Concern 248 · Working draft · editorial review in progress
Under-specified stopping conditions
Under-specified stopping conditions leave an agent without a clear rule for when to finish, pause, or return control to a person.
Understanding the concern
Some tasks have an obvious endpoint, while open-ended research or improvement can continue indefinitely. Without limits, an agent may repeat work, consume resources, or keep acting after the useful part is complete. It may also stop too early if it uses a weak success test.
A good stopping rule distinguishes completion from exhaustion of time, budget, or available evidence. Reaching a limit should produce an honest status, not a false claim of success. Clear checkpoints also let a person decide whether further effort is worthwhile.
An example
An assistant keeps polishing a report because better has no defined endpoint, while the deadline passes.
Illustrative unless identified as a documented case.
Words in plain English
- Agent
- An AI system that can choose and carry out several steps toward a goal, using the tools and access people give it.
Evidence and its limits
The sources support resource limits and task-success evaluation; the distinction between completed and budget-limited work is a design recommendation.
OWASP Gen AI Security Project · Security guidance
LLM10:2025 Unbounded Consumption ↗ (opens in a new tab)Describes uncontrolled inference, resource exhaustion and budget risks; unintentional loops are a related application scenario.
Kapoor and colleagues · 2024 · Research analysis
AI Agents That Matter ↗ (opens in a new tab)Examines agent evaluation, cost, reproducibility and benchmark overfitting; concerns the benchmarks studied.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
What evidence counts as completion, and what limits require the agent to pause and report?
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.
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?
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?
Stewardship
Stewardship means caring for resources and systems that others depend on, including people who will use them later. It looks beyond the benefit of a quick launch.
Plan for maintenance, energy use, data protection, and eventual shutdown. Ask who will look after the tool when the original team moves on and how future users can avoid inheriting hidden costs.
Ask together: What are we responsible for caring for over time?
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.