Log in / Create free account🌐 ES☀️

User manuals · Module 9 — Suite para ChatGPT Ads

ChatGPT Ads manual · The account audit and its score

⏱️ 7 min read · 🤖 ChatGPT Ads · updated on 2026-09-28

📗 This is the user manual for the Suite for ChatGPT Ads, the tool in the Ninja Scripts panel. Here you can search it, listen to it, highlight it and save it to favourites. It is updated with every release of the tool.

A health snapshot of the whole account, with a score from 0 to 100 and the list of what to fix in order of severity. It's recalculated on every visit and after every read (hourly): it costs nothing, it doesn't go out to the internet and it writes nothing in your account.

Where you find out: the email report (weekly and monthly) carries its 🩺 «Account health» block — score, how much it has gone up or down since the start of the period, and the critical findings; and in the panel, the red badge with the number of criticals in the 💡 Optimise menu, visible from any screen and the immediate warning. The audit sends no emails of its own: the report is what tells you about it.

The six areas and their weight

Area The question it answers Weight
🚦 Delivery can it serve? 18 %
🧱 Structure is it well built? 18 %
🖼️ Ads is there something to compete with and something to test? 16 %
📏 Measurement do we know what works? 18 %
💶 Money is the spend going where it should? 15 %
📐 Relevance does everything talk about the same thing? 15 %

Each area starts at 100 and loses points per finding: 40 for a critical, 18 for an important, 7 for an improvement. The score is the weighted mean. An area with no data doesn't score: its weight is shared out among the others, rather than penalising you for something that can't be measured.

≥ 80 good · ≥ 55 needs work · below that, poor.

Two caps that prevent a misleading score

  1. With critical findings the score cannot say «good». With one it won't go above 79; with two or more, above 54. Without this, five areas at 100 masked a collapsed delivery and the account came out «good» with its campaign paused and a rejected ad.
  2. Spending for real (50 of your currency in 30 days) with no target cost per conversion caps you at «needs work». It isn't an accusation — nobody knows whether it's wrong: it's refusing to hand out a pass when nobody can say whether that money is well spent. It lifts as soon as you set the target, which is one field.

The score card tells you when the score is capped and why.

The fourth state: «can't be judged yet»

Besides critical, important and improvement, there are two categories that exist to avoid noise:

Those things are said rather than kept quiet. On a new channel, without this state half the report would be noise and the other half silence.

📐 One case worth knowing: if you haven't saved your OpenAI key, the relevance index is worked out with an approximate method, and with it the 📐 Relevance area doesn't score — its 15 % is shared out among the others and it shows under «can't be judged yet». That's deliberate: the two scales aren't comparable, and accusing with the approximate one would be judging the instrument, not the account. Save the key (pennies) and that area starts counting.

What it checks

It doesn't repeat the 💡 Recommendations rules: it absorbs them, with their own wording, so if their thresholds ever change the audit changes with them. On top of that, its own checks:

Thresholds in plain sight

Every finding carries its figure and its threshold in the wording itself, and the screen publishes the full threshold table in a collapsible panel. That way you can argue with a threshold instead of believing a score.

The history

One row per day is stored, with the score and its areas, and the screen draws the 30-day trend. It's the only thing that can't be reconstructed backwards: it starts the day it's first calculated, so on a freshly connected account the chart takes a few days to say anything.

📎 Sources and further reading

⚠️ Free training with no support. Ninja Scripts support channels (email and Telegram) are only for the use of the scripts, not for Google Ads questions or questions about this training.

Pick up here

← BeforeChatGPT Ads manual · Recommendations and the target cost per conversionSuite para ChatGPT AdsAfter →ChatGPT Ads manual · Rejected ads: the reason and the fixSuite para ChatGPT AdsRelatedChatGPT Ads manual · What the tool is and what ChatGPT Ads allowsSuite para ChatGPT AdsRelatedChatGPT Ads manual · Connecting your account: the key, the pixel and the hourly readSuite para ChatGPT AdsRelatedChatGPT Ads manual · Getting around: menu, date ranges and chartsSuite para ChatGPT AdsRelatedChatGPT Ads manual · Overview: your account's numbers at a glanceSuite para ChatGPT Ads

See the full syllabus

🎓
You're reading the Ninja Academy in the open

Create your free account (no card) to save your progress, take the graded quizzes, earn the Basic level certificate and unlock part of the Intermediate and Advanced training.

Create my free account →
🥷

Subscriber feature

This option is part of Ninja Scripts’ paid subscriptions.

See the subscription →