RoboCoders: Judgment Day – AI Coding Tools Face Off at JFokus 2026
Abstract
Can AI-powered coding tools take software development to the next level? Unlike traditional code assistants that provide suggestions or guidance, AI-driven coding tools like JetBrains Junie and Kiro promise to act as full-fledged agents capable of handling entire workflows. In this live showdown, we’re putting that promise to the test by challenging these tools to build a smart light bulb controller—something we’ve never developed before. From setting up the project and implementing features to testing, debugging, and optimizing, the AI will take the reins. The audience will decide the winner based on how well the tools perform and, of course, whether the demo actually works. Join us to see if AI coding tools can deliver on their bold promise of transforming development, or if they’re just another stepping stone on the path to something bigger.
Resources
- The Birth of Vibecoding
- Intent Integrity Chain Presentation
- Spec-kit with skills completed demo
- Kiro completed demo
- GitHub Spec-kit
- Baruch’s Spec-kit fork with skills and IIC
- Spec-kit in Tessl Registry
- OpenSpec
- Skills support in Claude Code
- Skills support in OpenAI Codex
- Skills support in Gemini CLI
- Tessl - Package Manager for Skills
- Kiro IDE
- Baruch’s books
- Viktor’s Books
- Confluent + Apache Flink
- Shelly Smart Home
- Shelly API Reference
- Context7 MCP