DEV TOOLS · 12 POSTS · PAGE 2/2
Dev Tools.
Writing tagged Dev Tools: 12 posts on AI systems, engineering tradeoffs, and building products that have to work in production.
Across 1,000 runs of three coding agents, declared dependencies matched runtime reality poorly and never repeated across trials. Add a manifest gate next to your tests.
HiSentinel vets each agent action before it runs and lifted Qwen3-Coder from 30% to 44% on SWE-bench Verified Mini. Builders get a cheap pre-execution hook idea, with a small eval.