On a schedule

Compare this week with last in one email

A Monday table shows users, sessions and conversions for the last two weeks with the percent change.

Runs: On a schedule
Apps: Google Analytics
AI: Not needed
Access: analytics.readonly

Send this to your assistant

Create a ClickRuntime automation: every Monday at 8am, email me GA4 users, sessions and conversions for last week and the week before, with the percentage change.

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

The operations lead at an ecommerce shop wants a plain answer every Monday: did the store do better or worse than the week before? Google Analytics can show two date ranges, but it takes several clicks, and the percentage change has to be worked out by hand or in a spreadsheet. So the comparison happens occasionally, usually after something already feels wrong.

Every Monday, ClickRuntime runs one GA4 report with two date ranges, last week and the week before. It works out the percentage change for users, sessions and conversions and emails a tidy table with each figure and its delta. Nothing is interpreted or written by AI, so the table is precise and repeatable.

It is the sort of email that sits at the top of the inbox on Monday and takes thirty seconds to read.

What you get out of it

The direction is clear immediately
Green or red movement in users, sessions and conversions tells you whether the week went well. No calculation is required, so you can react straight away and not wait for a monthly review.
Conversions next to traffic
Seeing conversions beside sessions shows if growth is real or just noise. Traffic up and conversions flat is a sign to check the landing pages rather than celebrate. That prompts a look at landing pages instead of a premature celebration.
Same measurement every week
Because the same query runs each time, the percentages are comparable week to week. Arguments about how a number was calculated disappear, and discussion moves to what to do about it.
Small trends are caught
A few percent decline a week is easy to miss in the dashboard but obvious across four emails. You act before a slow slide becomes a quarterly problem. Trends beat snapshots every time.
No spreadsheet to maintain
Teams that used to paste numbers into a sheet can stop. The percentage maths is done for you, which removes one source of copy-paste errors and one more Monday chore.

How it works

What happens, step by step

Every Monday at 8:00, ClickRuntime pulls users, sessions and conversions from Google Analytics for this week and last week.
It works out the percentage change for each figure.
You get an email with a small table: each figure, this week, last week and the change.

Before it runs live

Connect Google Analytics

What you get

RunsOn a schedule

Compare this week with last in one emailtoday, 9:00Succeeded

Email · Week over weektotalUsers 6,120 5,480 +11.7% conversions 212 240 -11.7%

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
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other Google Analytics 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.

week_over_week_comparison_email.pyexample

from clickruntime import on_trigger, credentials, http, notify

PROPERTY = "123456789"
METRICS = ["totalUsers", "sessions", "conversions"]

@on_trigger
def run(event):
    res = http.post(f"https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY}:runReport",
        headers={"Authorization": f"Bearer {credentials.connection('google', 'work')}"},
        json={"dateRanges": [{"startDate": "7daysAgo", "endDate": "yesterday", "name": "this"},
                             {"startDate": "14daysAgo", "endDate": "8daysAgo", "name": "last"}],
              "metrics": [{"name": m} for m in METRICS]},
    ).json()
    by_range = {r["dimensionValues"][0]["value"]: [float(v["value"]) for v in r["metricValues"]] for r in res.get("rows", [])}
    this, last = by_range.get("this", [0] * 3), by_range.get("last", [0] * 3)
    lines = [f"{m:<12} {t:>10,.0f} {l:>10,.0f} {(t / l - 1) if l else 0:>+8.1%}" for m, t, l in zip(METRICS, this, last)]
    notify.email_me("Week over week", f"{'':<12} {'This week':>10} {'Last week':>10} {'Change':>8}\n" + "\n".join(lines))
    return {"sent": True}

FAQ

Common questions

Which metrics are included?

Users, sessions and conversions are the default, with each shown for both weeks and as a percentage change. You can add others like engagement rate or revenue if they matter to your team. A short table stays more readable than a long one.

How is the percentage change calculated?

It is the difference between last week and the week before, divided by the week before. A fall from 2,000 to 1,800 sessions shows as minus 10 percent. If the earlier week was zero, the change is shown as not applicable instead of infinite.

Does it use calendar weeks or the last seven days?

You can choose either. Monday to Sunday calendar weeks line up neatly for a Monday email, while a rolling seven days works for businesses that run any day. Pick one and keep it so comparisons stay consistent.

What permissions does it need?

analytics.readonly. Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's 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.

Daily