Agentic Engineering

2026-03-24 · Source: Beyond Jupyter | TransferLab — appliedAI Institute · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

A full-day, hands-on course titled "Agentic Engineering with Claude Code" will teach participants how to effectively manage coding agents for application development and codebase refactoring. The course focuses on practical workflows to plan, steer, and verify AI-generated code changes, addressing potential issues like poor or incorrect output. It covers turning tasks into clear instructions, managing context for Claude Code, applying customization, mitigating risks related to sensitive data and licensing, and utilizing Claude Code's tools and extensions. The curriculum includes practical agentic workflows for both new (greenfield) and existing (brownfield) projects, incorporating planning, checkpoints, verification, and session handoff.

Key takeaway

For software engineers and AI engineers seeking reliable coding agent workflows, this course offers practical methods to manage Claude Code effectively. You will learn to plan, steer, and verify AI-generated code, mitigating common failure modes and ensuring high-quality output. This training is crucial for anyone prototyping new code or maintaining existing codebases with AI assistance.

Key insights

Effective agentic engineering requires structured workflows to plan, steer, and verify AI-generated code.

Principles

• Curate usable context to avoid overload
• Mitigate risks like sensitive data exposure
• Apply checkpoints and verification

Method

The course employs a structured approach: short instruction, live demonstration, guided hands-on exercise, and brief discussion/Q&A for each topic block.

In practice

• Turn coding tasks into clear instructions
• Customize Claude Code for project conventions
• Use tools for greenfield and brownfield work

Topics

• Agentic Engineering
• Claude Code
• AI-generated Code
• Code Refactoring
• Context Management

Best for: Software Engineer, AI Engineer, Machine Learning Engineer

Related on AIssential

• How to Write Robust Code with Claude Code — Automated robustness in agent-generated code is achievable through structured prompting and verification.
• Build with Claude Code: New Cohort Launch — An intensive course teaches engineers to build production-ready applications using Claude Code's agentic capabilities and advanced development techniques.
• How to Refactor Code with Claude Code — Continuous code refactoring is vital for maintaining the effectiveness and accuracy of AI coding agents.
• Applying an Agentic Coding Tool for Improving Published Algorithm Implementations — Agentic coding tools can significantly improve published algorithm implementations across diverse domains within a single workday.
• My cheatsheet for a clean context — Effective coding agent use requires mindful context management, precise prompting, and systematic debugging.
• .agent folder is making claude code 10x better... — Optimizing LLM context through structured documentation and sub-agents dramatically improves coding agent performance.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Beyond Jupyter | TransferLab — appliedAI Institute.