different things — only your context picks the right one.
Lesson 3
Context and rules in one place.
Draft a description with Copilot (it already saw your columns and quality issues), answer up to eight short questions, then save everything to a Copilot Brief sheet: description, column lines, sheet rundown, and analysis rules written exactly as given.
Core principles
- Purpose, target metric, column meanings, sources, time period, known relationships, limitations — cover each in the description.
- Context changes the answer: industry shipments may correlate with revenue because both track the same market — a sanity check, not an insight.
- Six rules in the brief: no causation claims; flag weak correlations; report row counts; check seasonality; no invented numbers; raw sheet read-only.
- Read the brief Copilot writes — fix wrong column descriptions before you trust analysis.
- Wrong brief poisons every session — spend time here; it is cheaper than fixing downstream charts.
Check yourself
Why does this lesson put context and rules on a Copilot Brief sheet?
The brief is your contract with Copilot: what the data means and how hard to push on correlations. Without it, insights are guesses dressed as facts.
Do this in Copilot
Complete the draft-and-save flow. Confirm all six rules appear verbatim on Copilot Brief.
Paste this into Copilot Chat and work through it before moving on.
Draft dataset description
Based on what you already know about this workbook from the analysis so far, draft a first-pass description of this dataset: its purpose, the main number I care about, what each column means, where the data likely comes from, the time period, and any relationships you can infer. Mark anything you are unsure about, and ask me up to 8 short questions to fill the gaps. Then combine your read and my answers into a 5 to 6 sentence description I can save.
- Clarifying questions
- After you answer questions, save with:
- Save the finished brief to a new sheet called Copilot Brief. Include, in order: 1. A short plain-language description of the dataset. 2. A one-line description of every column. 3. A rundown of the sheets in this workbook and what each is for: the raw data sheet is the read-only original; the Clean Data sheet is the cleaned copy and your default for all analysis; the Copilot Brief sheet holds the context and rules. 4. The analysis rules below, written in exactly as given: - Treat the raw data sheet as read-only. Never modify, reformat, or delete it; do all work on copies. - For each correlation, give plausible reasons and at least one alternative explanation. Do not claim one thing causes another. - Flag any correlation under 0.4 as weak and note how little it actually explains. Do not base any recommendation on weak correlations alone. - Before correlating, tell me how many rows each column actually has, and exclude or flag any column with significant gaps. - Check whether a relationship could just be seasonality or a shared time trend before calling it meaningful. - Only use values that are actually in the data. If a number is not present, say it is not available rather than estimating.
Did you run this in Copilot? Mark complete when you have tried it.
RecordedNext lesson: Start Every Session with the Brief →
Navigate: press j for next lesson, k for previous.