Guide | Prompting

7 changes to make for GPT-6

GPT-6 Astra acts instead of asking, follows long instructions more closely, and formats everything unless you stop it. Here are the 7 changes, with a filled example for each one.

Start here

The model changed. Your prompts didn't.

GPT-6 Astra landed in paid ChatGPT accounts this month, and it behaves differently from what came before. It acts instead of asking. It follows long instructions much more closely. It formats everything unless you tell it not to.

So the habits you built to work around an older model are now working against you. Here are the 7 changes, in the order I'd make them. The first is a setting. The other 6 are one line each in how you write the ask.

Where these came from. Six of them are in OpenAI's own prompting guidance for this model, which is public. The effort call is Ruben Hassid's, from a week of using it every day, and I've marked it as his.

7 changesFilled example for eachChecked against OpenAI's own docsSeptember 2026
The list

7 changes, in the order to make them

Each one is a change to how you ask, not a new tool to learn. Read the change, take the example, and put it in your next real prompt.

01
Set the effort level

The change: before you type anything, pick how hard it thinks. Light is fast and shallow. Medium balances quality against waiting. High is for hard reasoning and deep planning.

Whose call this is

Ruben Hassid keeps his on Medium after using Astra every day for a week. He calls it the best mix of speed, cost and thinking. He also works only in Work or Codex mode. That part is his setup from real use.

OpenAI does not publish a best setting. Their own guidance calls effort a tuning knob and says task clarity matters more than the level you pick. Which is what the other 6 changes on this page are.

02
Name the finish line

The change: start the prompt with what you want to be holding when it stops, not with what you want it to look at.

Instead of
  • Help me analyze this spreadsheet.
Write
Copy it. Fill in anything in [brackets].
Give me a ranked list of my [5 best months], tell me how you grouped them, and flag anything based on too little data. Deliver the ranked list first, then your reasoning.
03
Say what each file is for

The change: when you attach something, give it a job. A file is evidence, a style example, a template, or instructions. Astra guesses if you don't say, and it guesses worst on style examples.

Copy it. Fill in anything in [brackets].
Use the [brand guide] for voice and tone only, not for facts. Use the [product brief] for all product details. If they disagree about a feature, flag the conflict before you write about it.
04
Stop saying ask me questions first

The change: Astra pauses to check far more than older models did. That old opener now interrupts work you wanted finished. Name only the decisions you actually want a say in.

Copy it. Fill in anything in [brackets].
Ask me only about [the audience and the deadline]. Make reasonable assumptions on everything else, complete the work, and list your assumptions at the end.
05
Say what readable means to you

The change: left alone it writes long, formats everything, and reuses the same stock phrases. Describe the shape you want once and put it in your custom instructions so you never ask again.

Copy it.
Default to clear, concise paragraphs, each developing one main idea. Use lists only when the information is genuinely parallel, sequential, or easier to compare. Keep paragraphs to two or three sentences. Explain an unfamiliar term the first time it appears. Start with the useful finding and end with one practical action.
Where to put it

This one belongs in your custom instructions, not in every prompt. Set it once and every answer after it comes back in your shape.

06
Correct it while it works

The change: you can send a new instruction mid-job and Astra folds it into the plan instead of you cancelling and rewriting. OpenAI calls this mid-turn steering.

What it looks like
  • It starts summarizing the wrong column. You type Use the March column instead of the totals while it is still going.
  • It updates what it is doing and keeps working. You keep the run instead of paying for it twice.
07
Give the checking a scope

The change: Astra tests and verifies thoroughly by default, which is slow on small reversible work. Tell it what is worth checking instead of letting it check everything.

Copy it. Fill in anything in [brackets].
Before you deliver, confirm the totals match the source, identify duplicate entries, and check that every date falls inside [the reporting period]. Report any mismatch you could not resolve. Do not run broader checks than that on this task.
Bonus

3 more from OpenAI's guidance, for anyone going further

These are in the same OpenAI document and are aimed at people running longer or more complex work. If the 7 above are enough for your week, stop there.

Before you go

One thing worth knowing

OpenAI's own guidance says to treat the effort setting as a tuning knob and not the main way to get better answers. Task clarity, constraints, and saying what the output should look like matter more than the level you pick.

Which means changes 2 through 7 on this page are worth more than change 1. Start with the finish line.