---
title: How Ari adapts question difficulty in real time
description: A plain-language look at how Greenroom's AI interviewer adjusts follow-up depth without turning the interview into chaos.
url: https://usegreenroom.app/blog/how-ari-calibrates-difficulty
last_updated: 2026-06-11
---

← Back to blog

Engineering

# How Ari adapts question difficulty in real time

Apr 18, 2026 · 7 min read

![How Ari adapts question difficulty in real time — cover illustration from Greenroom, the AI mock interviewer](/assets/blog/how-ari-calibrates-difficulty-hero.webp)

Ari does not blindly escalate every answer into a harder problem. It uses the candidate’s response quality, clarity, and confidence signals to decide whether to probe deeper, clarify, or move forward.

## Why this matters

Too many AI interviewers either feel static or interrogative. Static interviews miss differentiation. Overactive follow-ups frustrate good candidates. The trick is controlled adaptation: enough to reveal signal, not enough to feel arbitrary.

![Greenroom session where Ari asks a question generated from the candidate's own GitHub repository](/assets/blog/pool-github-question.webp)

Greenroom reads your GitHub — the questions come from your actual code.

## The product principle

We optimize for interviews that feel intentional. The best follow-up is often the one that sharpens the current answer, not the one that shows off the model.

## Frequently asked questions

### How does Ari decide how hard the next question should be?

Ari tracks how completely and confidently you answered, then adjusts follow-up depth: strong answers earn harder probes into trade-offs and edge cases, while struggling answers get scaffolding rather than a pile-on. The goal is a realistic stretch, not chaos.

### Will Ari keep grilling me if I'm doing badly?

No. Like a good human interviewer, Ari de-escalates: it simplifies, offers a foothold, and moves to a different area to find what you do know. A session that's all failure teaches nothing.

### Does adaptive difficulty make scores incomparable between sessions?

No — scoring is anchored to a rubric, not to the question sequence. Difficulty calibration changes the path through the interview, while the rubric keeps the grading consistent.