Research · Paper

Chasing Jarvis: Can Technically Sophisticated Non-Programmers Deploy SaaS Applications Using AI Coding Agents? An Empirical Investigation Through Context Engineering and the Lumina AI Case Study

Published
15 March 2026
Author
Dr. Tali Režun
Series
Chasing Jarvis
Topics
Chasing Jarvis · Context Engineering · Lumina AI

The empirical study behind the non-developer thesis. Two years of participatory action research (2023–2025), combining systematic tool experimentation (Cline, Claude Code, Augment Code, Google AI Studio, Cursor) with the build of Lumina AI, which went from concept to production in 30 days on Firebase, React and Gemini. Synthesises 80+ sources. Five propositions cover production feasibility, the "70% problem", security-verification risk, and orchestration as the new expertise. Conclusion: "bounded democratisation". Non-programmers can ship, but only by mastering context, not code. RG shows 1 citation.

Cite this work

Režun, D. T. (2026). Chasing Jarvis: Can Technically Sophisticated Non-Programmers Deploy SaaS Applications Using AI Coding Agents? An Empirical Investigation Through Context Engineering and the Lumina AI Case Study. talirezun.com. https://talirezun.com/library/chasing-jarvis-non-programmers-saas

@misc{chasing-jarvis-non-programmers-saas,
  author = {Dr. Tali Režun},
  title = {Chasing Jarvis: Can Technically Sophisticated Non-Programmers Deploy SaaS Applications Using AI Coding Agents? An Empirical Investigation Through Context Engineering and the Lumina AI Case Study},
  year = {2026},
  url = {https://talirezun.com/library/chasing-jarvis-non-programmers-saas},
  note = {talirezun.com}
}
DOI: none yet