The AgentivUse cases

An agent that sorts the shared Gmail inbox into reply, action and FYI, drafts the replies and logs every decision in a Sheet

Function: OperationsEffort: An afternoonPublished: 2026-10-16

The problem

A shared info@ or ops@ inbox gets a hundred emails a day and the person on duty reads all of them to find the twenty that need something. Replies go out late, tasks hide in threads, and nobody can say afterwards what was handled or why.

How the agent works

On a schedule, or when the duty person clicks a button in the Gmail side panel, the agent collects unread emails from the last seven days and sends the subject and body of each to Gemini with a fixed prompt. Each email is classified as needs-response, action-required or for-your-info and gets the matching Gmail label. For needs-response emails the agent writes a draft reply in Gmail; for action-required ones it logs the task. Every email, its category and the reason are appended to a Google Sheet so the team can audit the decisions. A person reviews the drafts before sending and moves tasks to the task board; the agent never sends mail.

Worked example

Google's own Apps Script samples repository ships this as the Email Classifier add on: it processes unread emails from the last seven days, classifies each into needs-response, action-required or for-your-info, applies the label, generates draft replies for the needs-response group and logs each email's details, classification and reason to a Google Sheet. A sibling sample in the same repository labels emails with an upset tone using Gemini on Vertex AI. Google notes the sample has only basic error handling, so harden it before daily use.

PDPA note. Email bodies sent to Gemini may contain customer personal data. Run it inside your own Google Cloud project under your Workspace terms, restrict access to the log Sheet, and exclude mailboxes that handle HR or health matters.

Run this in your business

Digigen's AI Workshop and Solution Design package takes a use case like this from idea to a working build: a half day workshop with your team (THB 25,000) or ten days of discovery, prioritisation and solution design (THB 160,000, credited against the build).

Book the AI Workshop

Sources

Related use cases

An agent that pulls yesterday's Shopee and Lazada orders into one Google Sheet and flags what has not shipped

OperationsEffort: About a weekShopee · Lazada · Google Sheets

The owner opens two seller centres every morning, exports two spreadsheets and adds them up by hand to learn what sold, which SKUs are running low and which orders are still waiting to ship. On a busy day the check is skipped and a ready to ship order sits past the deadline.

An agent that reads your monday.com project boards every Friday and drafts the client status report

OperationsEffort: An afternoonmonday.com · Claude

Project managers spend Friday afternoon copying statuses and dates out of monday.com into an email or slide for each client. The report goes out late, looks different from one PM to the next, and the overdue items that matter most are buried in a list of everything else.

An agent that reads invoices dropped in a shared Drive folder, extracts the fields into a Google Sheet and queues them for approval

FinanceEffort: An afternoonGoogle Drive · Google Sheets · Gmail

Supplier invoices arrive as PDFs by email and LINE and someone retypes the number, date, amount and due date into a spreadsheet before the accountant sees them. Typos slip through, due dates get missed and month end starts with a hunt for the invoices nobody logged.