Daily sales and labor digest for restaurant managers
Each morning, an agent pulls the prior day's sales, covers, and labor hours from Toast and 7shifts, compares them with targets and the same day last week, and posts a short digest for the owner.
The use case
Restaurant owners often check sales on their phone at midnight and labor costs at the end of the month, by which time it is too late to adjust. The numbers exist in the POS and scheduling app, but nobody has time to put them side by side every morning. This agent pulls the prior day's net sales, covers, average check, voids, comps, and labor hours from Toast and 7shifts, compares them with the targets in a sheet and the same day last week, and writes a short plain-English digest. Every number cites the report it came from. It notes large swings, such as comps well above normal, without guessing causes. The owner or general manager reads the digest and decides what, if anything, to change.
Example workflow
- Early each morning a scheduled job pulls the prior day's sales summary from Toast and labor hours from 7shifts.
- The agent reads targets for sales, labor percentage, and comps from a Google Sheet the owner maintains.
- It compares the day with its targets and with the same weekday last week, and marks any number outside the set range.
- It drafts a short digest with each figure, its source report, and the comparison, without guessing at causes.
- The digest is posted to the owner and general manager in Slack or by email.
- The owner or general manager decides on any changes, and the agent stores each day's figures in the sheet for later review.
Tools
- Toast
- 7shifts
- Google Sheets
- Slack
- Claude
- Zapier or Make
Risks and guardrails
- A report could pull before the day is closed out and show incomplete numbers — guardrail: the digest shows the pull time and marks the day as incomplete if the POS close has not run.
- Readers may treat flagged swings as proof of a problem — guardrail: the digest states numbers and comparisons only and does not assign causes.
- Labor data could show individual pay to too many people — guardrail: the digest reports totals and percentages only and goes to the owner and general manager.
- Targets in the sheet could be outdated — guardrail: the sheet shows when targets were last updated, and the agent flags targets older than a set age.
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:
- 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)
- Zapier MCP (official page): zapier.com/mcp (checked 2026-11-09)
- Make MCP server (official page): developers.make.com/mcp-server (checked 2026-11-09)