Introduction
A provost asks: "What is our four-year graduation rate for first-time, full-time students who started in fall 2022?" Paste that into a general AI assistant and you will get a confident answer. It will almost certainly be wrong, because the assistant does not have your data. It is generating a plausible-sounding number from the public web, from IPEDS averages, or from its training prior. None of those are your institution.
This is not a hypothetical gap. The whitepaper on data request workflows found that 91.2% of institutions report real challenges getting accurate answers to questions like this one, and IR staff already spend 40 to 60% of their capacity on ad-hoc requests trying to get it right using tools built for general use. A general AI assistant does not close that gap; it answers the same ambiguous question with more confidence and no more data access than the spreadsheet email chain it is replacing.
What General AI Gets Wrong in Higher Ed
- It does not have your data. General AI reads the public web; it cannot reach your SIS, your warehouse, or your IPEDS submissions.
- It does not know the domain. It cannot tell you whether "enrolled student" means headcount or FTE in this context, or whether "graduation rate" means four-year or 150% time.
- It cannot show its source. When it gives you a number, you cannot trace it back to a specific table, year, or calculation method.
- It hallucinates confidently. A number stated with the right cadence is not a number you can put in a dean's memo.
What Higher-Ed-Native AI Gets Right
- It reads your data. Clema connects to your SIS, warehouse, LMS, and files, alongside the federal datasets you pull on, and answers from those sources.
- It knows the domain. IPEDS definitions, accreditation terms, retention versus graduation, FTE versus headcount, cohort definitions; these are built in, not taught in month one.
- It shows its source. Every figure carries the table, the calculation method, and the year, with an audit trail for compliance.
- It is governed. Role-based access, read-only connections, BAAs, and a query audit trail mean security review is a one-day pack, not a multi-week audit.
A GRS Example: ChatGPT vs Clema
Ask a general assistant like ChatGPT, "What is our 150% graduation rate for the fall 2018 cohort?" and it will return a plausible-sounding percentage, usually without asking which cohort you mean. It has no way to know that IPEDS reports this figure through the GRS (Graduation Rate Survey) component, and that the GRS denominator is the adjusted cohort, not gross headcount at entry, meaning students who leave for reasons IPEDS excludes from the calculation are removed from the base before the rate is computed. A general assistant does not know your adjusted cohort size exists, so it cannot use it.
Ask Clema the same question and it pulls the GRS cohort size and completions from your actual IPEDS submission, applies the adjusted-cohort calculation, and returns the rate with the component name, the collection year, and the calculation shown. One assistant guesses at a number that sounds like a graduation rate; the other shows you the GRS math behind the number you are about to put in a board memo.
The Source Test
The fastest way to tell whether an AI is general-purpose or higher-ed-native is the source test. Ask your question, then ask: "Where did that number come from?" A general assistant will give you a paraphrase of where it thinks the number lives in the public record. A higher-ed-native assistant will give you the table, the field, the calculation, and the year, pulled from your actual data.
That distinction is the entire reason Clema exists. Higher ed answers need to be defensible to accreditors, cabinets, and boards. A sourced answer is defensible; a confident paraphrase is not. See how it works in a live demo on your data.
See a higher-ed-native AI on your data
Book a demo and ask Clema the same question you would ask a general assistant. The source test will tell you which one to trust.
Book a Demo