FiveTech Software tech support forums

Hi Silvio,

just out of curiosity: you mentioned that you no longer program with Harbour and FiveWin.

What programming language and development environment are you using now? And what made you decide to switch?

Best regards,
Otto

Claude Code to the Max – and what is our role here?

In a very short time, we will be faced with an enormous amount of programs and apps – and often find ourselves not really knowing what to do with them. The biggest challenge will soon no longer be programming itself, but finding real testers and ...

Codex, Claude & Antigravity: Now with Full Session Tracking

Until now, our AI Dashboard has provided centralized logging for activities from Codex, Claude Code, and Antigravity.
With the latest update, we're taking visibility and traceability one step further:
Individual CLI sessions can now be ...

The IDE is becoming one tool among many. The real productivity gain comes from coordinating multiple AI agents while maintaining a clear overview of their output.

Running 3 AIs at the same time. One dashboard.

Waiting for a single AI to finish was slowing down my workflow, so I started working in parallel with Codex, CloudCode, and Anti-Gravity.

The problem?

When multiple AIs are generating answers simultaneously, it's easy to lose track of conversations ...

https://forums.fivetechsupport.com/viewtopic.php?p=285622#p285622

Why I Chose a Custom-Built Solution for the WINHOTEL Community Hub

When I look at the future of small software companies, I see two topics becoming increasingly important:

Customer Retention

Acquiring new customers is becoming ...

The Most Important Thing: Choosing the Right Problem

Many people ask about tools, methods, or resources. But the real question is:
Why do you choose a specific problem?
And how do you turn it into a solution that truly addresses customer needs?
This is where the core of entrepreneurship lies.

The ...

Warum ich für den WINHOTEL Treffpunkt eine Eigenentwicklung gewählt habe

Wenn ich auf die Zukunft kleiner Softwareunternehmen schaue, sehe ich zwei Themen, die immer wichtiger werden:

1. Kundenbindung

Neue Kunden zu gewinnen wird zunehmend aufwendiger und teurer.

Gleichzeitig entsteht der ...

If you work with multiple AI tools in parallel — ChatGPT for some things, Claude or Claude Code for others — you probably know the problem: every time you switch, you re-explain the project from scratch. That's the gap I'm trying to close with PE_EDITOR, a file-based "working memory" layer that sits ...

The context from which I approach these topics:

I started as a one-person company and today work with a small team.
WINHOTEL is a mature application that has evolved continuously over many years.
I operate and maintain a self-hosted infrastructure on my own servers.
GDPR compliance, data ...

Dear Antonio,

I think we fully agree on one important point:
The knowledge must be accessible.
An agent cannot work with information that it cannot see.

Where I currently think a little differently is in the areas of ownership, control and hosting.
For our environment, it is important that:
the ...

Dear Antonio,
yes, I understand the value of Git as project memory for source code.
But in my case the word “project memory” is broader than source code history.

Our daily work does not only consist of source code projects. It also includes operational data, customer-related information, personal ...

One thought that currently interests me a lot is the role of memory.
Modern AI systems are increasingly building memory, projects, agents and complete ecosystems around their models. This is useful, but it also creates a dependency on a specific provider.
My current idea with PE_EDITOR is therefore ...

Built a local AI Hub that lets me launch my favorite AI coding tools with one click.
No terminal commands to remember, no hunting for folders—just a clean desktop launcher for my development workflow.
Behind the scenes: exe-launcher.exe is a small Windows bridge built with Harbour.
It solves a ...

Strategy for the Next Month

Expanding our AI workflow is not about automating everything as quickly as possible. Especially in mature projects, full automation is not automatically the better solution.

The more practical approach is: semi-automated instead of fully automated.

In the next phase ...