Microsoft Research's PDD Kit turns intent into a Verus spec and proves agent-written code against it, verifying a Rust storefront's login logic
A proposal for scaling review of agent code: the developer reviews the spec, a prover checks the code for every input, and tests cover what a proof can't reach.
// Key points
- PDD Kit works with the developer to turn intent into a formal specification in Verus, proves the agent's code meets it for every input, and falls back to tests where a proof can't reach
- Inside GitHub Next's Chopin, it verified the login logic of Pet Store, a Rust storefront; Verus hardened the code and uncovered existing bugs
- The developer reviewed the intent and never read the generated code line by line
- The authors argue agent-written tests usually check what the agent built rather than what was asked for
Builder's takeFormal proofs won't cover a whole product, but login, sharing permissions and billing are small enough to specify. I'd try the idea on the AI cloud drive's share-link permission check first; even without Verus, writing the spec before handing work to the agent already catches the gap between what I asked for and what its tests check.
// Background · from #Coding agents
Full timeline →- Nov 6 GitHub's new pull request Overview page enters opt-in public preview, with a merge box redesigned to show the same information in under half the space
- Nov 5 OpenAI's autonomous pipeline found, validated and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel
- Nov 5 OpenAI to acquire Pierre Computer Company to expand Codex's tools for building, understanding and reviewing code