Concern 131 · Working draft · editorial review in progress
Prompt convention lock-in
Prompt-convention lock-in occurs when a workflow depends heavily on one model's particular way of receiving or responding to instructions.
Understanding the concern
Teams may build long prompts around formatting habits, special labels, or behavior that another system does not share. Changing providers or versions can then require more work than the simple interface suggests.
This is not always an intentional barrier. Some differences reflect design choices, and prompts can sometimes be adapted easily. The concern is whether the team understands and tests its dependence instead of assuming instructions are universally portable.
An example
A set of office procedures uses shortcuts that only one assistant understands, so a replacement needs extensive retraining.
Illustrative unless identified as a documented case.
Words in plain English
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
- Prompt
- The instructions or information given to an AI to guide its response.
- Interface
- The controls and displays people use to interact with software, such as buttons, menus, and chat windows.
- Lock-in
- Dependence on a tool or provider that is difficult or costly to leave.
Evidence and its limits
Supports hidden dependencies and downstream model reuse; portability must be evaluated for the actual workflow.
Sculley and colleagues · NeurIPS 2015 · Research framework
Hidden Technical Debt in Machine Learning Systems ↗ (opens in a new tab)Explains maintenance problems, hidden dependencies, feedback loops and changes in machine-learning systems.
Bommasani and colleagues · 2021 · Research report
On the Opportunities and Risks of Foundation Models ↗ (opens in a new tab)Discusses shared model dependencies and homogenization; not a current market-share estimate.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Which parts of this workflow depend on one provider's quirks rather than a clear task description?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Humility
Humility means recognizing the limits of our knowledge and being willing to learn from others. Expertise can be valuable without answering every question.
State where evidence is weak, invite criticism, and listen to people with different experience. Leave room to revise a decision when new information appears.
Ask together: What might we be missing, and who could help us see it?
Prudence
Prudence means using careful judgment before and during action. It balances worthwhile opportunities with the need to avoid harm that could have been anticipated.
Start with a limited trial, set stopping points, and prefer choices that can be undone when uncertainty is high. Review what happens rather than assuming the original plan remains sound.
Ask together: What is a careful next step, and when should we stop or change course?
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.