Residents were asking AI answer engines for clinic schedules, eligibility rules, and compliance steps. The department's deep menus and legacy PDFs meant those engines invented hours, or left the agency out of the answer entirely. This is a composite scenario built to demonstrate the GEO method, not a real client engagement.
By Matt·Updated June 9, 2026•Hypothetical scenario
Case profile
Industry
Government agencies
Organization size
Mid-sized regional public health department
Team size
2 communications specialists (small team)
Difficulty
Moderate
Estimated timeline
Variable
Figure 1 — profile of the hypothetical agency in this case study
The situation
What problem was the agency facing?
Residents were using AI answer engines to find community services, clinic schedules, and compliance rules. The agency was often missing from those answers, or described wrongly.
The agency's information sat behind deep menus and inside old PDFs. As a result, AI search tools invented opening hours, or skipped the agency altogether.
The challenge
People used to search in keywords: "city health clinic hours." Now they ask full questions, with several conditions at once. A realistic example: "I don't have insurance and my child needs school vaccines before Friday, where can I go near the downtown transit center?"
Traditional SEO aims to rank a page, using keywords and links. GEO works differently. It feeds an AI's knowledge graph, which is a map of how concepts, organizations, and places connect to each other. An engine needs to see clear links between your address, who qualifies for a service, when you are open, and what you have authority over. When it cannot see those links, it leaves you out of the answer rather than risk telling someone something wrong.
What citizens are asking AI
"Which county clinics offer free ambient air quality testing kits, and what do I need to bring to prove residency?"
"I want to open a small catering business from my home kitchen. What are the exact permitting steps and fees required by the local health department?"
"Are there any active water boil advisories or food safety recalls issued by the regional government right now?"
Why this matters: Faced with a multi-part question, the model writes a fresh answer from the strongest connections it can find. If your public information is stuck in an image of a table, or buried in legal language, it cannot find those connections. It will point the resident somewhere else, or repeat instructions that are out of date.
Baseline GEO audit
We ran the same set of test questions against each major AI engine, to see how well they could find and use the agency's public health information. Ratings are illustrative, not measured.
Category
ChatGPT
Gemini
Claude
Perplexity
AI visibility
Moderate
Weak
Weak
Moderate
Entity clarity
Moderate
Moderate
Weak
Strong
Program/service pages
Weak
Missing
Missing
Moderate
FAQ content
Weak
Weak
Missing
Weak
Trust signals
Strong
Strong
Strong
Strong
Expert profiles
Missing
Missing
Missing
Missing
ChatGPT
AI visibility
Moderate
Entity clarity
Moderate
Program/service pages
Weak
FAQ content
Weak
Trust signals
Strong
Expert profiles
Missing
Gemini
AI visibility
Weak
Entity clarity
Moderate
Program/service pages
Missing
FAQ content
Weak
Trust signals
Strong
Expert profiles
Missing
Claude
AI visibility
Weak
Entity clarity
Weak
Program/service pages
Missing
FAQ content
Missing
Trust signals
Strong
Expert profiles
Missing
Perplexity
AI visibility
Moderate
Entity clarity
Strong
Program/service pages
Moderate
FAQ content
Weak
Trust signals
Strong
Expert profiles
Missing
The audit showed a clear pattern. All four engines treated the agency as trustworthy, which the .gov domain earns automatically. None of them could reliably pull out specific operational details. ChatGPT and Perplexity sometimes retrieved high-level facts by browsing the live site, but missed the specifics of individual programs. Claude and Gemini surfaced no clinical programs or local FAQ content at all. The trust is already there. The site's structure is what stops these engines turning that trust into a useful answer.
Key issues found
Three structural gaps explained why a trusted .gov domain still failed to surface actionable answers.
1
"Invisible" PDF data caches
Eligibility rules, sliding-scale fees, and permit processes all lived inside long, untagged PDFs. AI engines can read text in a PDF, but they struggle to follow relationships across a complex layout. An eligibility table stuck in a PDF rarely gets connected back to the agency itself, so the information is effectively invisible when an engine writes an answer.
2
Ambiguous, promotional headings
Service pages carried creative headings like "Nurturing Our Community's Brightest Futures" instead of saying what the service is. AI engines lean on headings to work out what a block of text contains. A heading with no concrete nouns leaves the model guessing whether the section describes a medical service, an article, or a mission statement.
3
Total lack of backend structured data
The site had no structured data at all: nothing in the code to state its locations, service types, or jurisdiction. Without it, a model has to guess these details from ordinary text. When a page lists several phone numbers and addresses with no markup saying which belongs to which branch, engines tend to merge them, or drop them rather than risk being wrong.
Recommended GEO improvements
Targeted, editorial-first changes the lean team could execute inline within their existing CMS.
Transforming text for direct answers
Before — traditional marketing copy
"Welcome to the portal of our Environmental Health Division. It is the core mission of our dedicated team of regional inspectors to ensure that our beautiful community enjoys the highest standards of culinary safety and sanitation across all of our local dining establishments. If you have recently visited an eatery within our administrative boundaries and encountered conditions that you believe did not align with optimal public wellness or regulatory benchmarks, we provide mechanisms to register these occurrences for internal review."
After — GEO-optimized copy
How do I report a restaurant health violation in [Region Name]? You can report a restaurant health violation directly to the Regional Public Health Department by calling 555-0199 or filling out our online complaint form. Cost: Free of charge. Anonymity: You may file your report anonymously. Response Time: An environmental health inspector will conduct an on-site facility inspection within 48 business hours of receiving your complaint.
Why we chose it: These models favour text that answers a question directly. A short, factual summary at the top of a service page is easy for a model to quote and cite word for word.
Implementing GovernmentService schema
Add JSON-LD structured data to every core program page, naming the service type, the provider, and the area served. Schema removes the guesswork. It states the agency's location, hours, and jurisdiction in a form the engine reads directly, rather than inferring from prose.
Before — standard HTML
HTML
<div class="clinic-info">
<h2>Downtown Health Center</h2>
<p>Come see us at 100 Main Street for immunization
walk-ins Monday through Wednesday, 8 AM to 4 PM.</p>
</div>
A third recommendation (transitioning PDF data into high-density FAQ blocks) rebuilds buried regulatory, permitting, and service-delivery workflows directly on the website as structured web pages built around explicit questions. Web pages parse cleaner in AI scraping loops than embedded document formats, turning unindexed data into a highly crawlable format LLMs can instantly pull from.
Common questions
Do we need permission from IT to add structured data to our pages?
Usually yes, but the change is small. Structured data is a block of code that sits in the page template and does not alter how the page looks. Framing it that way, as a template change rather than a redesign, tends to move faster through an approval queue than a request that sounds like a website project.
Our forms and eligibility rules are legally reviewed. Can we still simplify the wording?
You can usually add without changing. Leave the legally reviewed language exactly as it is, and put a short plain-language summary above it. The summary is what an AI engine will quote; the reviewed text stays available underneath for anyone who needs the precise wording.
We publish everything as PDFs because that is our records process. What do we do?
Keep the PDF as the record and publish the same information as an ordinary web page. The PDF continues to serve your archival and accessibility requirements, while the HTML version is what search and AI tools can actually read and cite.
How often should a public agency recheck its AI visibility?
Quarterly for a general check, and immediately after any change to hours, locations, eligibility rules, or emergency guidance. Residents ask AI tools about exactly those details, and outdated answers about a public service cause real problems.
Continue learning
Related guides that map directly to the three recommended actions above.