[We've raised €1.1M to fix AI coding drift
→](/content/blog/we-raised-1-1m-to-fix-ai-coding-drift/index.html)
The Straion Blog
Insights on AI-assisted development, coding standards at scale, and building software that stays on track.
AI coding agents are changing how software gets built. But speed without standards is just chaos. We write about what we're learning — from the trenches of building Straion, from conversations with engineering leaders, and from watching this space evolve at breakneck speed.
Product deep dives. Engineering lessons. Industry hot takes. No fluff.
Latest off the Press
We raised €1.1M to fix AI coding drift February 24, 2026
Straion announces its €1.1M seed round led by Marathon VC and outlines why autonomous engineering needs a rules layer to prevent AI coding drift.
Lukas Holzer, Katrin Freihofner, Fabian Friedl
All Posts
90% Rule Adherence March 26, 2026
When Claude Code runs with Straion, it stops guessing and starts coding like your best engineer. Straion's automated context layer drives rule-adherence into the 90%+ range, so your AI isn't just writing code—it's following your standards.
Katrin Freihofner
One million tokens won't save your engineering standards March 19, 2026
The industry is celebrating one million token context windows as the solution to AI coding problems. The research says the opposite. More context degrades rule adherence. Here's why less context wins.
Lukas Holzer
Your AGENTS.md is costing more than you think March 3, 2026
ETH Zurich researchers tested whether AGENTS.md and CLAUDE.md files actually increase the success rate of coding agents. The result: LLM-generated context files reduced resolve rates by ~3% and inflated cost by over 20%. Static context files have no concept of relevance, dumping every rule on the agent regardless of the task.
The fix isn't writing a better file; it's changing the delivery mechanism entirely. Deliver only the rules that matter for the specific task, dynamically, at the moment the agent needs them.
Fabian Friedl