# How to Run a Citation Gap Analysis

> The websites AI answers cite are now part of how buyers find you, and most belong to someone else. Here is how to turn them into a work queue: two kinds of buyer question, a verdict on every cited page, an owner per task, and an agent that rebuilds it monthly.

By Vlad Shvets, Partner @ Qvery · Published 2026-09-04 · Updated 2026-11-02 · 20 min read
Canonical: https://qvery.ai/blog/how-to-run-citation-gap-analysis/

Sooner or later someone asks you for budget "to get us onto the sites ChatGPT cites." It is a fair request, and it usually arrives with a list.

Buyers do ask assistants. In Forrester's 2025 survey of business buyers, **94% used AI** in their buying process, and buyers reported that AI tools help them "consider more vendors in less time."

The pages those answers read are now part of how your company is found, and most of them belong to someone else. The reports you already get cannot show them: in our research, [89.6% of the websites ChatGPT cited were not on Google's first page](https://qvery.ai/blog/ai-citations-vs-google-serp/) for the same buyer question.

A citation gap analysis finds those pages and sets them against where your company appears.

Finish the analysis as **a work queue**: each cited page gets a verdict, an owner, and a date. Rebuild it monthly because the answers move.

We ran the whole audit on email marketing software, a category crowded enough that every kind of website turns up. In our research, shortlist and evaluation questions went to ChatGPT and Google AI Mode in September 2026, and the cited pages of every site on the two resulting lists were opened on October 15.

- **7 of 15** cited sites held a task the company could do there
- **3 of 7** of those tasks surfaced only through evaluation questions
- **41.38%** of evaluation answers cited none of the shortlist list's sites

Source: Our research: email marketing software questions on ChatGPT and Google AI Mode, September 2026; cited pages opened October 15, 2026

You will build that queue with two prompts, then see how we handle the monthly work at Qvery.

One limit before the steps: it finds where your company is missing from the sources an answer cites. It does not tell you why an engine chose a source, and getting onto a page does not promise that the next answer names you.

## What You'll Need

**What you'll need**
- **Engines:** ChatGPT and Google AI Mode, opened signed out or in a browser profile with no search history.
- **Questions:** the ones your buyers ask, from first-call notes, the lost-deal reasons in your CRM, and prospects' emails before a quote.
- **Assistant:** one that reads a pasted document and runs a calculation on an uploaded file, and a spreadsheet beside it.
- **Owner:** one person who runs the audit and knows what your company can offer a publisher, a directory, or a creator.

Time: Asking and copying run a minute or two per answer, so 160 answers take 2 hours 40 minutes to 5 hours 20 minutes, over at least two days. The assistant steps took under two minutes in our run.

This builds the gap list, the queue, and the monthly routine around it. Writing the pitches, filming the videos, and tracing revenue back to AI answers are separate jobs that start once the queue exists.

## Step 1: Write The Questions Buyers Ask At Both Moments

**Shortlist questions** ask for names: which providers to look at, which suit a team like mine, which have a free plan. **Evaluation questions** ask for a judgment about a kind of thing: is it good enough for us, does it hold up in a busy month, is it worth the money.

Google Search Central says AI Mode may search related subtopics and sources to build a response. Keep shortlist and evaluation questions separate: Step 4 tests whether they lead to different pages.

Write every question in both shapes and keep the situation identical, so the only thing that changes is what the buyer wants back. These pairs come from our September run:

**The same situation, asked both ways: four pairs from the September questions**

| Shortlist shape | Evaluation shape |
|---|---|
| Which email platforms include a free plan | Do free-plan email platforms hold up well |
| Best email platforms for small marketing teams | Are email platforms good enough for small marketing teams |
| Recommended email marketing platforms for local charities | Do email marketing platforms work for local charities |
| Best email tools for online shops | Are email tools good enough for online shops |

Use **first-call notes** for evaluation questions and the lost-deal field in your CRM for the shortlist prospects chose instead.

Write the recorded question first, then its twin in the other shape, and mark the twin as yours. Then ask a salesperson whether a prospect would say it. **Twenty questions in each shape** is a workable start.

> 📖 **Cited And Named Are Two Different Lists** An answer cites the pages it read and names the companies it recommends. In September, ChatGPT called ActiveCampaign "Best overall for most businesses" when asked for the best email marketing platforms, and none of its six sources was ActiveCampaign's site. This audit works on the cited list; Step 3 also records who is named.

## Step 2: Ask Each Question More Than Once And Keep Every Source

Open both engines signed out, or in a browser profile with no search history. Google's AI Mode help page says answers can reflect past searches when personalization is on. OpenAI's search help page says ChatGPT web search works signed out.

In ChatGPT, open a new chat, select **View all tools**, then **Search**, and send the question. When the answer arrives, select **Sources** and copy each link. In Google AI Mode, go to google.com/ai, ask the same question, and copy the links shown with the answer.

> 📌 **Save Every Answer In The Same Shape** 
> - A first line that starts with Q: and carries the question, an id, the shape, the engine, and the date, like `Q: Are free email marketing platforms good enough | id: A014 | shape: evaluation | engine: ChatGPT | date: 2026-10-15`.
> - The answer, pasted as it appears.
> - The word Sources:, then one link per line, or the words "no sources".
> - An id for every answer (A001, A002, and on), never reused, because Step 4 counts answers by it.

Before you move on, check that every block ends in a Sources list or in the words "no sources". A block that ends any other way was cut short in the copying; ask the question again rather than guess what it cited.

Ask every question at least **twice on each engine**, on different days. When we asked the same question again, the second answer kept on average **40.68%** of the sites the first one cited on ChatGPT, and 40.75% on Google AI Mode. A site that shows up once may be gone the next time.

Twenty questions in each shape, two engines, and two asks each make 160 answers. The copying is **most of the hours** in this audit, which matters later when you decide what an agent should take.

Keep answers with no citations as rows marked "no sources". In September, **7.2%** of evaluation answers and **2.4%** of shortlist answers cited nothing; deleting those rows would hide that gap.

Two asks a month tell you which sites turned up this month. Which of them stay, and which come and go, shows only when the same questions are asked every day.

GEO Agent: https://qvery.ai/geo-agent/

## Step 3: Let An Assistant Turn The Answers Into Rows, Then Check Its Work

Paste every saved block into an assistant with this prompt, put your company's name where it says `<your company>`, and save the table it returns as worksheet.csv:

**The extraction prompt**

```
I saved some AI answers by hand and pasted them below. Each answer starts with a line that begins "Q:" and ends where the next "Q:" line starts. Turn them into rows for a citation worksheet.

Write one row for every source link listed under an answer, with these columns:
answer_id | question | shape | engine | date | cited_url | domain | page_title | named

Rules:
1. Copy each URL as pasted, then delete tracking parameters such as utm_source. Never write a URL that is not in the paste.
2. The domain is the site's host without "www." Keep subdomains: help.klaviyo.com stays help.klaviyo.com.
3. If an answer lists no source links, write one row for it with "no sources" in the cited_url column.
4. Take the answer_id, shape, engine and date from the "Q:" line. If one is missing, write "unknown". Do not guess.
5. In the named column, write "yes" only if <your company> appears in the answer text itself, otherwise "no". A source title or a link label does not count.
6. Give me the table only, then one line saying how many answers you read and how many rows you wrote.

The answers:
```

I tested this in Claude Code on three September answers, with ActiveCampaign as the test name. It returned 18 rows, including one "no sources" row; **every URL matched** the paste. Here are the first rows with some columns omitted:

**The first rows the extraction prompt returned on three saved answers**

| answer_id | shape | engine | cited_url | named |
|---|---|---|---|---|
| A001 | shortlist | ChatGPT | getomnichannel.com/email-marketing/best-email-marketing-software/ | yes |
| A001 | shortlist | ChatGPT | hubspot.com/pricing | yes |
| A002 | evaluation | ChatGPT | hubspot.com/pricing/marketing?tier=starter | yes |
| A003 | shortlist | Google AI Mode | no sources | no |

It removed the tracking tag ChatGPT adds to its links and kept the parameter that changes the page, HubSpot's `?tier=starter`. It marked ActiveCampaign as named in the first answer, the one whose sources never included ActiveCampaign's site.

Three answers prove the prompt runs. They do not prove it never slips on the hundredth, so four checks stay:

- The row count equals the links you pasted, plus one row for each answer with no sources.
- Every URL in the table appears in your paste, apart from the tracking parameters the prompt removes. One that does not is invented; delete the table and run it again.
- One row in ten opens to the page its title describes.
- You read the named column yourself for five answers, because it is the one column that takes reading rather than copying.

## Step 4: Build A Separate Working List For Each Kind Of Question

A frequently cited site may add no answers beyond those your list already covers. Choose sites by the answers they add instead.

Ranked by citations alone, the September shortlist sites needed **15 rows** to reach four fifths of their answers. The rule below needed **eight**.

Take the site cited by the most answers and set those answers aside. From the answers left, take the site cited by the most of them, and keep going until the list covers **four fifths** of the answers that cited anything.

Four fifths keeps the list short enough to open every page; the pool just below it is the next place to look.

![Three steps building the shortlist list: Mailchimp first, then YouTube, then GetOmnichannel instead of Brevo, with a loop back until four fifths of the answers are covered.](https://qvery.ai/blog/how-to-run-citation-gap-analysis/illustration-how-the-list-is-built.webp)

*Watch the third step: the pick goes to the site in the most remaining answers, not the most answers.*

Do it once per kind of question, never on the two pooled. This prompt runs it on the worksheet from Step 3, uploaded as a file:

**The working-list prompt**

```
The file worksheet.csv is a citation worksheet: one row per source an AI answer cited, and an answer_id that is the same on every row from one answer. Rows that say "no sources" are answers that cited nothing; leave them out of everything below.

Do this separately for each value in the shape column:
1. Count the answers that cited at least one source. That count is the base.
2. Build the working list. Pick the domain cited by the most answers, then set aside every answer that cites it. Repeat on the answers that are left, each time picking the domain cited by the most of them (break a tie alphabetically), and stop as soon as the answers set aside reach four fifths of the base.
3. Next to each domain, show the running share of the base covered once it is added.

Then, for each shape's list, show the share of the OTHER shape's base that cites at least one domain on it.

Use code for every count. Show the two lists next to each other and mark the domains that appear on both.
```

On the September worksheet it returned these two lists, each site in the order the rule added it, with the share of that kind of question's answers covered once the site was in:

**The two working lists, in the order the rule added each site**

| # | Shortlist list | Covered | Evaluation list | Covered |
|---:|---|---:|---|---:|
| 1 | mailchimp.com (both) | 28.69% | youtube.com (both) | 18.97% |
| 2 | youtube.com (both) | 54.1% | mailchimp.com (both) | 36.21% |
| 3 | getomnichannel.com (both) | 60.66% | beehiiv.com (both) | 45.69% |
| 4 | stackfyi.com | 65.57% | proton.me | 54.31% |
| 5 | hubspot.com | 69.67% | apiscout.dev | 59.48% |
| 6 | lettr.com | 73.77% | fitsmallbusiness.com | 64.66% |
| 7 | zapier.com | 77.87% | mailerlite.com | 68.97% |
| 8 | beehiiv.com (both) | 80.33% | litmus.com | 72.41% |
| 9 |  |  | aicpa-cima.com | 75% |
| 10 |  |  | getomnichannel.com (both) | 77.59% |
| 11 |  |  | help.klaviyo.com | 80.17% |

The list built from shortlist questions reached **58.62%** of the evaluation answers, against 80.33% of its own. Put the other way, **41.38%** of the evaluation answers cited none of the sites a shortlist-only team would be working on.

The same gap held when we built each engine's lists separately:

**The Shortlist List Misses Evaluation Answers On Both Engines** (% of answers that cited a source)

The list built from shortlist questions reached 80.33% of its own answers but 58.62% of the evaluation answers, and the drop held on each engine alone: 49.32% on ChatGPT and 60.47% on Google AI Mode.

| Label | Shortlist answers, the list's own | Evaluation answers |
|---|---:|---:|
| Both engines | 80.33% | 58.62% |
| ChatGPT | 81.33% | 49.32% |
| Google AI Mode | 82.98% | 60.47% |

Share of answers citing at least one site on the list built from shortlist questions: first the shortlist answers it was built from, then the evaluation answers. Each engine row uses a list built from that engine's answers alone. September 2026. Source: Our research: email marketing software questions on ChatGPT and Google AI Mode, September 2026

These are one category's numbers in one month. In your own sheet, look for the drop from a list's own coverage to its reach into the other kind of question, and how big it is.

> ⚠️ **The Bottom Of Each List Is A Tie** 
> - beehiiv.com closed the shortlist list because it comes first in the alphabet among seven sites on the same count.
> - Treat the last rows as a pool and let the page check choose.
> - Whatever the tie order, the shortlist list stayed under two thirds of the evaluation answers: 50.0% to 58.62% with the engines together, never above 61.64% on either engine alone.

Keep subdomains separate: help.klaviyo.com is a help center; klaviyo.com is a homepage. They need different work.

### A Site-Type Report Would Call These Two Lists The Same

Sorting the sources by type (vendor sites, roundups, review directories, forums, video) is the obvious shortcut, and on these two lists it hides the split.

**The Mix Of Site Types Barely Moves Between The Two Kinds Of Question** (% of answers that cited a source)

Vendor sites, roundups, review directories and forums appeared at similar rates for both kinds of question, while half the sites on the shortlist list were missing from the evaluation list.

| Label | Evaluation questions | Shortlist questions |
|---|---:|---:|
| Vendor sites | 80.17% | 75.41% |
| Roundups and best-of pages | 43.1% | 50.82% |
| Video | 18.97% | 25.41% |
| Agencies and consultants | 18.1% | 23.77% |
| Review directories | 14.66% | 15.57% |
| Community forums | 10.34% | 11.48% |

Share of the answers that cited any source in which at least one site of each type appears. A single answer cites several types, so the shares do not add to 100. Engines pooled. Source: Our research: email marketing software questions on ChatGPT and Google AI Mode, September 2026

A type summary tells you to pitch roundups. It cannot say which roundup, and in this category the roundups split by question: stackfyi.com and zapier.com sat only on the shortlist list, fitsmallbusiness.com and apiscout.dev only on the evaluation list.

## Step 5: Open The Cited Pages And Give Each Site One Of Four Verdicts

Open each cited page, check whether it includes your company, and assign one of the four verdicts below. Record what on the page supports your choice.

A page that already includes you **is not finished**: read what it says about you. If the price, the plan, or a feature is out of date, the task is a correction sent to whoever runs the page; if it is right, note it and move on.

A site whose pages offer different routes gets one row per page.

**The four verdicts, and what each one needs to see on the page**

| Verdict | What you must see on the page | What your team does |
|---|---|---|
| Contribute | A route you control: a submission form, or a channel of your own | Use it, with one owner and one date |
| Earn | An editor who decides: a stated method or editorial standards | Pitch something the page lacks: data, a test account, a correction |
| Competitor's page | A rival's own page, help center, or comparison | Note the question it answers that your site does not |
| Watch | No route: a standards body, a neighboring product | Log it and look again next month |

We opened these cited pages on October 15, 2026, judging them as a hypothetical email platform absent from both lists:

**All 15 sites from the two lists, read as a platform that is on neither list**

| Site (list) | What the cited page showed | Verdict |
|---|---|---|
| youtube.com (both) | Creators' comparison videos, such as Stewart Gauld's top five for small business | Contribute |
| mailchimp.com (both) | A vendor's homepage and pricing | Competitor's page |
| getomnichannel.com (both) | A ranked roundup with a stated method, updated October 5, 2026 | Earn |
| beehiiv.com (both) | A vendor's own comparison post | Competitor's page |
| stackfyi.com (shortlist) | A tools directory with a "Submit Tool" link | Contribute |
| hubspot.com (shortlist) | A vendor's homepage, pricing, and security page | Competitor's page |
| lettr.com (shortlist) | A roundup that discloses "Lettr is our product" | Competitor's page |
| zapier.com (shortlist) | An editorial roundup: "We independently review every app we recommend" | Earn |
| proton.me (evaluation) | A secure email provider's security page | Watch |
| apiscout.dev (evaluation) | An API directory with a "Submit API" link | Contribute |
| fitsmallbusiness.com (evaluation) | A roundup with a published methodology and editorial standards | Earn |
| mailerlite.com (evaluation) | A vendor's pricing and free-plan pages | Competitor's page |
| litmus.com (evaluation) | A post by an outside contributor; no published submission route | Earn |
| aicpa-cima.com (evaluation) | The standards body's SOC 2 page | Watch |
| help.klaviyo.com (evaluation) | A vendor's help center | Competitor's page |

YouTube is Contribute because the route is your own channel: a video of yours on the same question is a new source beside the creators', not a place inside their videos.

**Seven of the 15 rows** held a task on the site itself, and **three of those seven** exist only because the evaluation questions were asked: apiscout.dev, fitsmallbusiness.com, and litmus.com. A gap list built from shortlist questions alone would have sent the team to stackfyi.com and zapier.com and never to them.

Two of the seven come with a condition to check first. apiscout.dev lists APIs, so it fits only a platform with a sending API, and litmus.com publishes no submission route, so the pitch starts as a question to its editor.

![Two panels: tasks found by shortlist questions and tasks found by evaluation questions. Both share YouTube and GetOmnichannel; three tasks appear only on the evaluation side.](https://qvery.ai/blog/how-to-run-citation-gap-analysis/illustration-where-the-work-came-from.webp)

*Compare the bottom of each panel: the evaluation side holds three tasks the other never reaches.*

The six rivals' pages point at work on **your own site**: check whether you answer the pricing, support, and comparison questions they answer.

The two Watch rows point the same way. The AICPA and CIMA SOC 2 page was cited on the evaluation question about SOC 2, and HubSpot's own security page on the shortlist one.

If buyers in your category ask about a standard you meet, a plain page on your own site that says so is the task.

Google Search Central says AI Mode supporting links must be indexed and eligible for a Search snippet. OpenAI's crawler documentation says opting out of OAI-SearchBot excludes a site from ChatGPT search answers.

Ask whoever runs your website to confirm that neither is blocked.

Three of the seven work rows carry an advertising link (getomnichannel.com, stackfyi.com, and apiscout.dev), and stackfyi.com and apiscout.dev name each other as sister sites. On GetOmnichannel's roundup the link sits in the header, above the ranking it publishes:

![The GetOmnichannel page Best Email Marketing Software in 2026, with an Advertise your product button in the header, the author's name, and a last-updated date of October 5, 2026.](https://qvery.ai/blog/how-to-run-citation-gap-analysis/getomnichannel-roundup.webp)

*Look at the top right: the advertising link sits on the same page as the ranking.*

Buying advertising is **a separate decision** with a price on it. The verdict records that the site sells advertising beside its editorial; whether to buy any is the owner's call.

If the lists hold little work in your category, open the pool just below the cutoff as well. The sites tied with the last picks, such as techradar.com, capterra.com, and stackbriefly.com on the shortlist side here, are the next candidates, judged the same way.

## Step 6: Put An Owner, A Date, And A Number On Every Task

Whoever owns pipeline signs the worksheet off. Each Contribute or Earn row gets a name and a date. A Competitor's page or Watch row that points at a page your own site lacks becomes an **own-site task** with an owner; the rest get one line, "check next month".

**Write the reason** beside every verdict, in a sentence. It is what lets someone else, or an agent, apply the same judgment next month.

Prioritize rows that reach the most answers for the least effort. In this hypothetical queue, each task is due before next month's audit, except the robots.txt check, due this week:

**The finished queue for the hypothetical company**

| Site | What to do | Owner |
|---|---|---|
| youtube.com | Publish your own walkthrough; offer cited creators a test account | Content lead |
| getomnichannel.com | Ask to join the deliverability benchmark the roundup runs | Marketing lead |
| stackfyi.com | Read the form's requirements, then use Submit Tool | Marketing lead |
| zapier.com | Pitch the editor if your free plan is missing from the roundup | Marketing lead |
| apiscout.dev | If you offer a sending API, submit it through Submit API | Product lead |
| fitsmallbusiness.com | Pitch the editor against its published methodology | Marketing lead |
| litmus.com | Ask whether the blog takes a post on preference centers | Content lead |
| Your security page | Write it: SOC 2 questions cited a standards body and a rival | Product lead |
| Your robots.txt | Confirm Googlebot and OAI-SearchBot are allowed | Web lead |

Then decide what you will count, and what each count can and cannot tell you:

**What to count after each audit, and what each count tells you**

| What to count | Where it comes from | What it tells you |
|---|---|---|
| Hours per audit | The owner's own log | What the audit costs, and what an agent would save |
| Rows the assistant got wrong | The Step 3 checks | Whether the extraction can run with lighter checking |
| Tasks done by next month | The worksheet's date column | Whether anyone is working the queue |
| Target pages that now include you | Each Contribute or Earn page, opened again | Whether the work landed on the page |
| Answers that name you | The named column from Step 3 | A trend, not proof that the work caused it |
| Your own pages on each list | Next month's two lists | Whether the engines now cite you directly |
| What a buyer says they read | The first sales call | The closest link from this work to revenue |

In Gartner's survey of 645 B2B buyers, 45% used generative AI during a recent purchase, mostly for vendor information, and **69%** prefer to validate AI-generated insights with a sales rep.

So ask on that call what the buyer read before they called, and write it down.

None of these counts proves the work made money. A citation and a sale sit far apart, and the question on the first call is the nearest link between them; it rests on what a buyer remembers.

## Have An Agent Draft Each Month's Queue For The Owner To Approve

An agent can repeat the extraction, arithmetic, and comparison each month. The owner still judges new pages and approves the work.

Use the daily answer and citation records from [the GEO Agent](https://qvery.ai/geo-agent/), or the answers your team saved by hand, as the inputs to this monthly brief.

The agent runs six steps a month, written here so you can brief whoever builds it:

1. **Read the month's records** The month's answers and their sources, from the GEO Agent's records or the blocks your team saved; last month's worksheet with every verdict and its reason; the month's first-call notes and lost-deal reasons from the CRM; and your own website.
2. **Run on the first working day of the month** One run a month, on the same questions, so this month's lists compare with last month's.
3. **Rebuild both lists by the same rule** Four fifths of each kind of question's answers, with the ties shown, then a comparison with last month: sites that joined, sites that left, and sites whose cited page changed.
4. **Carry every verdict that still holds** A site keeps last month's verdict while the engines cite the same page, and every carried page goes back to the owner to reopen once a quarter, because a page can change at the same address. A new site, or a known site cited on a new page, goes to the owner marked "to open", with the page links and the answers that cited them.
5. **Draft the own-site gaps and the pitches** For each rival's page or Watch row, look for a page on your own site that answers the same question and note what is missing. For each Earn row the owner has approved, draft a pitch against the page's own stated method.
6. **Hand the owner one queue** Carried rows, rows to open, rows that left, and drafts, in one sheet. The owner rules on every new row and every draft.

> ⚠️ **What The Agent Never Does** 
> - Ask ChatGPT or Google AI Mode anything itself: it works from records you already hold.
> - Open a third-party site on its own: it lists the pages, and a person opens them.
> - Send, submit, publish, or pay for anything the owner has not approved.

Count it the way you counted the first audit. The owner's hours on the monthly review sit beside the hours the hand-run audit took, and the rows the owner corrects are **the agent's error count**.

## How Qvery Keeps Your Citation Queue Moving

We begin your citation audit with the GEO Agent's records. It prepares questions using what you sell, the industry you serve, and the competitors you face.

It runs those questions every day. ChatGPT and Google AI Mode are its two destinations, with countries chosen by you. It retains responses and their complete citation lists.

You can inspect sources by country or topic and compare sentiment with rivals. Visibility and competitor share of voice sit alongside that evidence. We go through the findings together, then handle corrections and content work on the pages the audit identifies.

When rebuilding the queue takes too much time, we learn how your owner reaches each verdict and create a custom agent for that monthly routine. It runs on autopilot in your existing systems, preparing changed rows and pitch drafts for approval.

Your queue owner learns to review the agent's output as we get the first version running within two weeks. We tally audit preparation hours saved and row errors avoided each week, using the manual audit as the comparison.

Your worksheet gives us the decisions the agent must learn to carry forward.

Have Us Maintain Your Monthly Citation Queue: https://calendly.com/qvery-vlad/30min

## Compare The Second Audit With The First

Run the second audit a month after the first and lay the two worksheets next to each other. If the top four rows of each list held and the hours stayed small, keep doing it by hand.

If the rows churned and the copying grew, an agent's build and review is worth pricing against those hours.

Either way, keep the first month's verdict column with its reasons. It is the one part of the audit nobody can rebuild from the answers, and it is the rulebook an agent drafts against in month two.

The same decision about repeated work applies to the call notes your salespeople enter into the CRM.

Carry Buyer Questions From Sales Calls Into Your CRM: https://calendly.com/qvery-vlad/30min

## Frequently asked questions



### What is a citation gap analysis?

A citation gap analysis compares the websites AI engines cite for your buyers' questions with the pages that include your company. The useful result is a work queue: which pages need attention, what your team can do there, and who owns each task.

### Is being cited the same as being recommended?

Being cited and being recommended are different. In our September research, ChatGPT named ActiveCampaign its best overall email marketing pick while citing six sources, none of them ActiveCampaign's site. Keep a separate column for whether your company is named in the answer itself.

### How many questions do we need, and how often should we ask them?

Twenty in each shape is a workable start, on both ChatGPT and Google AI Mode, with each question asked at least twice on different days. Answers move between asks: a second ask of the same question on ChatGPT kept on average 40.68% of the sites the first answer cited.

### How often should we rerun the analysis?

Rerun the analysis monthly using the same questions so you can compare lists. Open new or changed cited pages, carry forward verdicts that still hold, and reopen carried pages quarterly because their contents can change at the same address.

### Can we run this with a spreadsheet and ChatGPT alone?

You can collect answers by copying and pasting, then use the two prompts here to extract rows and build lists. A person opens the cited pages and assigns verdicts. Copying takes more time as the question list grows.

### Can an agent run the whole audit?

It can run the repeating part: rebuilding the two lists from the month's records, comparing them with last month's, carrying the verdicts that still hold, and drafting own-site gaps and pitches. The verdict on a new page, and anything sent, submitted, or paid for, stay with a person.

### How do we decide which cited websites are worth our team's time?

Open the cited page, not the homepage, and look for a route: a submission form, an editor with a stated method, or nothing at all. Rows with a route become tasks with an owner and a date. Rivals' pages and standards bodies get logged, unless they show a page your own site is missing.

### Should we pay for advertising on a site that ranks vendors?

That is a separate decision, made by whoever owns the budget, with the price in front of them. The audit only records that a site sells advertising next to its editorial, so the owner can weigh it against the rows that cost nothing but time.

### Does this work outside software, for a law firm or a logistics company?

The steps carry over; what you test in your own category is whether the two kinds of question pull different sites. Your lists will hold other sites, such as directories, associations, and trade press, and the same four verdicts sort them.

### Why build separate shortlist and evaluation lists?

A buyer asking which providers to consider may get different sources from one asking whether a type of product is good enough. In our September example, the shortlist list reached 58.62% of evaluation answers. Build both lists before deciding which pages deserve work.

### What should we do with an answer that cites nothing?

Keep it in the worksheet with "no sources" in the cited URL column. There is no cited page to act on, but retaining the row lets you compare how often this happens across months.

### What if a cited page already includes our company?

Read the description before closing the task. An incorrect price, plan, or feature needs a correction sent to the page owner; an accurate description can be logged without further work.

### How do we know whether the audit is worth repeating?

Log the hours spent, extraction errors corrected, tasks completed, and target pages that now include you. Ask buyers on the first sales call what they read before contacting you. These records help you judge the work, but a change in citations alone does not prove that it generated revenue.