Question 1

How does a project with Quell-Code work?

Accepted Answer

After an initial call we analyse goals, data and processes, propose an architecture and estimate the effort. We then build in short iterations with working increments, test, go live and, if you like, continue to run it.

Question 2

What does a project cost?

Accepted Answer

It depends on scope and complexity. A focused prototype costs considerably less than a full platform. After the initial call you receive a transparent estimate, optionally as a fixed price.

Question 3

How quickly can you start?

Accepted Answer

Usually within a few weeks. An initial no-obligation call is often possible within the same week.

Question 4

Do you work remotely or on site?

Accepted Answer

Mostly remotely with fixed meetings and short paths. Workshops or on-site installations can be arranged.

Question 5

Who owns the source code?

Accepted Answer

You do. You receive code, documentation and all access — no lock-in.

Question 6

Is our data enough for AI?

Accepted Answer

For RAG assistants a few hundred documents are often enough. Custom machine learning models need more examples — we check this honestly up front.

Question 7

Which AI models do you use?

Accepted Answer

Depending on requirements the OpenAI API, other cloud providers with EU hosting or open models running locally on your hardware. We are not tied to any vendor.

Question 8

How do you prevent wrong AI answers?

Accepted Answer

With RAG and mandatory citations, clear system instructions, automated tests with real questions, confidence thresholds and approval steps for critical actions.

Question 9

Can you add AI to our existing software?

Accepted Answer

Yes. We integrate AI features via API into existing web, mobile and desktop applications — whether PHP, Node.js, Java, Kotlin or Swift.

Question 10

Where is the data stored?

Accepted Answer

Wherever you decide: on your own servers, with a German or European host or — if you prefer — in a cloud of your choice.

Question 11

Do you handle maintenance and hosting?

Accepted Answer

Yes. We set up servers, harden them, monitor operations and apply updates — or hand everything over to your IT.

Question 12

Do you take over existing projects?

Accepted Answer

Yes, including older codebases. We assess the state, fix critical issues first and modernise step by step.

Question 13

What does Quell-Code do?

Accepted Answer

Quell-Code is a software engineering company focused on artificial intelligence. We build AI agents, RAG systems and automations, install local language models and develop web and mobile apps as well as the server infrastructure behind them.

Question 14

Can AI models run locally without the cloud?

Accepted Answer

Yes. Open language models can run on your own hardware. We pick model size and quantisation to match your server or GPU, connect your documents via RAG and deliver an internal interface or API — with no data flowing to third parties.

Question 15

Which technologies does Quell-Code use?

Accepted Answer

Among others Python, TypeScript, JavaScript (React, Vue, Nuxt, Next.js, Node.js), PHP/Laravel, Kotlin, Java, Swift, Objective-C, Dart/Flutter, React Native, Lua, T-SQL, MySQL, MongoDB, SQLite, TensorFlow.js, OpenCV, WebSockets, Asterisk and Linux and Windows servers.

Question 16

How does a project start?

Accepted Answer

With a no-obligation conversation about your goal and starting point. You then receive an assessment of feasibility, architecture and effort. We build in short iterations with working increments.

FAQ on AI projects & software developmentClear questions, clear answers.

Working together

Artificial intelligence

Technology & security

Let’s talk.