Cursor 開発者習慣レポート（1 分で読めます）

• A field transformed
• Developer acceleration
• The economics of intelligence
• The power user gap
• The rise of context
• The shift to automation
• Methodology

A field transformed

The change sweeping through software development is astounding. This inaugural Developer Habits Report, based on Cursor data, captures that transformation across five themes:

• Developer acceleration. We chart how coding speed has doubled year-over-year, PRs are getting larger and deeper, and agent-generated code is surviving review at higher rates than ever.

• The economics of intelligence. We benchmark seven model families on cost per line and cost per submit, revealing wide heterogeneity in unit economics.

• The power user gap. We find that while AI is leading to broad productivity gains, the change is most pronounced in the top 1% of developers.

• The rise of context. We show the dramatic increase in input tokens, and the shift toward cache-read tokens, which is giving agents the working memory to take on more complex tasks and produce higher-quality code.

• The shift to automation. Finally, we look at how coding agents are evolving from a tool used by individual developers into an entire system for building and maintaining software, often automatically.

This report provides a data-driven fixed point for understanding where agentic software development stands today, and where it appears to be headed next.

• ### Code is moving faster

Developers are adding more code per week, with growth accelerating since the start of 2026. While this is not a perfect metric, it provides a directionally interesting baseline for understanding how developer work is changing.Lines added/dev/wkCode is moving fasterDevelopers are adding more code per week, with growth accelerating since the start of 2026. While this is not a perfect metric, it provides a directionally interesting baseline for understanding how developer work is changing.02K4K6K8K10K31 Mar '2530 Jun '2530 Sep '2531 Dec '2531 Mar '26Time-series data for Code is moving faster.DateLines added/dev/wk2025-01-013.6K2025-01-223.6K2025-02-123.9K2025-03-053.9K2025-03-264.2K2025-04-164.2K2025-05-074.2K2025-05-284.1K2025-06-184.4K2025-07-094.3K2025-07-304.5K2025-08-204.7K2025-09-104.6K2025-10-014.6K2025-10-224.8K2025-11-125.3K2025-12-035.5K2025-12-245.4K2026-01-145.5K2026-02-046.2K2026-02-257K2026-03-187.3K2026-04-087.2K2026-04-298.1K2026-05-168.6K

• ### Code additions are growing per PR

Lines added per PR are up roughly 2.5x year over year and the growth rate is accelerating.Lines Added per PR (p75)Code additions are growing per PRLines added per PR are up roughly 2.5x year over year and the growth rate is accelerating.010020030040031 Mar '2530 Jun '2530 Sep '2531 Dec '2531 Mar '26Time-series data for Code additions are growing per PR.DateLines Added per PR (p75)2025-01-01125.862025-01-22118.162025-02-12119.012025-03-05122.532025-03-26127.732025-04-16132.672025-05-07137.982025-05-28138.642025-06-18146.912025-07-09159.462025-07-30171.582025-08-20174.652025-09-10177.592025-10-01178.342025-10-22186.632025-11-12196.272025-12-03211.542025-12-24224.652026-01-14253.52026-02-04251.942026-02-25268.562026-03-18277.472026-04-08292.062026-04-29312.792026-05-16345.02

• ### Developers are taking on larger units of work

Mega PRs, defined as PRs with at least 1,000 lines changed, are becoming more common as developers use AI to take on larger units of work in a single PR. It's interesting to see the jump in mega PRs in January 2026, when many developers were trying out the latest improvements in coding agents and models.Share of merged PRs with ≥1,000 lines changedDevelopers are taking on larger units of workMega PRs, defined as PRs with at least 1,000 lines changed, are becoming more common as developers use AI to take on larger units of work in a single PR. It's interesting to see the jump in mega PRs in January 2026, when many developers were trying out the latest improvements in coding agents and models.0%5%10%15%31 Mar '2530 Jun '2530 Sep '2531 Dec '2531 Mar '26Time-series data for Developers are taking on larger units of work.DateShare of merged PRs with ≥1,000 lines changed2025-01-018%2025-01-227.5%2025-02-127.4%2025-03-057.6%2025-03-267.8%2025-04-168%2025-05-078%2025-05-288.4%2025-06-188.6%2025-07-099.2%2025-07-309.5%2025-08-209.6%2025-09-109.6%2025-10-019.8%2025-10-2210.3%2025-11-1210.6%2025-12-0311.2%2025-12-2411.9%2026-01-1411.6%2026-02-0412.1%2026-02-2512.4%2026-03-1812.4%2026-04-0812.5%2026-04-2913.4%2026-05-1613.8%

• ### Agent sessions are getting deeper

In just the last two months, average tool calls per session have risen roughly 30%. Coding agents are taking on more complex work, reading and editing files, searching code, running shell commands, and browsing the web more frequently.Mean Tool Calls per SessionAgent sessions are getting deeperIn just the last two months, average tool calls per session have risen roughly 30%. Coding agents are taking on more complex work, reading and editing files, searching code, running shell commands, and browsing the web more frequently.9010011012013014015031 Mar '2630 Apr '26Time-series data for Agent sessions are getting deeper.DateMean Tool Calls per Session2026-03-01113.632026-03-05112.742026-03-09112.512026-03-13112.32026-03-17114.292026-03-21120.772026-03-25127.792026-03-29126.312026-04-02126.332026-04-06130.92026-04-10131.62026-04-14131.662026-04-18131.212026-04-22129.382026-04-26127.392026-04-30127.092026-05-04134.722026-05-08133.162026-05-12134.062026-05-16145.08

• ### AI-generated code is surviving longer

Since the start of 2026, the share of accepted AI lines still present after 60 minutes has risen from roughly 76% to 81%.Survival ShareAI-generated code is surviving longerSince the start of 2026, the share of accepted AI lines still present after 60 minutes has risen from roughly 76% to 81%.70%75%80%85%31 Jan '2628 Feb '2631 Mar '2630 Apr '26Time-series data for AI-generated code is surviving longer.DateSurvival Share2026-01-0776.6%2026-01-1376.3%2026-01-1976.2%2026-01-2576.3%2026-01-3177%2026-02-0677.3%2026-02-1277.7%2026-02-1878.5%2026-02-2479%2026-03-0278.8%2026-03-0878.9%2026-03-1479.1%2026-03-2079.1%2026-03-2679.5%2026-04-0179.6%2026-04-0779.9%2026-04-1379.9%2026-04-1980%2026-04-2580.2%2026-05-0180.4%2026-05-0780.6%2026-05-1380.3%2026-05-1680.6%

Request costs differ widely by model family

Cost per agent request varies by nearly 9x across model families, showing that the same workflow can have very different cost profiles depending on the model behind it.

USD per Agent Request (Mean)

Request costs differ widely by model familyCost per agent request varies by nearly 9x across model families, showing that the same workflow can have very different cost profiles depending on the model behind it.$0.00$0.50$1.00$1.50opus 4.7opus 4.6gpt 5.5gpt 5.4<text y="16" text-anchor="end" transform="rotate(-30)" fill="currentColor" opacit