Skip to content

Details

AI coding agents can now write substantial amounts of open-source software, but generated code still needs more than a plausible implementation and a passing test suite.

In this session, Carl will demonstrate a workflow in which AI writes code, creates a formal specification, and produces a machine-checked proof of correctness. He is applying this approach to RangeSetBlaze, an open-source Rust library, using Lean to state and prove key correctness properties.

The broader idea is language-independent: AI may make formal verification practical for ordinary software development by taking on much of the proof engineering itself.

The session will explore what this workflow looks like in practice, where it works, where it breaks down, and how formal proofs can complement testing and code review as AI takes on more of the coding.

Related topics

New Technology
Open Source Python
Microsoft

Sponsors

Microsoft Reactor YouTube

Microsoft Reactor YouTube

Watch past Microsoft Reactor events on-demand anytime

Microsoft Learn AI Hub

Microsoft Learn AI Hub

Learning hub for all things AI

Microsoft Copilot Hub

Microsoft Copilot Hub

Learning hub for all things Copilot

Microsoft Reactor LinkedIn

Microsoft Reactor LinkedIn

Follow Microsoft Reactor on LinkedIn

You may also like