Decide which KPI movements are worth flagging this week
A decision model looks at each weekly metric change in context and decides whether it is worth a person's attention, so the weekly digest leads with the few movements that matter instead of every number.
An example pattern written by Agents Lookup. We have not yet found a public build of this exact job.
The use case
Weekly KPI digests list every metric, and the reader has to spot what changed and whether it matters. Code calculates the week-on-week change for each metric, and Jev reads each change with a short note on recent events, such as a sale, a holiday, or a price change, and answers how notable it is. Movements rated notable or urgent with a confidence of 0.8 or higher move to the top of the digest. Lower-confidence ratings are listed in a short check these section. Jev does not explain causes or recommend actions. The owner reads the digest, decides what to look into, and Claude can draft a short summary for the owner to edit.
Example workflow
- A scheduled job pulls weekly metrics from Shopify, Google Analytics, and the accounting system into a Google Sheet.
- Code calculates each metric's change and attaches any notes from a shared events tab.
- Each metric, its change, and the notes are sent to Jev as the state.
- Jev answers a Score question, how notable is this movement, with the levels expected, worth a look, notable, and urgent.
- Code orders the digest by that level and puts low-confidence ratings in a check these section.
- The digest is posted to Slack or emailed, and the owner decides what to follow up.
Tools
- Jev (TypeSafe AI)
- Google Sheets
- Shopify
- Google Analytics
- Slack
- Claude
Risks and guardrails
- A slow decline may never look notable week to week — guardrail: code also compares against the same week last month and last year.
- Missing event notes make expected changes look urgent — guardrail: the digest shows which notes were used, so the reader can spot gaps.
- Readers may skip metrics rated expected — guardrail: the full table stays at the bottom of every digest.
Related recipe
Weekly KPI Digest from Google Sheets with Source-Cited Numbers: An agent reads your defined metrics from Google Sheets, compares them to last week and targets, and drafts a plain-English digest where every number cites its cell. The owner approves before it goes to Slack or email.
Want it set up for you? Request a quote.
Sources
Written by Agents Lookup. Credits and official pages for the tools this use case names:
- Shopify Dev MCP server (AI Toolkit) (official page): shopify.dev/docs/apps/build/ai-toolkit (checked 2026-11-09)
- Google Analytics MCP server (official page): github.com/googleanalytics/google-analytics-mcp (checked 2026-11-09)
- Slack MCP server (official page): docs.slack.dev/ai/slack-mcp-server (checked 2026-11-09)
- Claude (official page): claude.ai (checked 2026-11-09)