Topic Archive
Verification
Tests, gates, and feedback loops that keep software honest.
Showing 5 articles tagged Verification.
Using decision models to speed up design rule violation repair in chip design
AI agents can fix design rule violations on chips, but the process is slow. We used a decision model to choose fixes for design rule check (DRC) violations on a digital and a photonic benchmark, and kept nearly all the quality of a large language model at under half its cost.
We built a layout viewer for AI agents. Then an agent scaled it to 38 million shapes.
How a goal-driven loop turned PhotonForge's browser LiveViewer from a half-million-shape viewer into a 38-million-shape, 60 FPS tool for humans and agents.
Predicting Peak Memory for an Electromagnetic Mode Solver
How we replaced a heuristic memory estimate with a calibrated model for Tidy3D mode solver workloads, eliminating under-predictions across the calibration set.
"What Should We Work On Next?"
The story of building an 80,000-line autodiff library almost entirely through AI agents — and the verification infrastructure that made it possible.
The Agent Control Loop — Engineering for Tolerance
Why agent reliability isn't magic model behavior — it's an environment where correctness is continuously verified. A framework for deciding when and how to delegate to AI agents.