Turn spreadsheet data into a weekly metrics report that someone signs off before sending
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Use cases
Methods
Draft a weekly KPI report automatically and send it only after approval
Steps
- Write the KPI definitions. Agree each KPI in one line with the column, filter and week boundary. Pick the time zone on purpose. Check: Two people read the definitions and compute the same number for last week.
- Build the script and checks. Paste the prompt. The agent writes code that loads sources, computes KPIs and prints data checks. Check: The script prints rows loaded, rows dropped with reasons, and the KPI table.
- Test against a week you already know. Run it on a past week where you have trusted numbers. Fix definitions until they match. Check: Every KPI matches your trusted numbers, or you know why it differs.
- Review the commentary. Read the three sentences. Remove any cause the data does not show. Check: Every claim in the commentary points to a number in the table.
- Schedule the run and the draft. Run it weekly and save the result as a draft to the approver. Do not wire it to send. Check: On Monday a draft is waiting with the right week dates in the title.
- Approve and send. The approver reads the data checks first, then the numbers, then sends. Check: The sent report has no DO NOT SEND flag and matches the draft.
- Optional: The source includes an agent prompt and a list of what goes wrong; they are linked there, not copied here.
- Note: Steps quoted from the Agents Handbook (CC BY 4.0). Works with Claude Code, Claude, n8n or ChatGPT. The report is drafted automatically but never sent without approval.
Run this method with your agent
Download .mdCopied 0
--- name: "build-a-weekly-kpi-report-for-approval-method" description: "Use when you need to Turn spreadsheet data into a weekly metrics report that someone signs off before sending. Draft a weekly KPI report automatically and send it only after approval" --- # Draft a weekly KPI report automatically and send it only after approval Job: [Turn spreadsheet data into a weekly metrics report that someone signs off before sending](https://aiagents.org/canai/build-a-weekly-kpi-report-for-approval) ## Need - AI agent ## Steps 1. Write the KPI definitions. Agree each KPI in one line with the column, filter and week boundary. Pick the time zone on purpose. Check: Two people read the definitions and compute the same number for last week. 2. Build the script and checks. Paste the prompt. The agent writes code that loads sources, computes KPIs and prints data checks. Check: The script prints rows loaded, rows dropped with reasons, and the KPI table. 3. Test against a week you already know. Run it on a past week where you have trusted numbers. Fix definitions until they match. Check: Every KPI matches your trusted numbers, or you know why it differs. 4. Review the commentary. Read the three sentences. Remove any cause the data does not show. Check: Every claim in the commentary points to a number in the table. 5. Schedule the run and the draft. Run it weekly and save the result as a draft to the approver. Do not wire it to send. Check: On Monday a draft is waiting with the right week dates in the title. 6. Approve and send. The approver reads the data checks first, then the numbers, then sends. Check: The sent report has no DO NOT SEND flag and matches the draft. 7. Optional: The source includes an agent prompt and a list of what goes wrong; they are linked there, not copied here. 8. Note: Steps quoted from the Agents Handbook (CC BY 4.0). Works with Claude Code, Claude, n8n or ChatGPT. The report is drafted automatically but never sent without approval. ## Credit Method author Agents Handbook editors (CC BY 4.0) Source: https://agentshandbook.com/p/build-a-weekly-kpi-report-for-approval
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/build-a-weekly-kpi-report-for-approval - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "build-a-weekly-kpi-report-for-approval",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}