Microsoft Research's PDD Kit formally proves AI-generated code meets your intent
omojumiller · x · 2026-10-22
- Problem: Agents now write more code than anyone can review; people skim diffs and push. Research shows the best AI code reviewer catches a bug on the first try only 42% of the time.
- Solution: Microsoft Research's new Proof-Driven Development Kit (PDD Kit) captures your objective in plain English as "intent", turns it into a formal spec in Verus (a proof language for Rust), and proves the code meets the spec for every possible input.
- Workflow: You review your plan and objectives, never the code or proof; empirical verification kicks in where proofs aren't possible. Integrated with GitHub Next's Chopin, with a demo taking a login flow from intent to verified PR.
More from coding & agent
- Hooking an AI Up to Your Bank Account With a 'Homeostasis' Goal Is the New Agent Pet — mimi10v3 · 2026-10-22
- Coinbase Ships Perps Trading for AI Agents After an Agent's Feedback Became a PR in 5 Minutes — MurrLincoln · 2026-10-22
- Grok Bot + REA workflow reverse-engineers paid apps to rebuild one feature for $0/month — alexcovo_eth · 2026-10-22
- terrio v0.4.0: Pure-Rust Geospatial I/O Library Ditches GDAL, CLI Under 15MB — giswqs · 2026-10-22
- DeepSeek-V4.1-Flash spotted running 5 parallel research subagents at near-zero cost — teortaxesTex · 2026-10-22
- One Cloudflare Durable Object at $9/month replaces Supabase's ~$33K real-time sync plan — threepointone · 2026-10-22