跳到内容

使用情况

How developers use AI.
While code generation still comes first, it's interesting to note that code review (a new option this year) has jumped straight to third place. After all, those 30k lines of codes that got vibe-coded over the week-end will need to be double-checked at some point…
您使用 AI 工具做什么?
多选
0%
20%
40%
60%
80%
100%
01
代码生成
02
代码审查与协助
+8
03
学习与研究
-1
04
Debugging
05
总结
-1
06
文本生成
-3
07
翻译
-2
08
图像生成
-2
09
计算机视觉
-2
10
语音识别
-2
0%
20%
40%
60%
80%
100%
8%
Percentage of question respondents who stated the entirety of their coding output is now AI-generated.

AI 代码生成

The difference with last year is striking here. Back then the average respondent was using AI sporadically to generate a small percentage of their code, but today that same developer is much more likely to rely on AI for the bulk of their coding.

While AI usage is up across the board, it's interesting to note that higher usage brackets are correlated with lower median years of programming experience. And as you'd expect, usage of a coding agent such as Claude Code is correlated with a higher proportion of AI-generated code.

您编写的代码中有多少比例是 AI 生成的?
0%
20%
40%
60%
80%
100%
1
0% AI
2
|
3
|
4
|
5
50%
6
|
7
|
8
|
9
100% AI
0%
20%
40%
60%
80%
100%

AI 代码重构

Similarly, using AI-generated code without having to refactor it first is no longer the exception, with many respondents reporting only needing to refactor around 25% of AI output.
在使用 AI 生成代码时,您在使用前重写或重构的比例是多少?
0%
20%
40%
60%
80%
100%
1
0% 重构
2
|
3
|
4
|
5
50%
6
|
7
|
8
|
9
100% 重构
0%
20%
40%
60%
80%
100%
When respondents do need to refactor AI-generated code, the culprits tend to be poor code style and hallucinations. Interestingly, variable renaming does not seem to be as much of a factor anymore, pointing to the fact that LLMs are getting better at following instructions and learning from existing codebases.
需要您重构 AI 生成代码的主要原因是什么?
多选
0%
20%
40%
60%
80%
100%
01
糟糕的代码风格
+9
02
幻觉和不准确
+6
03
可读性差
-2
04
过度重复
-1
05
错误的代码
+2
06
变量重命名
-4
07
性能问题
-2
08
过时的导入
-4
09
安全问题
-3
10
无
0%
20%
40%
60%
80%
100%
61%
Percentage of question respondents who use AI to generate code on a daily basis.

代码生成频率

It seems clear that AI has become embedded in our work, with a majority of respondents using it multiple times per day, and a growing segment using it constantly.

And the more frequently you use AI, the lower your median number of years of programming experience is likely to be.

您多久使用一次 AI 工具来生成或重构代码?
0%
20%
40%
60%
80%
100%
1
从不
2
每年几次
3
每月几次
4
每周几次
5
每天几次
6
每小时几次
7
经常
0%
20%
40%
60%
80%
100%

其他任务频率

While the main focus of this survey is coding, other AI uses are also seeing increased used compared to last edition. After all if you trust AI with the main part of your job, it does seems logical to trust it with everything else, too.
除了代码生成之外,您多久使用一次 AI 工具处理其他任务?
0%
20%
40%
60%
80%
100%
1
从不
2
每年几次
3
每月几次
4
每周几次
5
每天几次
6
每小时几次
7
经常
0%
20%
40%
60%
80%
100%

生成的代码

Almost every type of generated code saw an increase compared to last survey, with tests in particular becoming a key reason to use AI.
您使用 AI 工具生成什么样的代码?
多选
0%
20%
40%
60%
80%
100%
01
辅助函数
02
前端组件
03
测试
+1
04
文档和注释
-1
05
核心应用逻辑
06
API 集成代码
07
Scripting
+1
08
CSS 代码
-1
09
配置代码
10
数据库查询
+1
11
无
12
All of the above
13
其他答案
0%
20%
40%
60%
80%
100%
The proportion of respondents enjoying the benefits of AI without personally having to spend their hard-earned cash has dramatically shrunken year-over-year; while the $100-$500 monthly spend demographic is seeing significant growth. This may be due to the rise of coding agents, which often carry heavier financial costs compared to simple chatbots.
您个人每月在 AI 工具上花费多少(美元)?
0%
20%
40%
60%
80%
100%
1
$0
2
$1-$20
3
$20-$50
4
$50-$100
5
$100-$500
6
$500-$1000
7
$1000-$5000
8
过滤掉的答案
-2
0%
20%
40%
60%
80%
100%
While the 2026 survey also included a question about company AI spend, its data wasn't usable because it didn't clearly state whether the question was about total company-wide spend, or per-employee spend.
Don't hesitate to use our built-in Query Builder on any other chart to filter these survey results according to any specific industry sector.
你在哪个行业工作?
多选
0%
20%
40%
60%
80%
100%
01
编程和技术工具
02
咨询服务
03
电子商务与零售
04
金融
05
营销/销售/分析工具
+1
06
教育
-1
07
卫生保健
08
娱乐
09
政府
+1
10
新闻、媒体和博客
-1
0%
20%
40%
60%
80%
100%
More and more respondents have tried local AI models, and while they aren't as powerful as their cloud-based cousins right now, there is strong potential for disruption as they provide a cheaper alternative to traditional frontier labs models.
您尝试过在自己的机器上本地运行 AI 模型吗?
0%
20%
40%
60%
80%
100%
1
不,不感兴趣
2
不,但感兴趣
3
是的
4
其他答案
0%
20%
40%
60%
80%
100%
Sentry MCP

Sentry MCP

Sentry MCP plugs Sentry's API directly into your LLM, letting you ask questions about your data in natural language.
感谢合作伙伴对我们的支持! 了解更多。