Stop Conditions
62%
Lesson 5 of 8

Stop Conditions

An agent needs explicit rules for when it is done, when it is stuck and when it must stop for safety.

Active reading
Why this matters

An agent needs explicit rules for when it is done, when it is stuck and when it must stop for safety.

Success

Define the completed state.

Limit

Cap steps, time or cost.

Escalate

Stop and ask a person when needed.

Understand the working model

Without stop conditions, an agent can loop, repeat actions or keep spending resources because “try again” always appears possible. Bound the loop before deployment.

Use both positive and negative stops: finish when the objective is verified; stop when step limit is reached, required data is missing or a protected action is requested.

Example
Stop when ticket is created and ID is stored. Maximum 6 tool calls. If customer identity cannot be verified, stop and request human review.
Practice

Apply the pattern above to one real task you already do. Keep the first version small enough that you can inspect every input and output.

Common mistake

Do not use “the model decides when it is done” as the only stop rule.

Key takeaway

Bound agents with explicit success criteria, resource limits and escalation rules.

Next lesson

Human Approval

Continue to the next lesson.

Continue →