Founder, Poligon Tech
George Jucan runs Poligon Tech, a founder-led software and applied-AI team in Romania that builds AI agents for operations teams. The agents run over the ERP, email and spreadsheets a company already uses, with people approving every decision that matters.
He builds with coding agents such as Claude Code and Codex every day, and writes Poligon's Insights on agent harnesses, developer tools, human-in-the-loop design and what it takes to run AI in real operations.
Which agent harness should you use? A plain-language comparison of the main coding agents, self-hosted personal agents and control surfaces: what each is built for, why it is good, and where it falls short.
Most AI readiness assessments end in a slide deck. A workflow audit ends with an agent running on your real cases and a go or no-go. What each one covers, what it costs, and what to ask for.
CLAUDE.md, skills, hooks, subagents and MCP servers all extend Claude Code, but they solve different problems. A practical guide to which one to reach for, with examples.
A step-by-step guide to exposing ERP data to AI agents through the Model Context Protocol: narrow tools, read-only credentials, validated inputs, and a safe path to writes.
Human-in-the-loop only works if the approval step is fast, informed and honest. How to decide what an AI agent may do alone, what it must ask about, and how to keep approvals from becoming rubber stamps.
Hermes Agent from Nous Research is an open-source, self-hosted agent that remembers, learns skills and lives in your chat apps. What it does, when it is worth using, and a step-by-step VPS setup with sensible security.
Running Hermes, OpenClaw, T3 Code or Claude Code on an always-on server makes agents more useful and, done right, safer. When it is worth it, which setup fits which harness, and a security checklist.
An agent harness is the software around a language model that gives it tools, context, permissions and a loop. Here is what goes into one, and why it decides whether an agent works in production.
T3 Code is a free, open-source app for driving Claude Code, Codex, OpenCode and other coding agents from one place: desktop, web or phone. How it works, how to set it up, and where it falls short.
Ce este un agent AI, cum diferă de ChatGPT și de RPA, ce poate face concret într-o firmă de distribuție, transport sau producție, unde nu ar trebui folosit și cum începeți fără migrare de ERP.
Ghid în română pentru Hermes Agent de la Nous Research: ce face, la ce e bun, cum îl instalezi pe un VPS, cum îl conectezi la Telegram și cum îl securizezi.
Ghid în română pentru Claude Code, agentul de programare de la Anthropic: instalare, primii pași, CLAUDE.md, moduri de permisiuni, skills, hooks, subagenți și MCP, plus cum îl folosim noi pe proiecte reale.
We use analytics cookies to see which pages help and to measure our ads. No data is sold. Privacy