Three-part prompt: goal, done, and an out
Technique
Every long task prompt states what you want, what counts as done, and when the agent should stop and ask you. Models are trained not to give up, so they tend to answer their own questions and push on.
Theo's current stance
Theo says an explicit 'ask me if X' line makes models willing to stop when genuinely stuck.
Try it
- State the goal, then 'Done means…' with checkable conditions such as tests passing or a screenshot.
- End with one line on when to stop and ask, e.g. only if a test fails for a reason it can't explain.
First seen
11:32
explain. This is the perfect simple one, two, three. What you want, what means done, and the out if it needs an out if it does get confused or does something
Every mention
11:32
explain. This is the perfect simple one, two, three. What you want, what means done, and the out if it needs an out if it does get confused or does something
8:12
silly, but these models have been RL'd to hell and back to not give up on tasks. So, if the model asks a question, the initial thing it's been RL'd to do is to try and answer the question itself. So, if it did have
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.