Weekly

Get a plain-English read on this week's ads

A Monday email compares this week with last and explains which campaigns moved and what to look at.

Runs: Weekly
Apps: Meta Ads
AI: Yes, uses the built-in AI allowance
Access: ads_read

Send this to your assistant

Create a ClickRuntime automation: each Monday, compare this week's Meta Ads results with the week before and email me a short explanation of what changed and which campaigns need attention.

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

Meta Ads Manager gives you columns of numbers, and it expects you to find the story. A small business owner running four campaigns sees spend, reach, results and cost per result, but it takes real effort to compare this week with last week, notice that one ad set doubled its cost per result, and decide what to do about it. Many people just glance at total spend and move on.

Each week, ClickRuntime fetches two weeks of insights from Meta, uses its built-in AI to compare the periods and writes a short commentary in plain words: what changed, what likely caused it and what to try next. The commentary is emailed to you, with no OpenAI or Anthropic key needed.

It is especially helpful for owners and marketers without time for a deep weekly review, and for agencies preparing client notes.

What you get out of it

You get a plain-language read, not just numbers
Instead of staring at columns, you read that cost per result rose 30 percent because one audience tired out. That points to a decision you can make straight away. It reads like a short note from a colleague who studied the account.
Week-on-week changes are not missed
The AI looks at two weeks side by side, so a quiet decline in click rate is noticed before it becomes expensive. Gradual problems are the ones people usually overlook.
Suggestions give you a starting point
Each note proposes something to try, such as pausing the weakest ad or moving budget to a campaign that converts. You still decide, but you do not start from a blank page.
Ad budget goes further
Spending stays with campaigns that deliver and stops flowing to those that do not. Even a small reduction in wasted spend each week adds up over a quarter. The effect is gradual but real.
Useful for client communication
Agencies can reuse the commentary as the base of a weekly note. Clients receive an explanation they can follow instead of a spreadsheet they cannot interpret. That makes reporting faster and conversations with clients more productive.
Learning builds up over time
Reading a short explanation each week teaches you what drives your results. After a few months you start to spot the patterns yourself, even before the commentary points them out.

How it works

What happens, step by step

Once a week, ClickRuntime pulls your Meta Ads results for this week and the week before.
AI compares the two weeks and explains in plain English what went up, what went down and why it matters.
It points out campaigns that need attention, like one whose cost per purchase is climbing.
You get the write-up by email.

Before it runs live

Connect Meta Ads

What you get

RunsWeekly

Get a plain-English read on this week's adstoday, 9:00Succeeded

Email · Meta Ads: this week vs lastSpend rose 18% but purchases were flat. "Autumn sale - prospecting" CPA climbed from $24 to $38; consider refreshing its creative.

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 Meta Ads 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_analysis_of_weekly_results.pyexample

from datetime import date, timedelta
from clickruntime import on_trigger, notify, http, credentials, ai

ACCOUNT = "act_123456789"

def week(token, since, until):
    return http.get(f"https://graph.facebook.com/v21.0/{ACCOUNT}/insights", params={
        "level": "campaign", "time_range": f'{{"since":"{since}","until":"{until}"}}', "access_token": token,
        "fields": "campaign_name,spend,clicks,ctr,actions,cost_per_action_type", "limit": 200,
    }).json()["data"]

@on_trigger
def run(event):
    token = credentials.connection("meta-ads", "main")
    end = date.today() - timedelta(days=1)
    this_week = week(token, end - timedelta(days=6), end)
    last_week = week(token, end - timedelta(days=13), end - timedelta(days=7))
    keep = lambda rows: [{k: r.get(k) for k in ("campaign_name", "spend", "clicks", "ctr", "actions")} for r in rows]
    summary = ai.generate(
        "Compare this week's Meta Ads results with last week's. In under 200 words, explain what changed "
        f"and which campaigns need attention.\n\nThis week: {keep(this_week)}\n\nLast week: {keep(last_week)}",
        max_output_tokens=400,
    ).text
    notify.email_me("Meta Ads: this week vs last", summary)
    return {"campaigns": len(this_week)}

FAQ

Common questions

How much data does the AI look at?

It receives two weeks of insights from your ad account, such as spend, results, cost per result and click metrics, at the level you set. That is enough to compare the latest week with the one before it.

Can the AI make changes to my campaigns?

No. It only reads insights and writes commentary. It does not pause ads or change budgets, so all decisions stay with you. Any change to what the commentary covers is shown for your approval first.

Is the advice reliable?

Treat it as a well-informed starting point. The AI works from the figures it is given and cannot see your product margins, seasonality or creative content, so check suggestions against what you know about the business.

What permissions does it need?

ads_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 (weekly). 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.

Weekly