Notes on building AI for regulated work.
Articles on AI engineering, product judgment, and executive risk — the three views you have to hold at once when shipping into regulated work. From a team that holds all three.
What's new at Neuralcraft: April 2026
Monthly roundup — new eval harness, the launch of policy guards, and three customer go-lives.
Read article →Why we built Neuralcraft
We started Neuralcraft to bring production-grade AI systems to teams operating in regulated, high-stakes environments.
Read →Evaluating LLMs in regulated environments
Eval is the hardest part of shipping AI in regulated spaces. Here is how we approach it for healthcare and finance customers.
Read →Audit trails for AI systems
What an auditable AI system actually looks like in production — and the four log streams every team should be writing from day one.
Read →What's new at Neuralcraft: March 2026
Monthly roundup — observability upgrades, new SDK, and the first round of partner integrations.
Read →Deployment patterns for healthcare AI
Three deployment shapes we have seen succeed inside hospital networks — and the one that keeps failing.
Read →Choosing models for compliance
A pragmatic decision tree for picking between hosted and self-hosted models when compliance is non-negotiable.
Read →Blindfolded: Building AI Systems for the Dark Web
What we learned shipping image classifiers for darknet investigations — where the AI team can't see the training data.
Read →