News, releases and behind-the-scenes notes from our AI platform.
By Pavlo Chabanov — founder of Snaga. For most of this platform's life, the intelligence inside your agents came from someone else's servers. You wrote a prompt, it left our infrastructure, it was decrypted and read in cleartext on a machi
Hi. My name is Pavlo Chabanov, I'm a software engineer and developer with 30 years of experience. I've prepared for you and for your agent an instruction that will keep you disciplined in building quality software through a protocol of prof
LLM Studio is a Snaga platform tool for training your own language models for a specific domain. Unlike supervised fine-tuning on input/output pairs, training uses a domain verifier: the generated output is executed, and the score is comput
The platform has grown a lot this past month — from a single AI chat into a visual command center for whole teams of agents. Here's what you can do now. - Build squads visually — an n8n-style canvas: drag to connect agents, inspect any n
By Pavlo Chabanov — founder of Snaga. If you run a small company, the work that has to happen — answering customers, writing posts, chasing leads, reconciling numbers — never stops. And it is almost never the work you started the company t
Last time I set the direction toward end-to-end confidential inference. This is the arrival: a working system you can watch, with its cryptographic core grounded in Ada and SPARK — and the deeper layers it now frees us to build. By Pavlo C
By Pavlo Chabanov — founder of Snaga and the engineer behind its agent runtime. --- Every time you send a prompt to a hosted language model, it is decrypted and read in cleartext on someone else's machine. TLS protects the message in tran
Every Pod begins with one member: the Head Agent. It's the first thing that exists in your workspace — before any squad, before any specialist, before the first task. You write to it the way you'd write in a notebook, and behind that one qu
By Pavlo Chabanov — the engineer who built the Snaga ecosystem, and the author of its constitution. --- Every platform that gives agents real autonomy faces the same question sooner or later: when software acts on its own, what binds it?
An agent in your Pod isn't born knowing how to research a market, read a PDF, or place an order. And you don't teach it by programming. You hand it a SPEC. A SPEC is a sealed package of capability. Tools, skills, views and permissions — ve