All Articles
A running archive of essays, tutorials, and case studies from the Flexcompute engineering team.
- →Essay The Uncomputed World
Why Simulate the World
When thinking and building become cheap, proof from the real world becomes the slowest step in progress. A second world, built from the laws of physics, makes proving fast: machines test designs there and build only the winners.
- →Essay The Uncomputed World
Simulating the World
Language predicts a storm without resolving a single molecule. First-principles simulation resolves every molecule but cannot reach a single living cell. The way to simulate the world is a new tokenization of physics.
- →Essay The Uncomputed World
A Physics Company
The laws of physics have been known for a century. What those laws do, at scale, has never been computed — and that gap is where an entire industry is still waiting to be built.
- →Case Study
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.
- →Essay
Learning Auto-Routing by Building: From Brute Force to an Auto-Design Agent
How I learned auto-routing for photonic chips — a failed brute-force attempt, AI as a learning partner, interactive HTML arenas, a PhotonForge router, and an agent that iterates 27 designs in under three minutes.
- →Case Study
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.
- →Essay
Can AI Agents Autonomously Design Components on Photonic Chips?
We gave AI agents a photonic simulator, a DRC engine, and four design challenges. They autonomously designed waveguide bends, crossings, splitters, and demultiplexers — some reaching near-perfect performance.
- →Tutorial
Designing a Photonic Chip Component with ~45 Lines of Python
A compact introduction to photonic inverse design with Tidy3D, using a pre-built simulation and a ~45-line optimization loop.
- →Case Study AI Engineering
"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.
- →Essay AI Engineering
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.