I’m Miguel Diaz Kusztrich, a Spanish freelance software developer working in industrial software for automotive manufacturing logistics. My AI work began with an experiment: an AI-assisted chess database. It has since developed into a broader platform idea in which AI is part of how an application is operated, rather than a chatbot bolted onto it.
What I mean by integrating AI into an application
“I’ve been experimenting with AI integration in software applications for some time, not as an isolated chatbot feature, but as part of the application architecture itself,” I wrote in my DEV Community article. That distinction is the starting point for this work: instead of limiting AI to a separate conversation window, an application can make its own data and operations available to a model as part of a managed workflow.
As an Amazon Associate I earn from qualifying purchases.
This is my architectural approach, not a claim that it has been independently tested against chatbot-style features or other products. The application remains responsible for how work proceeds; AI is one way to interact with it.
The chess database experiment
The first concrete example was an AI-assisted chess database. I explored having AI assistants understand the database and support several kinds of interaction with it:
#1 Best Overall
- Search for games.
- Add commentary.
- Configure parts of the application.
- Play chess.
The experiment helped me see AI as another way for people to operate an application, rather than simply as an extra feature inside it. That is my reflection on the project, not a measured finding about accuracy, usability or performance.
From a chess project to a broader platform
My current direction is a more general, extensible desktop platform that brings AI, multiple databases and modular application components together. In the architecture I describe, the application manages context, exposes functions and resources to models, and retains control of the workflow. A model can work with application capabilities, but the application determines what is available and how the interaction fits into the broader task.
Rank #2
I have pointed readers to two videos: one demonstrating the chess database and another presenting the current architecture. They are demonstrations of the work as I describe it; the available material does not establish independent results for technical performance or production readiness.
Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallOutdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWhat this introduction does—and does not—establish
This is a description of a developer’s projects and architectural direction, not a product evaluation. It does not establish measures of model accuracy, speed, security, user adoption or effectiveness, and it does not claim the platform is released or production-ready. The point is the evolution of the idea: from experimenting with AI actions in a chess database to designing an application architecture in which models can use application data and capabilities under the application’s control.
Quick Recap
Best Value
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
