Blog

Practitioner notes. No hype, no vendor pitches — just what we've built and learned.

25 February 2026

Which AI to Use for ISO 26262 Documentation — And What It Actually Costs

Choosing AI infrastructure for automotive safety documentation is different from normal AI procurement. This article covers deployment options (standard API, enterprise tier, private cloud, self-hosted), model comparison for safety work, real cost estimates, and what we actually run.

25 February 2026

From RAG to Agents: How We Made Our Safety AI Actually Think

We promised a follow-up on agentic workflows. Here it is. After two years of RAG for ISO 26262 documentation, we rebuilt the system around multi-agent orchestration. Completeness before human review went from 60-70% to 85-90%. More importantly, where engineers spend their time changed completely. This is what we built, what improved, and what still does not work.

31 July 2024

We Built an AI That Writes ISO 26262 Safety Cases. Here's What We Learned.

We actually built it — an AI system that generates functional safety requirements, technical safety requirements, and safety plans that hold up under ISO 26262 assessment. Not a concept. Not a demo. A working prototype we've been testing against real documentation. Here's an honest account of what works, what surprised us, and where human judgment is still non-negotiable. Plus the full architecture, tools used, and what we're building next.

19 July 2024

Your ISO 26262 Assessor Doesn't Trust Your AI. Here's Exactly Why — And How to Fix It.

Most automotive safety teams are making the same mistake: they bolt AI onto their existing process and hope the assessor plays along. They don't. After 15+ years in functional safety assessments, I've seen exactly why AI-generated safety cases get flagged — and it's not the AI's fault. It's how teams present it. This post breaks down the 5 real objections assessors raise, and what you actually need to do to get them on board. Spoiler: transparency beats perfection every time.