JALZAP: An Agile Hybrid for AI-Accelerated Software Development

The rapid adoption of generative AI tools allows software teams to quickly code applications, but it comes at a cost: high scope volatility, technical debt, and unrealistic expectations, which break traditional Agile frameworks. This thesis introduces JALZAP, a lightweight, hybrid Agile framework designed to serve small, high-agility teams facing compressed timelines and unpredictable schedules. This framework was evaluated over 16 weeks through a Portland State University Capstone project working for a pre-seed startup sponsor, where a six-person team built Flowmind: an AI-powered iOS task management app meant to serve users with neurodevelopmental disorders like ADD/ADHD. JALZAP implements structural boundaries, including a Kanban-like “One-Task” restriction, an XP-inspired “Zero-Point” rule that deprives technical debt tasks of story point value, and mandatory “Sprint Breaks.” Framework performance was analyzed quantitatively through GitHub Project Insights, revealing JALZAL successfully stabilizing team velocity over eight sprints, delivering 178 completed story points, reducing scope through negotiation by 50% through empirical metrics, and ultimately shipping 10 production builds to iOS TestFlight. The findings demonstrate JALZAP’s success as a transferable model for small, constrained teams navigating high-volatility startup environments.