GSC Wizard

@gscwizard

Talk with your SEO data from GSC, Bing, Yandex, Merchant Center and GA4 in your AI assistant via GSC Wizard. Next: Google Ads / Bing Ads integration.

's Gravenhage

Joined September 2026

2 Following

3 Followers

7 Posts

gscwizard retweeted

Jan-Willem Bobbink

@jwbobbink

3 days ago

Don't use a direct Search Console API connection to your chatbot or agent to analyse your SEO performance. I see thousands of people making decisions on the wrong data. That was the core of my All Day AI talk today: "Agents hallucinate your numbers". Thanks to everyone who joined. Full slidedeck at https://t.co/6EVFYcB4DQ The most common mistake is not the AI being bad at math. It's the AI doing good math on incomplete data. Connect Search Console to Claude or ChatGPT and ask for your CTR. The tool hands the model the top 100 queries. The model adds them up neatly and gives you an answer: 3.11% CTR. 5,952 clicks. The real numbers for the same site and period: 2.56% CTR. 7,271 clicks. Why? Those 100 rows are only the top of your data. Everything below page one is missing, and Google hides the rare queries anyway (privacy, blabla). On my own site that's 18% of clicks. Across the properties I measured, it's close to half on average. The model can't know what it never received. So it does the careful math, adds a polite caveat, and is still wrong. In my test: 15 out of 15 times. The fix is simple: don't let the model calculate. Give it the totals, calculated on the server, and let it write the sentence. Same model, same question: 15 out of 15 right. If you use AI for SEO reporting, compare one answer with your Performance report this week. You might be surprised. #SEO #MCP #AIagents

jwbobbink's tweet photo. Don't use a direct Search Console API connection to your chatbot or agent to analyse your SEO performance. I see thousands of people making decisions on the wrong data.

That was the core of my All Day AI talk today: "Agents hallucinate your numbers". Thanks to everyone who joined.

Full slidedeck at https://t.co/6EVFYcB4DQ

The most common mistake is not the AI being bad at math. It's the AI doing good math on incomplete data.

Connect Search Console to Claude or ChatGPT and ask for your CTR. The tool hands the model the top 100 queries. The model adds them up neatly and gives you an answer: 3.11% CTR. 5,952 clicks.

The real numbers for the same site and period: 2.56% CTR. 7,271 clicks.

Why? Those 100 rows are only the top of your data. Everything below page one is missing, and Google hides the rare queries anyway (privacy, blabla). On my own site that's 18% of clicks. Across the properties I measured, it's close to half on average.

The model can't know what it never received. So it does the careful math, adds a polite caveat, and is still wrong. In my test: 15 out of 15 times.

The fix is simple: don't let the model calculate. Give it the totals, calculated on the server, and let it write the sentence. Same model, same question: 15 out of 15 right.

If you use AI for SEO reporting, compare one answer with your Performance report this week. You might be surprised.

#SEO #MCP #AIagents

GSC Wizard @gscwizard

8 days ago

@dnncha @tomosman Wear a magic hat and find out. If you can get me 666 followers, I'll tell the trick and write a case study.

gscwizard retweeted

Aleyda Solis 🕊️

@aleyda

10 days ago

Google doesn’t label AI Mode queries in Search Console, but they leave a trace: people reply to an AI, and the reply gets logged as a search: @jwbobbink classified every query of 155 sites over 16 months to see how often that happens, and how fast it’s growing 👇 Here are key insights: * Replies typed at an AI are now normal. Bare replies such as “yes”, “ja” or “yes please” showed up as searches on 94 of the 155 sites. Per million impressions they grew from 5.6 to 116: 21 times as many in 16 months. * German speakers say please to an AI, Indonesian speakers don’t. Three in four German yes-replies come with “bitte” or “gerne” (“ja bitte” on 52 sites). Dutch speakers add “graag” two times in three, English speakers say “yes please” 40% of the time, and Indonesian speakers never do. * Follow-up questions are rising from a small base. Queries like “what about salary” are still rare, but they grew 39x over the window, most of it after May 2026. * The typical site sees seven times more AI-shaped queries. The median site’s AI-shaped share of impressions went from 0.032% to 0.22%. Across all impressions pooled the share fell, because a few very large sites carry most of the volume. * AI-shaped queries rarely get clicked. Their click-through rate was 2.9%, against 35.6% for all queries pooled. * It’s still small. AI-shaped queries were 0.13% of all impressions. The growth is the story, not the size. More: https://t.co/xaQuuHbWY9

aleyda's tweet photo. Google doesn’t label AI Mode queries in Search Console, but they leave a trace: people reply to an AI, and the reply gets logged as a search: @jwbobbink classified every query of 155 sites over 16 months to see how often that happens, and how fast it’s growing 👇 Here are key insights:

* Replies typed at an AI are now normal. Bare replies such as “yes”, “ja” or “yes please” showed up as searches on 94 of the 155 sites. Per million impressions they grew from 5.6 to 116: 21 times as many in 16 months.

* German speakers say please to an AI, Indonesian speakers don’t. Three in four German yes-replies come with “bitte” or “gerne” (“ja bitte” on 52 sites). Dutch speakers add “graag” two times in three, English speakers say “yes please” 40% of the time, and Indonesian speakers never do.

* Follow-up questions are rising from a small base. Queries like “what about salary” are still rare, but they grew 39x over the window, most of it after May 2026.

* The typical site sees seven times more AI-shaped queries. The median site’s AI-shaped share of impressions went from 0.032% to 0.22%. Across all impressions pooled the share fell, because a few very large sites carry most of the volume.

* AI-shaped queries rarely get clicked. Their click-through rate was 2.9%, against 35.6% for all queries pooled.

* It’s still small. AI-shaped queries were 0.13% of all impressions. The growth is the story, not the size.

More: https://t.co/xaQuuHbWY9

GSC Wizard @gscwizard

9 days ago

GSC tells you how your product pages rank in Google, but it says very little about the free listings that bring in a growing share of shop traffic. Merchant Centers own reports also make you dig to find out why a product isnt showing. I wanted both answers in one place.