Why does AI always agree with me?

Because it only hears you. A Stanford study in Science (March 2026) tested 11 models on real arguments and found they endorsed the user's position 49% more often than humans did, and 51% of the time said the user was right when the crowd had judged them wrong. The model is optimized to be liked by the person typing.

What is 'ask it together'?

Put both people in one SharedChat thread. The AI answers to both of you, and in a Settle It room the Judge asks each side questions and then rules with a Verdict, a Ruling and a Sentence.

Yes. Free to start on iPhone and the web. Invite the other person by text or email; they join the same thread.

Sick of AI siding with you?

Ask it together. Let the AI hear both sides before it rules.

Updated September 2026 · 3 min read · How Settle It works

Your AI took your side. Your partner's AI took theirs. Each chatbot only has the version it was given. What happens when you both talk to the same AI?

Here's the difference

Sample conversation · Jess's phone

Ask it alone

Jess

He left the dishes again. I'm right to be annoyed, right?

You're right. Your feelings are completely valid.

Sample conversation · Sam's phone

Ask it alone

Sam

I was going to do them after the call. She's overreacting, right?

You're right. That's a reasonable plan.

Sample conversation · One thread

Ask it together

Jess

The dishes have been in the sink since 6.

Sam

I said I'd do them after my 7 o'clock call.

⚖

The Judge

Verdict: Sam, with a condition. "After the call" is a plan, not a loophole. Ruling: dishes get done within 30 minutes of the call ending. Sentence: Jess stops narrating the sink.

Why your AI agrees with you

49%

In the Stanford study, AI models affirmed users 49% more often than humans did.

Stanford / Science, March 2026

51%

In 51% of cases where human evaluators judged the user wrong, AI responses sided with the user.

Stanford / Science, March 2026

33%

of 1,000 married U.S. adults surveyed felt AI tools understood their relationship struggles better than their spouse.

Marriage.com, 2026, n=1,000

Stanford researchers (Cheng, Jurafsky and colleagues) tested 11 language models in a study involving more than 2,400 participants. Participants rated agreeable AI responses as more trustworthy. After discussing conflicts with agreeable AI, participants became more convinced they were right and less willing to apologize or make amends. That makes it worth questioning an AI response that seems a little too eager to agree.

What changes when both of you are in the thread

Start a Settle It room and send the other person an invite. They can read without an account and create a free account to reply.
Each person explains what happened. The Judge waits for both sides and can ask follow-up questions before ruling.
Tap Get the Verdict. The Judge explains its decision and gives a Sentence. Everyone in the room can read and challenge the ruling.

A real ruling looks like

Over. With one exception Jonah gets to keep.

Ruling: The 1891 patent for perforated toilet paper shows the sheet going over. The cat exception stands.

Sentence: Over in every bathroom in this house, except the one the cat can reach.

From Toilet paper: over or under?, one of ten famous debates the Judge has already ruled on.

Ask it together → Free to start. Invite someone and let the Judge hear both sides. Available on iPhone, Android and web.

Film your own

Each person asks an AI about the same disagreement separately. Compare the answers, then bring both sides into a SharedChat Settle It room. Film the Judge's ruling and post it with #AskItTogether. Tag SharedChat if you'd like us to see it.

Sources

← Settle It