Cover image

One Domain, Four Schemas

TL;DR for operators Scientific-literature extraction is not only a question of whether an AI system can find the right facts. It also needs a representation capable of preserving the distinctions engineers will later use. Sadruddin et al. build four separate machine-validatable process schemas for atomic layer deposition (ALD) and atomic layer etching (ALE), divided again between experiments and simulations.1 The split is consequential: the schemas contain between 167 and 275 properties, while required-property counts range from just 3 in ALD simulation to 56 in ALE simulation. ...

October 15, 2026 · 7 min · Zelina

From Fab War Room to Evidence Loop: A Semiconductor Yield-Investigation Agent

A composite 300 mm specialty fab redesigned yield-excursion investigations around six evidence-grounded agents while retaining human authority over equipment, recipes, lot disposition, corrective actions, and production release.

August 15, 2026 · 8 min · Vox
Cover image

Divide, Cache, and Conquer: How Mixture-of-Agents is Rewriting Hardware Design

Hardware design has a rather unforgiving relationship with “almost right”. A chatbot can produce a slightly clumsy paragraph and survive the incident. A Verilog module that mishandles reset logic, races a signal, or politely misunderstands concurrency does not get partial credit from physics. It fails simulation, or worse, passes the wrong simulation and then becomes a very expensive archaeology project later in the design flow. ...

November 5, 2025 · 13 min · Zelina