There’s a scenario that plays out more often than most HR teams realize.
An employee gets a referral to a specialist. Before booking the appointment, they ask their company’s benefits AI assistant whether the specialist is in-network. The assistant says yes. The employee books the appointment, goes to the visit, and two weeks later gets a bill for the full out-of-network rate.
What went wrong? The AI wasn’t lying. It gave a confident answer based on general information about how in-network referrals typically work. It just didn’t have access to your specific plan’s network, and it answered anyway.
That’s the problem citations are designed to solve.
What a citation actually does
When an AI assistant cites its source, it’s doing something more than footnoting an answer. It’s making a specific claim: this answer came from this document, this section, and you can verify it.
For the employee, that’s meaningful. “Your out-of-pocket maximum for in-network care is $4,500” is an answer. “Your out-of-pocket maximum for in-network care is $4,500, per your Summary Plan Description, Section 4.2” is an answer you can check. Those aren’t the same thing. One asks the employee to trust the assistant. The other gives them the tools to verify it themselves.
For HR, citations create something more valuable: accountability. A cited answer is tied to its source, which means your team can review recent answers and see exactly where each one came from. When something changes mid-year, you update the source document and the answers update with it.
For the organization, that traceability is what matters. An answer that names its source can be checked against the document it came from, which is categorically different from an inbox full of email replies or a document library that employees may or may not have read. Traceable doesn’t have to mean permanent: Tobie, for example, keeps Ask Tobie conversations only for a short retention window, with personal identifiers removed, and then deletes them.
The three failure modes of uncited AI
If you’re evaluating any AI tool for benefits communication, understanding how uncited systems fail is worth your time.
Hallucination. This is the most discussed failure mode in AI, and it’s the most dangerous in a benefits context. A general AI assistant is built to always produce an answer. When it doesn’t have the specific information it needs, it fills the gap with something plausible. The answer sounds confident and coherent. It may also be wrong.
In most contexts, a hallucinated answer is an annoyance. In benefits, it can mean an employee makes a coverage decision based on information that doesn’t reflect their actual plan. That has financial consequences, and those consequences tend to surface months after the original answer was given, long after anyone remembers what the assistant said.
Off-policy generalization. Even a well-calibrated AI can get this wrong. A general assistant trained on HR and benefits content knows how benefits typically work across thousands of employers. When an employee asks about their specific plan, the assistant might answer from that general knowledge rather than from your specific documents. The answer is accurate in the abstract and wrong for your plan. An employee who relies on it doesn’t know the difference.
No correction path. The third failure mode is structural. When an uncited AI assistant gives a wrong answer, there’s usually no way to know it happened until the employee surfaces the problem, sometimes much later. There’s no log. There’s no source to check. There’s no way for HR to review what was said and correct the record.
A system with citations addresses all three. The answer is bounded to your documents, so hallucination is constrained. The source is your specific plan, not general knowledge, so off-policy generalization is far less likely. And HR can review recent answers alongside their citations, so there is a correction path: a wrong answer points to the document that needs fixing.
“I don’t know” is a feature
This is worth saying directly, because it runs counter to how we usually think about AI.
The most important thing a benefits AI assistant can do is refuse to answer when it doesn’t have the information. Not deflect, not approximate, not generate something plausible. Refuse, and route the employee to a person.
A good source-grounded assistant has a clearly defined boundary. On one side: everything your approved documents cover. On the other: everything they don’t. When a question lands outside that boundary, the assistant says so explicitly. “I don’t have that information in your benefits guide. Please reach out to HR directly.” Then it stops.
That behavior is exactly what you want. In benefits, a confident wrong answer is worse than no answer. An employee who knows they need to call HR will call HR. An employee who received a wrong answer confidently will act on it, and find out it was wrong later.
The design philosophy matters here. General AI assistants are optimized to be helpful, which in practice means being answer-generating. A benefits assistant optimized for accuracy is built differently. Saying “I don’t know” is the correct output when the documents don’t support an answer. That’s not a limitation. It’s the point.
What this looks like for the employee
Both let you pay for care with pre-tax dollars.
An HSA is yours to keep and rolls over every year. An FSA is use-it-or-lose-it within the plan year.
All of the above sounds like infrastructure. From the employee’s perspective, it’s much simpler.
An employee asks a question about their dental coverage. The assistant gives a clear, plain-language answer and shows a small citation: “Source: Dental Plan Summary, Coverage and Limitations.” The employee can tap the citation to see the relevant section. The answer takes about fifteen seconds to get, it’s available at 10pm from their phone, and they can verify it themselves if they want to.
That experience is different in kind from a PDF, a portal, or an email to HR. The answer is immediate. The language is plain. The source is visible. The employee doesn’t have to wonder whether they’re getting information about their plan or about plans in general.
That’s what source-grounded AI looks like from the seat of the person using it.
What this looks like for HR
For the HR administrator, the experience is also different from traditional communication tools.
At any point, you can open the admin dashboard and review the questions employees have been asking recently, the answers they received, and the document sections those answers came from, for as long as the conversations are retained. You can see which questions were answered successfully and which ones the assistant couldn’t address. You can see the topics that are generating repeated questions, which often signals a gap in your documentation rather than a gap in the AI.
When a plan detail changes mid-year, you update the source document. The assistant’s answers reflect the update. You don’t have to rewrite FAQ content, send a corrective email, or hope that employees find the updated information on their own.
And when someone asks during open enrollment what employees are being told about their HSA limits, you can read recent answers and the document section each one cites, instead of guessing.
How to evaluate whether a system is genuinely source-grounded
Not every vendor who uses the phrase “source-grounded” means the same thing by it. Here’s how to check.
- Ask to see what happens when the assistant is asked a question that isn’t in your documents. A genuinely source-grounded system will say it doesn’t have that information. A system that uses the term more loosely may still generate an answer from general knowledge.
- Ask where each answer’s citation points. A real citation points to a specific section of a specific document. A vague reference to “your benefits guide” isn’t a citation in any meaningful sense.
- Ask what HR can review, and for how long. If the admin dashboard can’t show you recent conversations with their source citations attached, the accountability layer isn’t there. The vendor should also tell you plainly how long conversations are kept and what is removed from them.
- Ask whether your data is used to train models. A source-grounded system answers from your documents. It doesn’t need to learn from your employees’ conversations to improve its answers, and your employee data shouldn’t be feeding any training pipeline.
Benefits communication sits in a space where accuracy is genuinely high-stakes. The questions employees ask about their coverage aren’t hypothetical. They’re making real decisions about their healthcare, their finances, and their family based on the answers they get.
An AI assistant that cites its sources isn’t just a better product. It’s a fundamentally different kind of tool, one your organization can stand behind because you can check what it said, where it came from, and who can correct it if something goes wrong.
That’s what “trust me” never was.
Tobie’s AI assistant, Ask Tobie, answers from your approved benefits documents, cites its sources, and keeps conversations for HR review during a short retention window, with personal identifiers removed. To see how it works with your guide, talk with us.