First Advisor

Bruce Irvin

Date of Award

Winter 3-2026

Document Type

Thesis

Degree Name

Bachelor of Science (B.S.) in Computer Science and University Honors

Department

Computer Science

Language

English

Subjects

Agile software development, software architecture, conversational AI systems, iterative design, capstone engineering projects

DOI

10.15760/honors.1831

Abstract

This capstone review examines the development of AI Fishbowl, a public-facing, interactive artificial intelligence system, as a case study in how Agile methods evolve from a project management tool into a design philosophy under real-world constraints. Although the project adopted an Agile workflow early on through a Kanban-style task management approach, the initial system design and architecture were still shaped by a largely plan-first mindset. This created a mismatch between flexible process and rigid design assumptions, which became increasingly apparent as the team moved from high-level architecture into implementation.

A critical turning point occurred when early architectural plans proved difficult to translate into working code, revealing gaps between conceptual system design and the realities of integrating hardware, real-time speech processing, and distributed software components. Following this realization, the team transitioned toward more structured Agile practices, including sprint planning, reviews, and regular standups, which reframed design as an iterative process grounded in working software rather than upfront specification. The successful delivery of a minimum viable product emerged not from executing a fixed architectural plan, but from continuously revising design decisions in response to technical constraints and demo-driven timelines.

This paper argues that Agile became most impactful in the AI Fishbowl project not as a scheduling or task management framework, but as a design philosophy that reshaped how architecture, feature scope, and engineering tradeoffs were negotiated under real-world constraints.

Persistent Identifier

https://archives.pdx.edu/ds/psu/44764

Download

Share

COinS