Microsoft says AI-scale code migration makes verification the scarce resource

Microsoft has set out how its engineering teams are using AI agents for large-scale code migration and language modernisation, including work on Windows and Azure codebases and translations from C and C++ into Rust.

The company’s central argument is that generating code is becoming easier than proving it is correct. Microsoft describes migrations spanning a 400-million-line codebase and says small expert teams can approve reusable knowledge and resolve ambiguous cases while agents apply changes at scale. Reviewer agents, differential testing and held-out tests are used to challenge proposed fixes.

Microsoft is also experimenting with formal specifications inferred from existing software and with tools such as TLA+, F*, Lean and Verus. That could make architectural intent more explicit, but the company acknowledges a fundamental limitation: a specification derived from existing code may reproduce what the system does rather than what it should do.

This is an engineering account, not an independent evaluation. Its value lies in identifying the control bottleneck. As agents increase the volume and speed of change, organisations need stronger evidence at the specification and system-behaviour level, not simply more human reviewers reading individual lines.

AI for Leaders: Governance, Risk & Why Strategy Must Come First

Is your organisation adopting AI without a defined strategy or governance? If so, you're not alone — and the consequences range from data breaches to reputational damage to safeguarding failures. AI is a strategic risk, not a silver bullet, and definitely not a magic data fairy. Without clear ownership, rules, and accountability, AI can proliferate across your organisation in ways that cost more — in time, money, and trust — than not using it at all. Speakers: Craig Clark, Director at Clark & Company Information Governance Services, and Stewart Tinson, Project Director, AI-360. You'll learn: Why "understand your why" must precede any AI rollout Which risks senior leaders most commonly overlook — from data leakage to safeguarding How to measure AI value through outcomes, not adoption metrics Why accountability for AI governance sits with the C-suite, not IT or compliance Key topics: AI strategy • Risk appetite • Data protection • Bias & fairness • Safeguarding • AI literacy • Governance models • Return on investment • Executive accountability • AI use case tiering For CISOs, CIOs, and senior leaders who need to govern AI responsibly — before it governs them.

BrightTALK