Choose Your Thinking Partner

Step 1 · Describe the task

Choose the answer that best describes the task, not the answer that feels safest.

1. How repeatable is the task?

Would a clear checklist work most of the time?

Very repeatableClear steps or a known format

Somewhat repeatableFamiliar, with a few judgment calls

New or open-endedNo reliable checklist yet

2. How much judgment does the task require?

Is the main challenge execution, synthesis, or deciding between tradeoffs?

Very littleFollow instructions or transform material

SomeInterpret and make routine choices

A great dealWeigh ambiguous tradeoffs

3. What happens if the answer is wrong?

Think about stakes and how easily a person can reverse the result.

Easy to reverseA quick correction is fine

Worth getting rightNormal professional consequences

ConsequentialCostly, sensitive, or hard to undo

4. How many sources, constraints, or steps are involved?

Count competing inputs, requirements, and dependencies.

One or twoA focused request or source

SeveralNormal multi-step work

Many or conflictingEvidence must be reconciled

5. How easy is it to verify the result?

Can a person quickly tell whether it is good enough?

Easy to checkClear facts, format, or quality bar

Needs reviewGood judgment is visible with context

Hard to knowSubtle errors may be missed

6. What matters most for this run?

Volume and speed can justify a lighter option when the work is clear.

High volume or fast turnaroundKeep cost and latency down

BalancedNormal quality, speed, and cost

Quality over speedTime is available for a stronger pass

7. Is this the final critical review?

Reserve this for a difficult final pass where a small reliability gain matters.

NoThis is working output or a normal decision

Almost finalImportant, but not a last-chance review

Yes, final and criticalA small miss would materially matter

Advanced choices are separate from the everyday selector

None, XHigh, and Max are reasoning-effort settings, not model tiers. None is for pure transformations with no meaningful reasoning. XHigh is for rare critical review after it has shown a real benefit. Max is never the default: use it only for the hardest quality-first work after comparing it with XHigh.

Pro and multi-agent are also separate choices. Pro can be used with any GPT-5.6 model, while effort is selected independently. Multi-agent parallel work is a workflow pattern for complex deliverables, not another effort level. For most people, choose one worker and one thinking depth first.

Sources

Official OpenAI references

The selector is a practical routing aid. Test important workflows with your own representative work.

Start with the cheapest option that should succeed. Escalate after a concrete failure, or when the cost of being wrong is clearly higher than the extra model cost. · A free tool from Majestic Labs.