
As AI agents generate increasingly large volumes of code, traditional code reviews are struggling to keep pace. Shadaj Laddad, research lead for the Hydro team at AWS, believes the solution lies in automated correctness checks that operate outside an AI agent’s control.Speaking at AGNTCon + MCPCon, Laddad explained how Hydro, an open source Rust framework for distributed systems, uses compile-time checks to catch bugs before code runs. Inspired by Rust’s borrow checker, Hydro aims to provide shared, domain-specific guardrails that help developers maintain reliability even as agents produce larger, more complex code changes.The team is also exploring safeguards for recurring challenges such as idempotency, ensuring retried requests don’t execute twice. Laddad also highlighted Infinity, an open source runtime designed to support massive agent concurrency by suspending idle agents awaiting external operations. Developed jointly by AWS and UC Berkeley, Hydro and Infinity represent efforts to make AI-driven software development more scalable, efficient and trustworthy.Learn more from The New Stack around the latest developments around front end frameworks:AI-generated Rust compiles perfectly. That's the scary part. Do Frontend Frameworks Still Matter? A Thread Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.

AI agents were all over KubeCon. Production is another story

DuckDB just shipped its biggest release ever. Its own team says not to run it in production just yet.

DuckDB has an answer to “bloated” database messages

DuckLake 1.1 solves the absurd complexity of data lakes at AI scale
Free AI-powered recaps of The New Stack Podcast and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.