ASE-26: a curriculum for agentic software engineering as a discipline
📰 ArXiv cs.AI
Learn how to direct agents as a software engineer with the ASE-26 curriculum, a crucial skill in the age of automation
Action Steps
- Direct agents using ASE-26 principles to automate tasks
- Apply agentic software engineering concepts to existing projects
- Configure agent-based systems for efficient workflow management
- Test and evaluate the performance of agent-directed systems
- Integrate ASE-26 into existing software engineering workflows
Who Needs to Know This
Software engineers and DevOps teams can benefit from this curriculum to upskill and adapt to the changing landscape of software development, where directing agents is becoming a primary responsibility
Key Insight
💡 The role of software engineers is shifting from writing code to directing agents, with automation accounting for 79% of interactions
Share This
🚀 Learn to direct agents with ASE-26 curriculum! 💻 #AgenticSoftwareEngineering #Automation
Key Takeaways
Learn how to direct agents as a software engineer with the ASE-26 curriculum, a crucial skill in the age of automation
Full Article
Title: ASE-26: a curriculum for agentic software engineering as a discipline
Abstract:
arXiv:2606.01152v1 Announce Type: cross Abstract: The work of a professional software engineer has begun to consist, increasingly, of directing agents rather than writing code, and the empirical evidence for the shift is now several years deep. Anthropic's Economic Index puts automation at 79 per cent of Claude Code interactions [2]; Handa and colleagues at Anthropic find AI exposure for Computer Programmer tasks at approximately 75 per cent of the role's distinct activities [3]; Brynjolfsson an
Abstract:
arXiv:2606.01152v1 Announce Type: cross Abstract: The work of a professional software engineer has begun to consist, increasingly, of directing agents rather than writing code, and the empirical evidence for the shift is now several years deep. Anthropic's Economic Index puts automation at 79 per cent of Claude Code interactions [2]; Handa and colleagues at Anthropic find AI exposure for Computer Programmer tasks at approximately 75 per cent of the role's distinct activities [3]; Brynjolfsson an
DeepCamp AI