We build AI systems.
We write the words
that make them human.
SG Research is a lab where rigorous research and craft writing collide. We publish on multi-agent AI, ship content systems for clients, and think hard about where intelligence ends and narrative begins.
anomalous thermal signature, sector 7"
Temporal gap: 14h — insufficient"
Recommend: 2 additional corroborations"
Featured Publication
Tri-Persona AI: Teaching Machines to Argue with Themselves
OSINT analysts are drowning in data. Single-model AI hallucinates, misses context, and delivers false confidence. We took a different approach.
Inspired by the MAGI supercomputer from Evangelion, our architecture deploys three distinct AI personas that actively debate conclusions before surfacing them. The result: explicit reasoning chains, reduced hallucination, and a built-in audit trail for every inference.
What We Do
Creative & Technical Writing
Documentation that engineers actually read. UX copy that converts. Narratives that make complex systems feel inevitable. We write for humans first — from onboarding flows to game dialogue to research briefs.
AI Content Strategy
Not another chatbot. We design intelligent content pipelines — knowledge bases, auto-generation systems, editorial AI — that scale output without losing voice. Built for teams that care about quality at scale.
AI Research & Consulting
Bring us your hard problem. We work at the research level — multi-agent systems, data analysis, ML integration — and translate findings into decisions your team can act on. We publish what we learn.
Selected Work
The Lab
SG Research started with a question: why does most AI-generated content feel empty, and most technical writing feel inhuman? The answer is usually the same — whoever built it optimised for volume, not for truth.
We're led by Alexander V. Neri, a technical writer and researcher with 17+ years across enterprise software, game development, and machine learning. Founded in Manila. Headquartered in Amsterdam. Working with clients worldwide.
Our approach is simple: we treat content as a precision instrument and AI as a research subject, not a shortcut. When we build AI systems, we publish what we learn. When we write, we write like we mean it.
We are a small lab. Intentionally. Quality doesn't scale by headcount.
Start Something
Let's talk about your hardest problem.
Whether you need documentation that actually works, an AI system that thinks more carefully, or a research partner who publishes their findings — we're interested. Tell us what you're building.