The layered prompt
Technique
A prompt with layers: state the goal as non-negotiable, offer your own idea 'in my opinion' so the model can push back, admit what you don't understand, and ask for an audit rather than code, with permission to stop early if it finds a simple fix.
Theo's current stance
Theo finds that saying where his knowledge ends makes the model explain better and not blindly trust him. The early-stop permission keeps it from exploring 17 options when it already has the answer.
Try it
- Open with your priorities, e.g. a simple fix that won't confuse users.
- Add 'in my opinion' before your proposed solution and say what you're unsure about.
- Ask for an audit and tell it to stop and report if it finds a simple fix.
First seen
8:22
I then say, in my opinion, because if this thing isn't viable, I want it to tell me as such. Or if it thinks there's any reason I shouldn't do this, it'll be honest with me.
Every mention
8:22
I then say, in my opinion, because if this thing isn't viable, I want it to tell me as such. Or if it thinks there's any reason I shouldn't do this, it'll be honest with me.
9:52
This is me giving the model permission to at any given point, if it finds the solution, and it has four other sub agents going exploring other things, it can confidently stop and just tell me what it found instead of going forever for option one of 17 to be chosen…
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.