Problem
Research questions and friction points this paper is trying to address.
incidental learning
AI coding agents
knowledge debt
software development
developer expertise
Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development
🤖 AI Summary
This work addresses the unintended consequence of widespread AI programming agents: the erosion of informal, tacit knowledge that developers traditionally acquire through hands-on practice, leading to the accumulation of “knowledge debt” that jeopardizes long-term professional competence. To counter this, the paper introduces the novel concept of knowledge debt and presents SHIELD, a multi-agent system designed to reintegrate incidental learning into the software development workflow. SHIELD leverages the internal reasoning mechanisms of AI coding agents to deliver contextual, out-of-band learning prompts without disrupting developer productivity. Grounded in six design principles, the system fosters a learning-aware development environment centered on “pedagogical agents.” Prototype evaluation demonstrates that SHIELD effectively enhances developers’ understanding and skill retention while preserving coding efficiency.
📝 Abstract
AI coding agents are rapidly reshaping how software is built, with developers increasingly delegating substantial coding tasks to autonomous agents in pursuit of higher productivity. While these gains are real, they come at the cost of incidental learning. Developers historically acquired informal knowledge through effortful problem-solving, and this has long shaped how software engineering expertise develops. However, with over-reliance on agentic coding, unpracticed skills could atrophy silently over time. As this learning pathway is short-circuited, developers risk silently accruing Knowledge Debt, a developer-level analogue of Technical Debt, where changes the agent executes that the developer cannot fully understand accrue over time. In this paper, we argue that incidental learning will not re-emerge on its own and must be consciously designed back into developer-agent interactions, and propose six design principles to guide such systems. We then present "SHIELD", a multi-agent system grounded in the notion of "agents that teach", that operationalizes these principles by leveraging the AI coding agent's own reasoning to surface contextual, out-of-band learning moments without disrupting developer flow. Through this work, we envision a path toward learning-aware development environments where productivity and learning are complementary, not competing.
Innovation
Methods, ideas, or system contributions that make the work stand out.
incidental learning
knowledge debt
AI coding agents
learning-aware development
multi-agent system
🔎 Similar Papers
No similar papers found.
