AI agents
Multi-step agents with one clear role, scoped tools, hard limits and an escalation path to people. Measured by eval scenarios, not by a good first impression.
- Role & limits
- Tool scoping
- Human-in-the-loop
Novaeon Studio · The AI Agent Factory
We design, build, release and run AI agents on the hardest stacks — SAP included. With 22+ years of enterprise SAP delivery behind every release.
AI-generated photorealistic image: sunrise over the horizon of the Earth seen from orbit, with the Novaeon station and agent vessels moving along three orbits through four gates
The company is laid out like a station. Each room has its own page, its own proof and a way back.

The problem we solve
A demo agent takes an afternoon. An agent your auditors, your works council and your operations team will accept is architecture: defined role, tested skills, clear limits, a human who signs off — and a release process that lets you change it without fear.
How an agent ships
The same path every time. Nothing reaches production on enthusiasm alone.


Pick the process where an agent pays off. Map inputs, decisions, risks and owners — and decide where a plain workflow is the better answer.
Build the agent and its skills: tool contracts, guardrails, prompt-injection tests, eval scenarios and the human approval step.
Promote it like software: versioned, tested against a fixed baseline, risk-rated, approved, traceable — and reversible.
Watch quality, cost per action and drift in production. Improve on a release cadence, not by hot-fixing prompts.
What we build
Multi-step agents with one clear role, scoped tools, hard limits and an escalation path to people. Measured by eval scenarios, not by a good first impression.
The deterministic building blocks agents call: look up, validate, create, post. Small, tested, versioned — the part that makes an agent reliable.
ERP, CRM, APIs, documents. We connect the systems an agent needs — and automate the work that needs no agent at all.
Local and self-hosted models when data must not leave your infrastructure. Agents on your hardware, under your control.
Free download
40 checkpoints in 9 blocks show whether your agent is inventoried, tested, approved, monitored and reversible. A free PDF, no email required.
In-house · Agent Ops
Before we build agents for clients, we run them in our own company, with the same quality and release controls we implement for our clients.
Our own benchmarks, October 2026. The routing benchmark uses 60 realistic requests with fixed reference labels (measured before operations cases were added).
Hard stacks
The enterprise stack we have delivered on — and the agent stack we run ourselves.
We know these landscapes from the inside. Each page shows which agents make sense there and what has to be in place.
Where we are
Novaeon Studio, or simply Novaeon, is a Romanian AI agent studio. Our registered office is in Sat Dudu, Chiajna, Ilfov, directly at the western edge of Bucharest, Romania. We work with companies in the Bucharest area, across Romania and across the EU.
Questions
No. SAP is where our release discipline comes from and where agents are hardest to get right, but we build agents, skills and integrations on any stack — including fully self-hosted models.
There is no standard Joule path for on-premise S/4HANA or ECC today; SAP ties it to cloud editions and specific contracts. The readiness check tells you what is possible in your landscape — and which agents you can build without waiting for Joule.
Every change to an agent — prompt, model, tool, data source — goes through versioning, a fixed eval baseline, a risk rating and an approval, with a known-good release to roll back to. Like ChaRM, for agents.
Yes. We build on local and self-hosted models when data must not leave your infrastructure, and we scope every tool an agent can reach.
With a 30-minute Agent Strategy Call, then an audit. You decide after the audit whether and what we build.
We don’t train foundation models. On Hugging Face we have published an open dataset of synthetic agent change requests and a LoRA adapter for Qwen3-4B trained on it. We offer dataset creation, evaluation sets and LoRA fine-tuning of open models as a service. Our other public Hugging Face builds are quantised versions of open models, and every model is tested against a fixed gate before it goes live.
AI assistant of Novaeon Studio
AI assistant — may make mistakes. Answers come only from this website. Chats are stored for 30 days, without your IP address, to improve the answers. Privacy