# Tools · Avtoris

> What Avtoris builds with: AI agents, a proven stack and own tools such as the AI Visibility Check.

What we build with, and what we build ourselves.

[How we build](https://www.avtoris.studio/en/tools#methode)

Tools

Good tools are boring. We choose proven technology and use AI where it really saves time.

Method

## How we build with AI

We design the system, the models and the tests. AI agents write most of the code. The responsibility stays with us.

1.  01

    ### System

    First we design the system: data, processes, limits. On paper, before any code.

2.  02

    ### Tests

    We define how we see that it works. The tests come before the code.

3.  03

    ### Agents

    AI agents, above all Claude Code, write a large part of the code. Fast and by our rules.

4.  04

    ### Review

    Every change goes through review, tests and measurement. Only then does it go live.

Stack

## Our technology

No framework of the week. These are the tools we really build with.

*   ### Web · Websites and apps

    Static pages where possible. Servers only where needed. That makes websites fast and cheap to run.

    *   Astro
    *   Next.js
    *   TypeScript
    *   Tailwind CSS
    *   HTML
    *   CSS
*   ### Data · Models and analysis

    Forecasts, simulations and tests on data the model has never seen.

    *   Python
    *   Time series
    *   Monte Carlo
    *   Backtesting
*   ### AI · Agents and assistants

    We use AI for code, research and automation. In client projects it answers only from checked sources.

    *   Claude
    *   Claude Code
    *   Groq API
    *   Agent APIs
*   ### Operations · Hosting and versions

    Every change is versioned and has a preview before it goes live.

    *   Vercel
    *   Git
    *   GitHub

Own tools

## Built by us

Tools from our projects and from the team. Some are open on GitHub.

*   [In use · · AI Visibility Check · Checks which AI crawlers read a website and what AI systems say about a company. The base for our audit. · To the offer](https://www.avtoris.studio/en/offerings#ki-sichtbarkeit)
*   [In QFT · · Forecast engine · Six models, a walk forward backtest and 2000 Monte Carlo paths. It calculates the daily budget in QFT. · To QFT](https://www.avtoris.studio/en/ventures#qft)
*   [Open source · · Basketball Checker · A board game with its own bot. A linear model rates every move. Tested with 5000 simulated games. · Code on GitHub ·](https://github.com/DjordjeMojsilovic/basketball_checker)
*   [Open source · · AssistantHub Pro · A desk assistant on an ESP32 with AI chat, Telegram bot, web UI and habit tracking. 3368 lines of C++. · Code on GitHub ·](https://github.com/DjordjeMojsilovic/AssistantHub-Pro)

## Tell us what you are planning.

[Start a project](https://www.avtoris.studio/en/intake)

---

Quelle: https://www.avtoris.studio/en/tools · Überblick für Agenten: https://www.avtoris.studio/llms.txt · Kontakt: djordje.mojsilovic@avtoris.studio