VIGCON2026

Robotic Process Automation (RPA) is now a well-established technology used across many industries, and it has taken root within VIG as well. Thanks to RPA, colleagues at Kooperativa and ČPP are freed from repetitive, tedious tasks that software robots can perform faster, more reliably, and virtually 24/7.

In this talk, we will explore how RPA works in practice, which types of processes we automate, how our approach may differ from that of other companies, what impact AI and large language models may have on the future of RPA, and how the role of software robots might evolve in an AI-driven world.

Benefits

• ●Rapid prototypes with real components
• ●Demonstration of complex business requirements
• ●Reduction of manual work

Implementation

• ●Online documentation (vigo.vig.cz)
• ●Guidelines for AI tools

Two tools

Windsurf: Structured generation with React → basis for development
Make: Creative variants for solution finding

Examples

Life calculators (Windsurf) | Reports (Make)

Outlook

Figma Connect → closed iteration between AI generation and Figma

Implementation experience (Neuron, Experta, EOP)

Challenge to keep our platform apps universal

• ●screenshots, why microFE, universality of search and display

Transition from Camunda specific to platform agnostic

• ●adapters

ZenBPM as reaction to operation complexity and pricing of Camunda 8

• ●financial flexibility
• ●special operations requirements (DC3- without business data), transparency, backup/restore
• ●Zeebe shortcomings

/content depends on OPS/DevOps part and ZenBPM approval at IK

/OPS topic: Camunda Enterprise experience ? (transition from K8s to VMs, EntraID)

Starting with a single sentence from business, we expose the critical gaps that emerge: scope ambiguity, technical tradeoffs, and implementation uncertainty. By exploring two contrasting solutions — one minimalistic, one maximalistic — we demonstrate why a specification must go far beyond the initial ask.

We then walk through the process of extracting a coherent business specification from vague requirements, and the transformation into a technical specification optimized for AI-assisted coding. Finally, we cover essential guidelines and coding standards that keep AI-generated implementations maintainable, scalable, and aligned with the technical vision.

In this session, we will explore how modern AI workflows can significantly speed up software development and enable a one-shot approach to delivering business requirements.

Building blocks

• ●Rules and guidelines
• ●Sub-agents
• ●AI skills
• ●Slash commands
• ●MCP servers

Hands-on workflow

We will demonstrate how these AI features are implemented in our frontend development AI workflow. Using a real-world example, we will show how a business request can be transformed into a working solution in a single shot—faster, more consistently, and with minimal manual effort.

Rolling out AI in a 300+ FTE software house is not a tooling problem - it is an organizational transformation. We led the shift from isolated experiments to company-wide AI adoption, navigating skepticism, security concerns, developer productivity, and cultural change. This talk shares practical lessons from the front line: what actually worked, what failed quietly, and how leadership decisions, incentives, and guardrails determined the outcome.

Introduction

• ●Motivation and context for automated test generation
• ●Benefits: speed, consistency, maintainability

Junie and Guidelines – Overview

• ●What Junie is and how it works
• ●How guidelines influence test generation

Project Example

• ●Reference project and relevant structure
• ●Key testing guidelines overview

Supported Test Types

• ●API, DB, and Kafka test generation
• ●Multi-technology test scenarios

Test Generation Process

• ●Steps to generate tests with Junie
• ●Inputs and review of generated tests

Example: Jira Xray to Automation Test Framework

• ●Practical demonstration