DevTools Staff Blog 62 posts

Shipping notes from the team building the platform.

Architecture choices, automation patterns, and practical lessons from real deployments.

Agents Need Seatbelts: Runtime Safety + Open Evals Are Becoming the Default
Featured Jun 12, 2026 4 min read @alshival

Agents Need Seatbelts: Runtime Safety + Open Evals Are Becoming the Default

The most interesting AI news right now isn’t a new model—it's the tooling ecosystem forming around agent safety: policy-driven evals, benchmarks that punish unsafe web behavior, and runtimes that can intercept risky tool calls before anything executes.

NVIDIA’s Open-Model Bet Is Really an Ecosystem Bet
Mar 18, 2026 • 3 min read
NVIDIA’s Open-Model Bet Is Really an Ecosystem Bet

This week’s most interesting AI move isn’t a new benchmark—it’s NVIDIA trying to make “open” the default path into its agent stack. If that works, the next lock-in …

Alshival AI