Meet the winners of our Built with Opus 4.6 Claude Code hackathon

2026-04-20 · Source: Claude Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Emerging Technologies & Innovation · Depth: Intermediate, medium

Summary

Anthropic announced the winners of its "Built with Opus 4.6 Claude Code hackathon," showcasing five projects that leveraged the Claude Code AI model. First place went to CrossBeam, developed by a personal injury lawyer, which aims to streamline California's housing permit process by using AI to parse documents and generate action plans, potentially reducing 90%+ rejection rates and six-month delays. Second place was awarded to Elisa, a block-based visual IDE created by a software engineer for teaching programming to children, which allows users to design software visually while AI writes the underlying code. Third place recognized PostVisit.ai, a suite of tools by a cardiologist that explains diagnoses, analyzes visit notes, and surfaces clinical evidence for patients and physicians. Additional prizes went to TARA, a tool for road infrastructure investment appraisal, and Conductr, a real-time AI musical bandmate.

Key takeaway

For AI Engineers and product managers seeking to accelerate development or empower non-technical users, consider integrating advanced coding assistants like Claude Code. You can significantly reduce development time, as demonstrated by projects built in under a week, and enable domain experts to create complex applications without writing a single line of code, broadening your team's innovation capacity.

Key insights

Non-developers can create impactful AI applications using advanced coding assistants like Claude Code.

Principles

• AI can automate bureaucratic processes.
• Visual interfaces lower programming barriers.
• AI can accelerate product development.

Method

The hackathon participants used Claude Code for various tasks, including generating code, creating tests, and analyzing complex data like blueprints, medical notes, and dashcam footage, often without writing traditional source code.

In practice

• Use AI for document parsing and action plan generation.
• Develop visual IDEs for simplified coding.
• Integrate AI for real-time data analysis.

Topics

• Claude Code Hackathon
• AI-powered Permitting
• Visual Programming IDE
• Digital Health Solutions
• Road Infrastructure Assessment

Code references

• mikeOnBreeze/cc-crossbeam
• zoidbergclawd/elisa
• Kye256/tara-transport-assessment
• nanassound/conductr

Best for: AI Engineer, Software Engineer, Domain Expert

Related on AIssential

• Meet the winners of the Built with Opus 4.7 Claude Code hackathon — Claude Code and Opus 4.7 enable rapid development of complex, multi-agent AI applications across diverse domains, even for non-programmers.
• Claude Code Skills 101: Everything You Need to Get Started With — Claude Code Skills enable AI agents to dynamically load context and execute complex workflows, moving beyond static prompts.
• How a non-technical project manager built and shipped a stress management app with Claude Code in six weeks — Non-technical users can rapidly build and ship complex applications using AI code assistants like Claude Code.
• Claude Code is Now Writing Claude Code — AI infrastructure and coding capabilities are rapidly advancing, driven by massive investments and self-improving models.
• Claude Coded My Python Project for 3 Hours Alone — Claude Code operates as an autonomous agent, independently developing and debugging complex Python projects with minimal human intervention.
• What's going on with Claude Code? — AI models are rapidly transforming software development, shifting human roles from coding to supervision and taste.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Claude Blog.