How Much Code Do Developers Really Let Agents Write?

Summary

JetBrains surveyed over 15,000 professional developers globally in 2026 to measure how much production code is generated by AI agents versus manual authoring. On average, respondents report that agents fully write approximately 47% of their code, while 38% involves AI assistance and 27% is written manually. Adoption varies across ecosystems, with Go, JavaScript, and TypeScript developers reporting the highest agentic code generation at 54% to 55%, while C and C++ developers retain the highest manual share. Senior developers lead adoption over juniors, with about a quarter delegating more than 80% of code generation to agents. Cluster analysis categorizes the developer population into agentic coders (31%), AI-assisted coders (47%), and manual coders (23%).

Context

JetBrains sought to evaluate claims regarding the extent of agentic AI adoption in software development and measure how agent-generated code shares vary by developer seniority, programming language, tooling, and geographic region.

Approach / What changed

The JetBrains Developer Ecosystem Survey 2026 sampled over 15,000 professional developers worldwide between May and July 2026. The analysis filtered unrealistic responses, used bucket midpoints to compute category averages, and applied hierarchical cluster analysis using the Ward method and Euclidean distance to group developers by AI usage profiles.

Takeaways

• Developers using Go, JavaScript, and TypeScript report the highest shares of agent-generated code (54% to 55%), whereas C and C++ developers maintain the highest proportion of manually written code at 38% on average.
• Among tool ecosystems, 42% of Codex users generate over 80% of their code with agents and 37% write zero code without AI, compared to 32% and 28% generating over 80% agentic code among Claude Code and Cursor users, respectively.
• East Asian developers in China, Japan, and South Korea lead agentic code generation, with 32% to 35% producing over 80% of code via agents, roughly double the 16% observed across Europe and the United Kingdom.

Related reading

• Jetbrains · Aug 25, 2026

  Ideas Worth a Longer Conversation: The JetBrains Research Podcast

  The JetBrains Research Podcast investigates foundational software development and computer science questions through discussions with industry researchers. In team psychology, Cat Hicks demonstrates that collaborative culture and organizational belonging reduce developer anxiety around automated tooling while curbing the risks of overproduction pressure. Historical analysis by Tomáš Petříček shows that programming spans five competing cultures rather than pure specification implementation, explaining why automated code generation historically encounters limits. Regarding artificial intelligence evaluation, Ibragim Badertdinov details how SWE-rebench isolates model capability through dataset decontamination, leveraging the strict verifiability of software test execution for training feedback. Additionally, conversations with Alexander Kulikov and Anna Kogan examine how foundational mathematical understanding aids AI oversight and address adoption hurdles for open-source computer vision infrastructure.

  Katie Fraser

• Dropbox · May 28, 2026

  Beyond code generation: rethinking engineering productivity in the age of AI agents

  Dropbox shares how widespread AI code generation shifts software development bottlenecks downstream into code review, CI infrastructure, and validation pipelines. To adapt, they built Nova, an internal coding agent platform that safely automates scoped tasks such as migrations and flaky test remediation. They also evolved their developer productivity framework to measure end-to-end customer impact and code quality rather than simple pull request throughput.

  Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra,Kazuaki Okumura

• Salesforce · Aug 20, 2026

  Why AI-Generated Code Is Easy but Engineering Trust Is Hard

  At Salesforce, engineering teams discovered that AI coding agents could produce internally consistent code and passing test suites that still failed to meet actual requirements. To ensure correctness before writing code, the team developed an agentic Spec-Driven Development workflow centered on explicit specifications and gated verification. The system separates evidence-based repository lookups handled by agents from subjective judgment calls escalated to human engineers. Implementation plans must cite repository evidence reviewed by a Skeptic Agent, while a Compliance Matrix traces each success criterion directly to executable test proof. Finally, a multi-agent review system evaluates the implementation under an asymmetric rule allowing an independent judge to downgrade passing checks but never override failed gates.

  Scott Nyberg

• Jetbrains · Aug 20, 2026

  PyCharm for AI-assisted Django Workflows

  According to the 2026 Django Developers Survey, ninety percent of respondents incorporate artificial intelligence into their weekly or daily workflows. While agents generate code rapidly, developers remain accountable for understanding, evaluating, and shipping changes within their applications. PyCharm addresses these demands by integrating support for external agents, local models via Ollama and LM Studio, and customizable agent skills across codebases. The IDE maintains version-specific framework assistance, including auto-completion for Django 6.0 template partials, alongside architectural inspection tools and visual diffs. Furthermore, developers can trace application components, inspect API endpoints, execute HTTP requests, and query database migrations directly through built-in tooling.

  Will Vincent