Where did we lose ground in AI answers this week?

Ask your assistant to call get_analytics with area=visibility and days=7 on the Attensira MCP server. It returns your mention and citation rates per engine with each change marked real or not. If nothing is real, stop. If something is, rank prompts worst first and read the answers behind the two or three that moved.

7 days free · card requiredConnect your assistant

Claudeattensira · attensira.com

Asked: Did we lose ground in AI answers this week?

called get_analytics area=visibility days=7

No loss we can prove. Neither the workspace's change nor either engine's passed the significance test, so the chain stops here.

All answers: 6.0%; n = 2,085 · change not proven
ChatGPT: 5.7%; n = 1,098 · change not proven
Perplexity: 6.3%; n = 987 · change not proven

The first call of the week, on our own workspace.

attensira.com workspace, read over the Attensira MCP · 4 Oct 2026

Who does the work

Analyst · Ran the test

Which call answers it?

Paste it into any client connected to the Attensira MCP server, or ask the question in your own words and your assistant picks the same call.

The call

{ "tool": "get_analytics", "arguments": { "area": "visibility", "days": 7 } }

What can’t this tell you?

Nothing in this chain says why a model changed its answer. Providers swap the models behind an answer surface without notice, and a rewritten system prompt on their side looks identical to a content problem on yours.
A seven-day window gives very few readings per prompt per model, and a rate built on a single-digit n swings for reasons that have nothing to do with you. Widen days before acting.

What is the chain behind it?

When one call is not enough, these are the calls that follow, in order, and why each one is there.

Call 01
Read the workspace level first
Call get_analytics with area=visibility and days=7. This establishes whether anything moved at all. If every delta comes back real:false, stop here — there is nothing to explain, and explaining it anyway is how a team learns to act on noise.
Call 02
Rank the prompts worst first
Call get_analytics with area=prompt, days=7 and order=worst_first. Ranking by how badly you are doing surfaces the losses instead of averaging them away against the prompts you already win.
Call 03
Read the per-platform rows
The same visibility call already returns one row per platform. A drop concentrated on one answer surface is a different problem from a drop across all of them; get_analytics area=platform with a filter opens one platform end to end.
Call 04
Read the answers behind the worst movers
Call get_prompt on the two or three prompts that moved most. The returned answer text is the only place in the product where you find out why a model stopped naming you, rather than that it did.

Why is a one-day drop not a loss?

Because the count can stay flat while the sample moves. We were named in 18 answers on 1 October and on 2 October, yet the rate halved, because twice as many answers were read. The chain tests the change before it calls anything a loss.

answers that named us, 1 Oct: 18 of 225; n=225 answers · 8.0%
answers that named us, 2 Oct: 18 of 438; n=438 answers · 4.1%
answers that named us, 4 Oct: 17 of 150; n=150 answers · 11.3%

Analyst · Ran the testattensira.com workspace, get_analytics area=visibility days=7, read over the Attensira MCP on 4 Oct 2026 · 27 Sep 2026 to 4 Oct 2026

What did it show on our own workspace?

No loss we can prove, which is the usual shape of a week. The right report was one line long, and the chain stopped after its first call. That is the point of starting at the workspace level: a null result costs one call, so a weekly ritual can afford to find nothing, instead of turning into a search for something to report.

How do I read what comes back?

Every delta comes back with real set to false: No change you can prove. It is not a decline and it is not a gain; the sample cannot separate it from noise.
Your rate flat while a competitor's rises: You did not lose ground — somebody else gained. That calls for a different response from a loss.
A drop on one model with the others flat: Most likely a change on that answer surface rather than a change in your content.
A rate that fell while n is in single digits: One or two readings moved it. Widen the window before treating it as a finding.

What does one answer on a lost prompt say?

Before calling a drop a loss, open the answers. Perplexity on 3 Oct, to “why is my brand not mentioned by AI”: guides from other vendors, no tool named, no Attensira. A loss is real only when answers like this repeat across days.

Answer · Perplexityasked 3 Oct 2026

Question: why is my brand not mentioned by AI

Perplexity answered: Your AI may not mention your brand due to prompt fit, source gaps, stale facts, or weak authority signals; fixing positioning, ensuring clear entity mapping, and providing strong, up-to-date citations usually helps.

Sources cited

1maxaeo.ai
2llmreach.ai
3searchintel.tech
4werkhaus.ai
5business.adobe.com
6geoscout.pro
+4 more

Not namedAttensira is missing from this Perplexity answer.

Analyst · Opened the answersattensira.com stored Perplexity answer, read over the Attensira MCP · 4 Oct 2026 · 10 links

Why does a drop on one engine point away from your site?

A drop that shows on one answer surface and nowhere else usually means that surface changed, not your pages. Open it on its own with area=platform and a filter. The fix for a surface change is patience and a wider window; the fix for a page problem is a content change. The worst-first prompt ranking is what keeps a real loss on three prompts from being flattened by twenty that did not move.

What does a mention rate not tell you?

How the answer described you. A mention that criticises you counts exactly like a recommendation, because mention rate measures whether you were named, not how. That is a separate reading, on the Sentiment page.

When one prompt keeps showing up, it has its own recipe. If the movement was a rival's rather than yours, check whether a competitor is gaining. After running the chain twice by hand, schedule it.

Questions about a weekly loss check

What does a delta of real:false mean?

It means the change is not distinguishable from sampling noise at the sample size collected. It is not a decline, it is not a gain, and it should not be reported as either. Attensira returns the flag precisely so that a weekly report can be written to ignore movement it cannot prove.

Why does a rate come back as null instead of zero?

Null means the model was never queried in that window — the row is marked tracked:false — so there is no reading to average. Zero means it was queried and never mentioned you. Treating null as zero invents a measured absence that nobody measured.

How short a window is too short?

Each prompt is read at most once per model per day, so a seven-day window holds at most seven readings per prompt per model. Each reading is 1 sample on Starter and 3 on Growth and up, so that is at most 7 answers, or 21. A rate on that few answers moves several points when one answer changes.

Do I need write access for this recipe?

No. get_analytics and get_prompt are both read-only tools, so a read-only API key runs the whole chain, as does any signed-in connection. Nothing here spends credits.

Can I run this on a schedule instead of by hand?

Yes — that is what create_automation is for, and the weekly digest recipe covers it. Write the instruction to name the areas and windows explicitly and to ignore deltas where real is false.

Where do these facts come from?

Attensira's MCP recipes state that sampling runs at most once per prompt per model per day, so a plan executed today shows its earliest possible signal tomorrow.
docs.attensira.com · retrieved 2026-10-05
“Sampling is at most once per prompt per model per day, so a plan executed today shows its earliest possible signal tomorrow and a trustworthy one much later.”

Where to go next

Ask once a week where you lost ground. Stop when nothing is proven.