RoboCon Online

Workshop Goal:
This workshop will show you how to integrate generative AI (OpenAI and Gemini) with Robot Framework. Together we will create a simple Python library, connect it with Robot Framework, and explore how LLMs can boost your testing workflows.

Key Objectives:

• Learn how to connect Robot Framework with modern AI models
• Generate test documentation and keyword descriptions automatically
• Create dynamic test data on the fly
• Experiment with working files as context for AI
• Understand how to extend Robot Framework with custom Python libraries

Knowledge Level:
Basic Python coding skills and prior experience using Robot Framework. You should be comfortable writing simple functions in Python and running Robot Framework tests. This workshop is aimed at intermediate automation testers and developers who want to explore AI-powered testing.

Workshop Agenda (09:00–17:00):

1. 09:00 – 09:30: Introduction – AI in testing, OpenAI and Gemini models, integration options
2. 09:30 – 11:00: Building a Python Library – Live coding session to create a simple AI-powered library
3. 11:00 – 12:00: Integrating with Robot Framework – Connecting the library to Robot Framework and running tests
4. 12:00 – 13:00: Lunch Break
5. 13:00 – 14:30: Working with Generative AI – Generating test data, documentation, and test cases dynamically
6. 14:30 – 16:00: Hands-on Exercises – Extending the examples and experimenting with custom ideas
7. 16:00 – 17:00: Wrap-up & Q&A – Best practices, limitations, and discussion

Preparation and Technical Requirements:

• Installed Python 3.10+
• Installed Robot Framework
• Basic IDE or editor (PyCharm, VSCode, etc.)
• API keys for OpenAI and Gemini (will be provided by us for the workshop day)

Description

Unlock the power of Robot Framework’s lesser-known dynamic and hybrid library APIs.

As automated testing scales across large, integrated systems, test frameworks must strike a balance between clean usability for testers and modular maintainability for developers. In this workshop, we’ll explore how Robot Framework’s dynamic library API enables just that.

Imagine testing dozens of RESTful services: user, orders, payments and many, many more. You also need to deal with authentication & authorization. With static libraries, you'd need a tangle of imports and exposed implementation details in every test suite. Instead, we’ll show how to build a single, unified RF library that dynamically loads service-specific Python modules at runtime. This allows test authors to use concise, readable test cases like Create New User or Verify Payment Received through one import, regardless of where the logic lives under the hood.

You’ll learn when and why to choose dynamic (or hybrid) libraries over static ones, how to implement them cleanly, and how this approach empowers cross-functional teams to scale their test automation without creating a mess.

This workshop is designed for test engineers and automation developers who want to move beyond simple static libraries and build flexible, scalable, and maintainable keyword libraries. Through a hands-on example based on REST API testing, you’ll learn how dynamic libraries work under the hood, when and why to use them, and how to structure Python-based libraries that expose clean, unified interfaces to test authors.

Key Takeaways

• Understand the differences between static, dynamic, and hybrid libraries in Robot Framework.
• Learn when and why to use dynamic or hybrid libraries in real-world test automation projects.
• See how Robot Framework discovers and executes keywords at runtime through the dynamic and hybrid API.
• Build maintainable dynamic and hybrid libraries that pulls together multiple Python modules under one import.
• Write clean, high-level test cases while keeping the complexity hidden in well-structured code.

Knowledge Level

• Robot Framework: Intermediate (understanding of test case syntax, keyword usage, and test suite structure)
• Python: Intermediate (modules, classes, methods, basic Python syntax)
• HTTP/REST APIs: Basic understanding of REST concepts and HTTP verbs (GET, POST, PUT, DELETE)
• Python Requests Library: Preferable, but not required (we will walk through usage in examples)

Agenda

1. Introduction

• 1.1 Why RF scripting isn't always enough
• 1.2 Introduction to the RF library APIs: Static vs. Dynamic vs. Hybrid
• 1.3 Taking a peek under the hood

2. Use Case: REST API Testing Framework

• 2.1 Overview of the demo application (multi-service REST API)

3. Static Library

• 3.1 Build the library
• 3.2 Using the Library in Tests
• 3.3 Limitations of the static approach

...

Kick off RoboCon Online with Miikka and René sharing Foundation updates and community highlights, followed by Pekka Klärck presenting the latest developments and roadmap for Robot Framework.

For a major bank in Germany, we built a comprehensive test automation solution for SAP landscapes using Robot Framework — designed to enhance consistency, traceability, and speed in quality assurance within a highly regulated banking environment.

The solution automates end-to-end SAP workflows, including:

• Data mapping validation across applications
• Inbound and outbound interface checks
• Verification of data initialization
• Validation of regulatory reports

Existing test cases are automated with Robot Framework and integrated into a CI/CD pipeline. Test results are automatically synchronized with Jira/Xray test executions via the Jira API, ensuring full traceability across requirements, tests, and defects.

The automation also performs formal validation of test artefacts in Jira (test cases, test plans, and test executions) and generates comprehensive reports using Jira Structure.

We also leverage Generative AI to support and enhance the test automation process. A key differentiator is our AI-driven quality assurance: a business-centric Pull Request Analyzer verifies whether pull requests align with corresponding Jira user stories, ensuring functional accuracy and completeness.

AI-based checks further validate both manual and automated test scripts — evaluating their structure, completeness, and clarity against internal quality standards and coding guidelines. This ensures high-quality documentation, easier maintenance, and more reliable test implementation.

In this talk, we will share our journey of integrating Robot Framework with SAP testing, CI/CD, Jira/Xray, and AI-based quality assurance. Attendees will learn how to scale Robot Framework in enterprise SAP environments and how AI can elevate both automation and documentation quality.

Hi, our names are Niels Janssen and Elout van Leeuwen. We’re test automation engineers and for the past year we worked for the Employee Insurance Agency (UWV) in The Nederlands. UWV is known for it’s microservice landscape. These microservices mostly interact with the help of IBM MQ (message queues). A message queue is essentially a mailbox. A simple example could be that one application puts something in the mailbox, while another application can get things out of that mailbox.

The advantage of using IBM MQ is that not both services need to be up and running all the time to communicate (asynchronous). Instead, we use the message queue. Now one application can put a message on the queue and can go offline, while the other application can get the message from the queue whenever it goes online. There are way more cases and variations to use message queues, this is just a simple explanation to be able to grasp the concept.

IBM MQ is still one of the most used message queue middleware applications to date within government corporations. While working with message queues at my current client, we noticed a lack of support for automating message queues with Robot Framework. Because of this shortcoming, we saw workarounds to simulate queues, for example by forcing services to use a windows directory as the “queue” and placing “messages” into that folder. Other services were configured to read from this directory instead of a real queue, and tests/assertions were done on the files within these directories.

But offcourse this is not ideal because within testing we should always strive towards a test environment that is as close to the production environment as possible, as discussed in the TMAP literature. In our search for a suitable solution we did stumble apon a Python package called ‘pymqi’ with which automating of IBM MQ is possible, but this was not yet properly integrated into the robot framework ecosystem. This is why we created the robotframework-ibmmq. robotframework-ibmmq acts as a wrapper for ibmmq and makes interacting with queues possible directly from within Robot Framework.

Modern QA teams generate thousands of Robot Framework test logs and reports, but extracting meaningful insights from them — especially identifying and documenting bugs — remains a manual and time-consuming process.

This session presents a novel AI-driven Bug Clarification and Creation framework, leveraging Large Language Models (LLMs) to automatically interpret Robot Framework outputs and turn them into structured bug reports.

Key topics covered:

Parsing and enriching Robot Framework test results with metadata (suite, test, logs, screenshots).

Using LLMs to analyze failure patterns and generate human-readable bug summaries.

Intelligent bug classification: functional vs. performance vs. environment issues.

Automated bug creation: seamlessly pushing reports to TFS, Jira, or any modern ALM tool via APIs.

Integration patterns and architecture design for hybrid setups (on-prem or cloud).

Real-world demo: converting a Robot Framework test log into a detailed, ready-to-triage bug ticket.

Takeaways:

Learn how to connect Robot Framework’s structured outputs with LLM reasoning.

See practical steps to automate defect triage and documentation.

Understand how this approach reduces human effort, increases accuracy, and accelerates release cycles.

This talk is ideal for QA engineers, automation leads, and AI enthusiasts seeking to bridge the gap between test automation and intelligent defect management.

What's new with RFSwarm

• New features that have been added
• Contributions to RFSwarm by NiceProject and introduce Arkadiusz, he will give a short talk about his contributions and the benefits of contributing to robot framework ecosystem projects
• RFSwarm tutorial videos
• RFSwarm LinkedIn group Where we are headed with RFSwarm.
• Planned features
• More tutorial videos

Robot Framework SchemathesisLibrary, what it is for and why I did it? RoboCon 2025, there was many talks which pointed me to look at Schemathesis project direction. After some reading and trying the Schemathesis out with some dummy projects, I tough that Schemathesis project looks really interesting. I tough this because Schemathesis promises to automatically generate thousands of test cases from OpenAPI or GraphQL schema and finds edge cases that break your API. It also nicely fits for me, because I have blank spot in API testing. Although I am familiar with APIs and have done some API testing in the past, I am not very proficient with OpenAPI schemas.

When I did start creating SchemathesisLibrary, I did set out few goals for me. First I should learn how to build a REST service with modern Python tools and how using OpenAPI schemas enables automatic test case generation. Secondly this project should give me better backgorund when talking at work about building RESt services and why doing an OpenAPI schema is an good idea.

Did I achieve all my goals, well to be honest, only partially. But along the way building the SchemathesisLibrary and discovering features from Schemathesis, Robot Framework, DataDriver and many other things. So although I did not reach all my goals, I along the way I did discover new paths to discover and learn. In conclusion, the project can be considered successful from my perspective and I hope that it is also usefull for the community.

Automation in Geographic Information Systems (GIS) is increasingly essential for ensuring consistency, reliability, and efficiency in spatial data processing and map-based software testing. This paper presents a comprehensive approach to automating user interface (UI) operations and tests within the very top open-source QGIS (Quantum GIS) using the Robot Framework. The focus is placed on automating map interactions, such as creating, editing, and validating spatial features - including points, lines, and polygons - directly within the QGIS Desktop graphical environment. The proposed automation framework integrates QGIS locators (Qt5, Qt6) as UI objects, PyWinAuto and PyAutoGUI python libraries to automate UI operations, and Robot Framework for design, execute and report tests. By combining above technologies, it allows to automate workflows that typically require extensive manual effort, such as digitizing vector layers, snapping features, setting symbology, and performing topological validation. Through the Robot Framework’s structured and modular test design, each QGIS UI action - like drawing geometries (example: drawing river as a line on map canvas) - can be expressed as reusable, human-readable test keywords. These keywords abstract low-level operations, enabling QGIS analysts or Geographers to build complex automated scenarios without deep programming expertise. Overall, this work contributes to the field of geospatial software engineering by providing a replicable strategy for automating tests of spatial UI workflows, especially for Plugins in open-source GIS platforms. It highlights how the Robot Framework streamlines quality assurance processes, accelerate development cycles, and enhance the reliability of spatial data operations. The result is a powerful, flexible testing solution that empowers GIS professionals and developers to ensure that map creation, editing, and analysis tools function correctly across diverse environments and datasets - without the need for repetitive manual validation.

Since keywords are the fundamental building blocks of tests, RoboView specifically concentrates on them. The objective of this approach is to provide users with a clear and organized display. Both tabular representations and visual views in the form of graphs are utilized, allowing users to quickly gain an overview and then conduct more detailed investigations at a granular level.

The tool will be offered as a VSCode extension, as the Robot Framework community predominantly uses extensions in this format. This approach enables us to reach the majority of users for RoboView. Additionally, providing it as a VSCode extension allows for straightforward installation and usage of our tool.

Join the live-streamed panel discussion hosted by Joe Colantonio!

The main topic is Robot Framework and AI, but the audience may engage throughout the session and ask questions to the panel.

Over the past year, RobotDashboard has evolved from a simple visualization tool into a mature open-source project that helps teams turn Robot Framework test results into actionable insights. In this session, I will share lessons learned from building, maintaining, and growing RobotDashboard. This includes challenges faced when supporting multiple Robot Framework versions, incorporating community feedback, and deciding which features to implement and prioritize. These experiences offer valuable insights into maintaining an open-source project, balancing user needs with technical constraints, and ensuring long-term usability and adoption.

I will also highlight the new features that make RobotDashboard more powerful and flexible than ever. These include custom database integrations, which let teams store test results in a way that fits their infrastructure; built-in server capabilities, enabling real-time access to both the database and the dashboard; customizable layouts, allowing teams to tailor the dashboard to their needs; and an improved interface, providing faster and more intuitive navigation of complex test results.

The session will also show how these enhancements translate into deeper, data-driven testing insights. Attendees will see how RobotDashboard can help spot flaky tests, identify long-running suites, detect regressions earlier, and analyze trends across multiple test runs. By combining historical data with the new features, teams can move from simply reporting test outcomes to understanding patterns and making better testing decisions.

Through practical demonstrations, real-world examples, and lessons learned from maintaining an open-source tool, this talk will provide attendees with both inspiration and actionable takeaways for improving their testing workflows. You will leave with a clear understanding of how to extract more value from your test results using RobotDashboard.

An overview of the recent funded development work on Robocop and Robotidy. The session highlights key improvements, ecosystem integrations, and what this means for Robot Framework users.

In modern software development, the integration of test automation into test management is a key success factor for quality assurance acceptance. In this talk we will present RoboMonX: a novel solution for the dynamic linking of test results from the Robot Framework with the test management tool Xray for Jira.

In contrast to conventional approaches, which require the results to be transferred at the end of the test execution, RoboMonX enables an incremental and event-driven update of the test plan in Xray. Each single test case is submitted to Xray immediately after execution, providing a real-time status of test progress and results in the test management system.

RoboMonX addresses the limitations of traditional integration approaches and offers significant benefits in terms of transparency, responsiveness and efficiency of the test process. The early detection of deviations and the continuous availability of up-to-date test results provide support for informed decision making in the development process.

Problem definition: Inefficient test reporting and delayed feedback of automated test case results, making it difficult to respond to defects in a timely manner.

Our approach: Development of a customized integration solution between Robot Framework and Xray using event-driven mechanisms for real-time transmission of test results.

Results: Increased transparency and dynamic visualization of test progress in Xray. Early detection of inefficiencies and potential risks in the test process. Improved decision making through timely availability of test results. Potential for increased efficiency and quality in software development.

Target Audience: The talk is aimed at professionals in the field of software development and quality assurance, test automation experts, developers QA Leads and product owner dealing with current test management challenges and solutions.

During the talk we will present RoboMonX and the results achieved but also discuss the potential for future developments.

As a Technical Pre-Sales Professional and Advisory Automation Solution Architect, I often work with global clients on automation proposals and consulting engagements. Provided the right fit, it’s relatively easy to convince technical teams to use Robot Framework, but the real challenge lies in influencing leadership and business stakeholders — who often make final decisions based on factors like cost, support, and ecosystem dependencies.

In this Talk we will go over a full length process of how we can understand an Automation ecosystem and how we can convince both Company and Client management in using Robot Framework.

In this talk, we’ll walk through a complete process for understanding an organization’s automation landscape and effectively positioning Robot Framework as the right choice — both technically and strategically.

We’ll explore key unique selling points (USPs) of the framework, including:

Ease of use Flexibility and adoptability Support for various tech stacks Extensive library ecosystem Availability of ready made libraries Space for Cusomization Vast community support Comparison with other Licensed and low code tools in the Market

This session aims to equip Robot Framework enthusiasts and practitioners with practical insights on how to make a compelling pitch into using Framework.

KeyTA is a simple web interface designed with the goal of allowing anybody to quickly get started using Robot Framework. It is optimized for user comfort and thus aims to provide a fast feedback loop. In particular, individual keywords can be directly executed and test cases can be resumed from the step that failed.

KeyTA was born out of the necessity to enable domain experts with no programming knowledge to leverage Robot Framework to automate processes and tests. They are used to working with graphical user interfaces (e.g. Excel, SAP) and they want to stay in this familiar environment when automating tasks they usually perform by hand.

KeyTA is being developed at NRW.Bank, the state development bank of the federal state of North Rhine-Westphalia in Germany, and a member of the Robot Framework Foundation. The core of the application was released by the bank as open-source software and imbus continues its development on GitHub.

This talk will provide a live demo that should serve as an introduction for new users. A short test case will be created from scratch using the Browser library. Along the way several features of KeyTA will be illustrated and the advantages of using it for web automation will become apparent.

Like many teams, we used to treat UI tests as something that must be green. For months after introducing them, the PyCharm QA team fought flakiness, managed mutes across environments, and tried to keep up with monorepo changes from hundreds of developers. We shifted to monitoring trends instead of day-to-day statuses and chose a bird’s-eye view of the system over inspecting single failures in a specific build or environment.

This talk shares our approach and the lightweight tool that enables it. The TestKeeper Service is a 100% vibe-coded solution with no FTE spent. Its stateless architecture builds views in real time from API requests, with no deployment or database maintenance. Instead of showing which tests failed, our service focuses on trends, highlights similar failures, and draws attention to cases where we should reproduce the failure manually.

Attendees will learn the following:

• The workflows we developed to enable the observability approach and complement the tool: recognising typical patterns of trends, standard steps to reproduce the issue, and distinguishing problems in the product from defects in tests
• Real cases from PyCharm: how we manage to spot and catch regressions against the background noise of flakiness
• Guardrails that we use to balance extending the coverage and fixing defects in tests, in addition to our overall approach to developing new tests
• How a stateless, zero-FTE, API-based service can deliver a significant impact, and how to apply a similar design in your context

The main goal of the talk is to provide evidence that observability over stability is a valid direction for developing a testing framework, especially for UI tests and complex systems. I want to show colleagues a better alternative to spending man-hours on fixing flaky tests, and how a vibe-coded internal tool became a game changer in the quality assurance infrastructure of PyCharm.

"Let me quickly fix that test before I log off for the day". Before you know it, it's 20:00, you're still running tests, you're really hungry for some inexplicable reason, you see the tests doing the same thing over and over again, you're ready to throw your laptop out of the window, if it would only open but even the window is being difficult (your phone is blowing up), the doorbell rings, and aâ̶̊ͅar̷̡̟͋̕͠g̵̣̰̫̉̆͠hh̸͖͙̃̈h!

Bad test performance is a universal annoyance. "Quickly" running some tests can take forever. But it can also be really hard to figure out how to speed things up. The result? Blankly staring at your screen, getting distracted, and annoyance slowly building up until you ~rage quit~ give up for the day.

To rid myself of this frustration, I make my tests faster. Fundamentally, there are only 2 core principles to speeding up your tests without impacting their contents:

• Do things simultaneously — Maximize CPU usage
• Do fewer things — Reduce CPU time

Caching is a way of doing fewer things. In Robot Framework, there are 5 levels of caching:

1. Test variable Store a value and reset it when the test finishes.
2. Suite variable Store a value and reset it when the test suite finishes.
3. Global variable Store a value and reset it when the test run finishes.
4. Pabot variable Store a value, share it with parallel test runners, and reset it when all tests finish.
5. Cache file Store a value, share it with parallel test runners, share it with the future test runs, and reset when the expiration time has passed.

Drawing from a real refactoring project, this talk provides concrete techniques for breaking up global resource files with the assistance of AI.

Topics covered:

• How we got here: Background on why codebases often implement this practice.
• Motivation: Why reducing reliance on global resource files is desired.
• AI memory simulation: Track keyword and variable definitions to aid in import redistribution.
• IDE integration: Combine diagnostic tools with AI to guide refactoring.
• Context management: Handle AI limitations when working across many files.
• Import cleanup: Detect and address unnecessary imports AI may introduce.
• Practical validation: Balance thoroughness with practicality when checking AI output.

Statistics on the codebase size and complexity will be provided, helping participants assess how these approaches will scale to their own projects.

Most importantly, participants will be inspired to tackle similar work in their own codebases.

This presentation will give a high-level walkthrough and demonstration of how Robot Framework RPA can combine with local AI Agents, MCP, and various LLM types to enhance their capabilities. This talk will discuss the following main topics below.

• Brief introduction to the open source AI Agent, LLM, and MCP ecosystem landscape.
• Overview of Codename Goose (https://block.github.io/goose/), an open source AI Agent framework project developed by Block (Jack Dorsey's company).
• Talk about how Ollama (https://ollama.com/) can be used to setup a locally running private LLM instance on your own hardware.
• Walkthrough/demonstration of the basic design of using Robot Framework RPA to automate sequential tasks with Codename Goose on a local LLM that can run on anyone's hardware.
• Talk about the Codename Goose Docker container and give an overview of situations where some models are too big and demanding for anyone's personal hardware.
• Walkthrough of the basic design and building-blocks of using Robot Framework RPA to automate parallel tasks with parallel running Codename Goose Docker containers connected a cloud AI product such as Google Gemini.

This is the public GitHub repo containing all of the automation demonstrations mentioned above. https://github.com/jg8481/Robot-Framework-AI-Agent-Datadriver

Ed Manlove will close the conference with brief closing remarks and a big thank-you.

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.