Keeping an Admissions AI Agent's Knowledge Base Current

An admissions agent is only as accurate as its knowledge base

An admissions chatbot's knowledge base goes stale exactly where mistakes hurt: fees, points requirements, entry routes and dates. Keeping it current is an organisational job more than a technical one: one source of truth, an owner for each content type, a review rhythm that follows the admissions cycle, and a short route for urgent changes.

A note on method: no paid keyword-volume tool was available, so this article was scoped from public search results. Every external source cited was opened. Nothing here comes from Skolbot or its customers, and we state no figures beyond sourced ones.

Why the knowledge base ages faster than the website

In a retrieval-based set-up, the agent pulls passages from an index of your documents and writes its answer from them. The original retrieval-augmented generation paper presents this as a way to reach external knowledge and keep it updated. Change a document and the answers can change, with no retraining.

The flip side: if last year's prospectus stays indexed next to this year's, the agent can quote either with equal confidence. Our guide to chatbot hallucination guardrails covers invented answers; this one is about answers that were right last cycle and are wrong now.

Typical causes:

• Duplicates: an old PDF, a blog post, an exported FAQ. Nothing says which one counts.
• Orphan copies: a fees table pasted into a working document nobody maintains.
• Changes outside the process: a revised entry requirement agreed at an academic council and never updated in the index.

Set the source of truth and a document hierarchy

For each kind of information, decide which document is authoritative. The agent should read that one, not a copy.

Add a conflict rule: if two passages disagree, the agent does not pick one. It flags the clash to your team and, meanwhile, offers the applicant a human adviser.

A review rhythm tied to the Irish cycle

Most Irish undergraduate applications go through the CAO, which has its own timeline, and points for entry depend on Leaving Certificate results and on the year's demand. Colleges also take applicants directly for some courses, for mature students and for further education routes. State on your own pages which route applies to each course, and explain how your points or entry requirements work, before the agent talks about them. Never let the agent predict next year's points.

1. Before applications open: a full review of fees, courses, entry requirements, supporting documents and process pages. Archive anything tied to the previous year.
2. During the application period: short, frequent checks on dates, routes and any change to course codes or requirements.
3. Offers and acceptance: check messages on reply dates, deferral, deposits and accommodation. These are the questions applicants worry about most.
4. Leaving Certificate results and after: offer rounds move quickly, so ownership and turnaround matter most here. If you cannot keep vacancy information current, point to the live page and a person. See also our note on keeping admitted students engaged.
5. After the start: retire what expired and review the questions handled badly. For the initial corpus, see how to train an AI chatbot on your school's data.

Owners, versions and traceability

Content without an owner goes stale. Three roles are enough for most colleges:

• Content owner (fees, courses, student services) fixes the source and declares the change.
• Knowledge-base manager reindexes, removes the old document and checks the result.
• Approver, usually the head of admissions, signs off anything that commits the institution: fees, requirements, dates.

For each document keep an upload date, an expiry or next-review date, the entry year it covers and the owner's name. A change log answers "why did the agent say that yesterday?". Check that your platform supports this metadata and rollback; do not assume it.

Expired documents should be removed from the index, not merely down-weighted. If you must keep the history, archive it outside what the agent can search.

When a date or requirement changes overnight

A moved closing date, a cancelled open day, a corrected fee: these arrive mid-cycle. Prepare a short route:

1. The owner corrects the source page.
2. The manager reindexes and removes the old version the same day.
3. A test question on the changed point confirms the new answer.
4. Meanwhile, a temporary instruction ("for this topic, hand over to an adviser") can suspend the automatic reply. Confirm your tool allows it before you need it.
5. The log records the time of the fix.

Set your own target for how long a wrong fact may circulate; the aim is that it never survives a working day.

Test freshness instead of hoping

Build a small question set whose correct answer changes over time: "When do applications close for next year?", "What are the fees for the BA?", "Do I need Higher Level Maths?". After every significant update, rerun it and mark each answer correct, cautious or out of date. Only the first two pass.

Add trap questions about last year, or about a figure that no longer exists. A good answer names the entry year and points to the source page. For the wider context, see the guide to AI chatbots in student recruitment.

Personal data and admission decisions

Keep applicant files, results and emails out of the knowledge base; it should hold publishable information. Ireland is in the EU, so data protection falls under EU rules supervised by the national Data Protection Commission; agree retention and handling with your data protection officer.

The EU AI Act applies directly here and lists systems intended to determine access or admission to educational institutions as high-risk. An information agent answering from published pages is not automatically in scope, but it moves closer if it ranks or screens applicants. So no screening rules belong in the knowledge base. Check the current application dates of the Act with your legal adviser.