Governing Technical Debt in Agentic AI Systems
For engineering managers and governance teams building production agentic systems, this provides a conceptual framework to identify and monitor accumulated liabilities from ad-hoc agent design.
The paper defines Agentic Technical Debt and Stochastic Tax as new governance challenges in agentic AI systems, and proposes lightweight dashboards to make them visible to managers.
Agentic AI systems are increasingly being explored as production infrastructure: they reason over multiple steps, call tools, act through workflows, and adapt through memory and feedback. These systems create governance challenges that are not fully captured by traditional software or predictive ML technical debt. We define Agentic Technical Debt as the accumulated liability created when prompts, memory, tool schemas, orchestration graphs, control policies, and observability routines are patched together faster than they can be validated, standardized, and governed. We define Stochastic Tax as the recurring operating burden of keeping probabilistic agent behavior within acceptable bounds. The distinction matters: debt is a stock of design and governance liability, while the tax is a flow of operating cost that arises because stochastic agents act through tools and workflows. We outline how managers can make both visible through lightweight dashboards and governance controls.