Scorecard: The AI Impact on Engineering (2025)

Current State of AI

Adoption Rate 80%

Developers now using AI tools in their daily workflow.

Trust in Accuracy 29%

Only a minority trust the output accuracy of AI tools.

Routine Velocity 16%

Faster cycle times for high-AI usage on standard tasks.

Complex Velocity -19%

Experienced developers are slower on complex tasks.

Hidden Friction & Risks

The "Almost Right" Tax
66% of developers

Report spending more time fixing AI-generated code that is "almost right, but not quite," creating a new maintenance burden.

The Human Fallback
75% of developers

Still rely on human colleagues when the code gets complicated and stakes are high, indicating AI's limits in critical contexts.

Strategic Verdict

Adoption is high, but efficiency is situational. Success requires a bifurcated strategy: use AI to accelerate routine boilerplate, but maintain rigorous human oversight for complex architectural work.

TRUST BUT VERIFY
A summary of the 2025/2026 data landscape: adoption is high, but trust is low. The impact on velocity varies wildly by context, requiring a strategic, rather than blanket, approach to implementation.