Reporting is manual and slow.

The plan

Turn verified metrics into a clear weekly update. This is a manual, AI-assisted workflow: you copy approved inputs into Claude, check the output, and move the accepted result into your existing process. Start with the synthetic example below.

You need access to Claude and your team’s approved document or spreadsheet workspace. Use only data your business permits in those services. Tool plans and limits vary; this walkthrough does not require an API connection.

1. Prepare a small, useful input

In Google Sheets make columns metric, current_week, previous_week, change and note. Use one definition and time window per metric. Calculate change with =B2-C2. For percentage change use =IF(C2=0,“n/a”,(B2-C2)/C2) and format numeric results as a percent. Have the metric owner reconcile totals before copying them.

Use this fictional sample for your first run:

M1 | Tickets received | 120 | 100 | +20 | +20%
M2 | Tickets closed | 110 | 105 | +5 | +4.76%
M3 | Backlog at week end | 35 | 25 | +10 | +40%
No cause of these changes has been verified.

2. Give Claude a precise job

Open a new chat at claude.ai. Paste the prompt below, then paste the sample after it under a heading called INPUT. For a PDF, attach the sample file to the chat instead. Keep the source and instructions clearly separated.

Write a weekly report with three sections: What changed, What we do not know, and Questions for the owner. Use only supplied numbers; do not recalculate them. Cite the metric ID beside every claim. Distinguish observations from possible explanations. Do not claim causation. Limit the report to 180 words.

INPUT:
[Paste the sample or your approved source here.]

Read the response before continuing. If required columns are missing, ask: “Return the same result using every requested column. Mark unsupported fields UNKNOWN.” Do not fill gaps by asking the model to guess.

3. Check against the expected result

Backlog rose from 25 to 35 (+40%, M3). More tickets arrived (M1); the data does not establish why. Ask the owner whether staffing or ticket complexity changed, without presenting either as fact.

4. Put the checked result to work

Compare each number in the narrative with the verified sheet. Keep metric IDs in the internal report so colleagues can inspect the source. The operations owner adds context, approves the report, and shares it through the usual channel.

Keep a status of draft, needs clarification, approved, or completed beside each item. A draft is not a completed action. If the service is unavailable, use the original source and your normal manual process.

5. Test the awkward cases

Test a zero previous week, a missing metric, and mismatched reporting periods. The report must state the limitation rather than invent a comparison. Measure total preparation and review time, plus factual corrections.

Run the same cases again after changing the prompt or source. Keep the input, output, correction, and reviewer decision together. Expand only when someone can reliably check the results.

If the result is off

Narrow the input to one record and recheck the source. For missing facts, ask the process owner. For an unsupported statement, remove it and add an explicit constraint to the prompt. If the same failure repeats, do the task manually until the source or instructions are fixed.

Scope: This is an original illustrative recipe with synthetic data, adapted from the field guides below. It is not a live-tested integration or a claim of time saved. Claude’s file-upload documentation explains supported attachments; the copy-and-paste path does not need file uploads.