R105 · Agent principles and patterns › Evaluation data for agents

Sonar State of Code 2027: AI code outpaces verification

Read the original

coding-agentscode-reviewsurveytestinggovernance

Source: Sonar, 2027 State of Code Developer Survey report, released 2026-11-12; survey of 1,026 developers and engineering managers. Press release; report. Highlighted on LinkedIn by Cole Medin, 2026-11-16.

Read with care: this is a vendor survey from a company that sells code verification, so the framing favours verification tooling. The numbers are still a useful snapshot of how teams say they work.

The headline numbers

The framework: four multiplying terms

Sonar frames code confidence as intent, guiderails, verification and evidence multiplied together, so a zero in any one term zeroes the result.

  1. Intent: define outcomes, architecture standards, quality and security criteria before agents start. Unclear requirements (37%) and rewriting AI code (26%) top the toil list.

  2. Guiderails: give agents standards, context and tool or permission limits while they work. Teams with clear controls report higher ROI more often.

  3. Verification: check every change independently of the agent that wrote it; 77% say strong verification tools raise their trust.

  4. Evidence: record what was checked, found and fixed so release decisions and AI's value can be audited.

The practitioner rule Cole Medin draws from it: agents may write anything, but nothing merges until a check the agent doesn't control passes. A model approving its own work doesn't count.

What it means for engineering leaders

Tradeoffs and caveats

Failure modes this data points to

Review checklist for an agentic delivery pipeline

Connections

See R105 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.