[2604.17460] Agentic Education: Using Claude Code to Teach Claude Code

Computer Science > Computers and Society arXiv:2604.17460 (cs) [Submitted on 19 Apr 2026 (v1), last revised 30 Apr 2026 (this version, v2)] Title:Agentic Education: Using Claude Code to Teach Claude Code Authors:Zain Naboulsi View a PDF of the paper titled Agentic Education: Using Claude Code to Teach Claude Code, by Zain Naboulsi View PDF HTML (experimental) Abstract:AI coding assistants have proliferated rapidly, yet structured pedagogical frameworks for learning these tools remain scarce. Developers face a gap between tool documentation and practical mastery, relying on fragmented resources such as blog posts, video tutorials, and trial-and-error. We present cc-self-train, a modular interactive curriculum for learning Claude Code, an agentic AI coding tool, through hands-on project construction. The system introduces five contributions: (1) a persona progression model that adapts instructor tone across four stages (Guide, Collaborator, Peer, Launcher), operationalizing Gradual Release of Responsibility for AI-mediated instruction; (2) an adaptive learning system that observes engagement quality through hook-based heuristics and adjusts scaffolding at two timescales, using streak detection for mid-module intervention and aggregate metrics for module-boundary persona changes; (3) a cross-domain unified curriculum in which five distinct project domains share identical feature sequencing, enabling transfer learning; (4) a step-pacing mechanism with explicit pause primitives...