Prompt Engineering for Educational GPT
Updated: 5 days ago
Custom GPT Becoming Your Educational GPT
One of the biggest misconceptions about prompt engineering is the belief that adding more instructions automatically improves a Custom GPT.
In reality, every new instruction competes with the previous ones. Eventually, the model starts redistributing attention rather than improving its capabilities. You fix one problem and quietly create three more.
That is exactly what happened while I was building a new educational GPT for my CIPS IT Procurement Foundations training.
Originally, the educational GPT had a relatively simple role:
to reliably retrieve course content,
expose the uploaded knowledge,
avoid hallucinations,
explain procurement implications.
It worked surprisingly well. The GPT consistently returned structured topics, such as the Kraljic Matrix, Buygrid, Relational Contracts, and other concepts, directly from the knowledge file.
Then came the dangerous intent: “Why won't I add one more capability?” So, I decided to introduce a practical case analysis. On paper, it sounded like a quick win:
case introductions
student scoring (P.S. I implemented this option.)
coaching feedback
challenge questions
course topic linkage.
Rob Peter to Pay Paul: Endless Prompt Reengineering
The GPT did not isolate these instructions to “case mode.” Instead, it applied the new behavior everywhere.
As soon as I added concise coaching logic, the GPT began compressing normal topic retrieval too. When I told it to “briefly explain” cases, it started summarising the retrieved course content instead of presenting it faithfully.
The degradation was immediate:
related topics disappeared,
examples vanished,
external links were skipped,
nested bullets flattened,
formatting collapsed,
sections merged.
Nothing was technically “wrong” with the instructions themselves. The problem was their cumulative interaction.
At some point, the GPT begins optimizing against itself.
One instruction says: “Be concise.”
Another says: “Retrieve the full topic block.”
Another says, “Explain the concept.”
Another says, “Do not summarize.”
The model tries to satisfy all of them simultaneously, and the result becomes unpredictable.
Ironically, the final solution looked very similar to solving a procurement governance problem. We had to separate operational modes:
Topic Retrieval Mode,
Case Coaching Mode,
Assessment Mode.
Then another issue appeared: the knowledge files themselves.
Long PDFs, inconsistent formatting, duplicated explanations, and presentation-oriented layouts created semantic ambiguity in retrieval. GPT started blending sections because the source material wasn't retrieval-friendly.
The eventual fix was brutally simple: rebuild the entire knowledge base into rigid retrieval blocks with standardized structures, explicit delimiters, and normalized formatting.
In other words, the AI problem was not really an AI problem. It was an architectural problem.
That may ring a bell for some organizations rushing into AI adoption today.
Most failures are not caused by weak models. They are caused by poorly governed complexity layered on top of otherwise capable systems.
That's why it always amuses me when people post "use my prompts," which sounds to me like "skip a diagnosis, take my medicine."
P.S. If these kinds of practical IT procurement and AI governance topics are relevant to your work, my IT Procurement Foundations course (try this CIPS link) explores:
SaaS economics
TCO of technology services
Kraljic Matrix in IT sourcing
Information asymmetry and Game Theory in negotiations
Incomplete and relational contracts, among others.
November 2026 Update
Because custom GPTs are transitioning to plugins, I migrated this GPT to an HTML page on this portal. It is full of course material, interactive tools, and learning aids.
Modern IT procurement is no longer just about buying technology; it is about managing complexity instead of collapsing under its weight.
Comments