On a schedule

Get a written monthly report from your numbers

Each month you get a written analysis of your sheet's figures, compared with earlier periods.

Runs: On a schedule
Apps: Google Sheets
AI: Yes, uses the built-in AI allowance
Access: read

Send this to your assistant

Create a ClickRuntime automation: on the 1st of each month, read my P&L sheet, compare last month with the month before and the same month last year, and email me a written analysis.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A small business owner keeps sales, expenses and ad spend in a Google Sheet. At month end she needs a report for her partner or her accountant, so she builds charts, compares against last month and tries to put into words why profit dropped. It takes half a day, so it happens quarterly at best, and by then a problem that began in week two has already cost her money.

On the schedule you set, ClickRuntime reads the ranges you specify, computes period totals and changes against the last period, and passes the figures to ClickRuntime's built-in AI. The AI writes a narrative covering what rose and fell, likely reasons visible in the data and what deserves attention, and the report is emailed.

Owners, finance managers and analysts use it for monthly, weekly or quarterly updates.

What you get out of it

Reports actually get written
A task that takes half a day is skipped when things get busy. Having the draft arrive in your inbox means the review happens regularly, and decisions are based on current numbers.
Totals are calculated, then described
Sums and percentage changes are computed from the sheet before the AI writes anything. The narrative explains calculated numbers, which keeps the figures accurate and the text readable. Nobody has to worry that the AI quietly invented a total.
Problems are noticed in week two
A weekly or monthly report highlights a rise in costs or a fall in sales while it can still be corrected. Leaving it to a quarterly review lets a bad trend run for months.
Stakeholders get plain language
Partners, investors and managers who do not read spreadsheets can follow a written summary. The numbers remain in the sheet for anyone who wants to dig into them. Less time goes to answering what the sheet means.
Consistent reporting over time
The same structure every period makes comparison easy. You can see how this month's report differs from last quarter's, instead of working through a different format each time. Trends become easier to spot over a year.

How it works

What happens, step by step

Every month ClickRuntime reads the profit and loss figures in your Google Sheet.
It compares the latest month with the month before and the same month last year.
AI writes a short report explaining what changed and why it matters.
The report is emailed to you.

Before it runs live

Connect your Google Sheets account and pick the spreadsheets it may use

What you get

RunsOn a schedule

Get a written monthly report from your numberstoday, 9:00Succeeded

Email · P&L analysis: Sep 2026Revenue rose 8% on August and 21% on Sep 2025, driven by the Acme contract. Software costs grew faster than revenue for the second month.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Run it at a different time, more or less often, or only on weekdays
Change what the AI looks for, or how it writes the result
Add another app, for example also send it to Slack
Combine it with other Google Sheets steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

ai_report_from_sheet_data.pyexample

from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from clickruntime import on_trigger, credentials, ai, notify

SHEET_ID = "your-spreadsheet-id"

@on_trigger
def run(event):
    sheets = build("sheets", "v4", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False).spreadsheets()
    rows = sheets.values().get(spreadsheetId=SHEET_ID, range="P&L!A1:Z").execute().get("values", [])
    header, body = rows[0], rows[1:]
    # Columns are months (oldest first): compare the last one, the one before, and 12 months back.
    cols = {"last month": len(header) - 1, "month before": len(header) - 2, "same month last year": len(header) - 13}
    table = "\n".join(f"{r[0]}: " + ", ".join(f"{k} {r[c] if c < len(r) else ''}" for k, c in cols.items()) for r in body)
    analysis = ai.generate(f"Write a short analysis of {header[-1]} for a business owner: what moved, why it matters, "
                           f"and what to watch.\n{table}", max_output_tokens=900).text
    notify.email_me(f"P&L analysis: {header[-1]}", analysis)
    return {"lines": len(body)}

FAQ

Common questions

Can it report on several tabs or ranges?

Yes. You can name each range, such as Sales, Expenses and Ad spend, and the report will cover them together. The AI can relate them, for example expenses rising faster than sales, when the data supports it.

Are the numbers in the report reliable?

Totals and changes are calculated by the automation from your cells, and the AI describes them. Always glance at the figures against the sheet the first few times. Any explanation of why something happened is an inference from the data.

Can I send the report to my accountant?

Yes. Add one or more recipients to the email, or send a short version to the team and a detailed one to finance. Review what the sheet contains first, since the report may expose sensitive numbers.

What permissions does it need?

read. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.

How many runs does it use?

One run each time it runs (on a schedule). Checks that find nothing to do and stop right away aren't counted.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

HourlyAI