AI coding tools are everywhere, but most teams still struggle with the same question: how do we use them for real engineering work without losing quality, control, or trust?

This session is a practical, hands-on walkthrough of an AI-aided development workflow that engineers can actually apply on Monday. We’ll use a local fullstack project and build a real feature together while keeping quality gates in place from start to finish.

What you’ll see

• How to frame prompts so AI produces useful, reviewable code
• How to run test-first development with Robot Framework as the safety net
• How to implement a feature incrementally across backend and frontend
• How to validate each step instead of “hoping” generated code is correct
• How to keep human engineering judgment at the center of the process

Core idea

AI does not replace engineering discipline. It amplifies disciplined engineers. In this talk, AI is treated as a coding collaborator: fast, helpful, and fallible. Robot Framework tests are the contract that keeps implementation honest. Together, they create a workflow where speed and quality reinforce each other instead of competing.

Why this matters

Many teams experiment with AI coding but get stuck in one of two extremes:

• blind trust (“it compiles, ship it”)
• total skepticism (“AI output is unusable”)

We’ll show a middle path: high-velocity delivery with explicit quality controls.

We will practice automating a Login in a VMWare/VirtualBox Windows system and then doing some actions.

Contents:

• About Image Recognition Libraries - SikuliLibrary (and ImageHorizonLibrary)
• Knowing the Java based SikuliX IDE and its possibility to run Robot Framework test cases.
• SikuliLibrary: -- Installation -- Planning the Test Suites file structure -- Defining Test Cases and Resources -- Running Test Suites
• Combining SikuliLibrary keywords with ImageHorizonLibrary
• Practice in automating a Login in a VMWare/VirtualBox Windows system and then doing some actions.

About: Image recognition libraries are used to automate tasks or testing, when it is costly or difficult to obtain object identifiers in the applications under test. These libraries use Computer Vision (OpenCV) to match reference images with a copy of the computer screen, and also Optical Character Recognition (OCR) for text extraction. With these techniques and operation system actions like mouse movement and keyboard strokes, the system can replicate the actions of the human user.

SikuliLibrary is a Robot Framework library that allows to use the SikuliX Java API. It uses Robot Framework Remote to interface Python functions with the SikuliX Java libraries, so it needs to have Java Runtime Environment installed in your system. -- diagram from project: https://github.com/MarketSquare/robotframework-SikuliLibrary/blob/master/docs/img/architecture.png -- The usual workflow for a Test Case or Task is:

• Import SikuliLibrary and start its server
• Define the location for the reference images
• Start the Application Under Test (AUT)
• Interact with the AUT by actions of mouse, keyboard, matching of reference images on the screen, and Optical Character Recognition (OCR) for text extraction.
• Complete the workflow by stopping the server.

SikuliX IDE:

• Installation SikuliX IDE, which requires Java
• Creating and Running a Test Case with SikuliX IDE

SikuliLibrary:

• Installation
• Planning the Test Suites file structure
• Defining Test Cases and Resources
• Running Test Suites

ImageHorizonLibrary is a Robot Framework library, based on pyautogui and other Python modules, and optionally opencv-python for adjusting the image recognition precision. This library does not have Optical Character Recognition (OCR) keywords. Similarly to SikuliLibrary, it uses reference images to interact with the AUT on the screen. We can say that the usual workflow is the same as the one with SikuliLibrary, except for the server and OCR parts.

Combining SikuliLibrary keywords with ImageHorizonLibrary: -- Installation of ImageHorizonLibrary -- Adjusting Test Suites to use SikuliLibrary and ImageHorizonLibrary simultaneously (conflicting keyword names) -- Running Test Suites

Practice in automating a Login in a VMWare/VirtualBox Windows system and then doing some actions.