# Our Framework for Reviewing AI-Generated Code

DevFeed: [Our Framework for Reviewing AI-Generated Code](<https://devfeed.tech/articles/our-framework-for-reviewing-ai-generated-code-65706.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/research/2026/10/review-ai-generated/>)

Author: Katie Fraser

Published: 2026-10-06T12:17:53Z

Content type: article

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [human-in-the-loop UX](<https://devfeed.tech/topics/human-in-the-loop-ux.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>)

Tags: [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [hax](<https://devfeed.tech/tags/hax.md>), [research](<https://devfeed.tech/tags/research.md>), [review](<https://devfeed.tech/tags/review.md>)

## AI overview

The article presents a three-level framework for reviewing AI-generated code, organized around calibrating reviewer trust to risk at overview, file, and code-snippet levels. Drawing on a participatory design study and survey, it argues that conventional diff views do not help developers allocate attention effectively across large generated changes. It discusses existing tools and design guidance for surfacing confidence and risk signals.

## Source excerpt

AI coding agents can now write thousands of lines of production code across a dozen files in the time it takes you to make coffee. The bottleneck is no longer code generation; it's review, and nobody's quite sure how to do it well yet. Our Human-AI eXperience team, in collaboration with researchers from Lund University, [...]