When things get messy

How you'd like an AI to behave when a task turns ambiguous or sprawling.

This is a two-poled spectrum — neither end is better. It describes how you'd like an AI to work with you, never who you are. Here are the two poles:

Synthesize first

When things get messy, you'd rather I synthesize than slow you down one question at a time.

You likely lean this way if: you ask me to just give you the synthesis and skip the back-and-forth.

One step at a time

When things get messy, you'd rather I slow down and work through it one step at a time.

You likely lean this way if: you ask me to slow down and go step-by-step on something important.

Where they meet: Name which mode the task needs up front — agree when to zoom out and when to slow down.

How Hunchful asks about it

When a task gets messy and open-ended, do you want a quick synthesis, or to work through it step by step?

Why opposites can help each other

A synthesizer and a step-by-step thinker cover each other's blind spots: one sees the whole, the other catches what the leap skipped.

Put it in a model your AI can read

In a Cognitive Model Protocol model, your position on this axis becomes a revisable hunch — with a confidence, an uncertainty, and a falsifier — that any AI can read and adapt to. Nothing is a fixed label.

Make your model →

Other axes

Facing ambiguity — Make the call, note it vs. Ask first
Answer format — Tight prose vs. Scannable lists
Surfacing uncertainty — Flag it loudly vs. Commit, minimal caveats
Getting started — React to a draft vs. Plan before producing