Reflections, experiments, and behind-the-scenes learning from a prompt engineer in the field.
All blog experiments and prompting tests are conducted independently. No client data is ever used in our posts or demonstrations. When real-world experiences shape our insights, we recreate those experiments using synthetic or publicly available data—never proprietary or sensitive material.
We believe transparency builds trust, and clear boundaries protect it.
What happens when a language model takes on a logic puzzle like Wordle? This experiment tests GPT-4o with the ReAct framework, showing where its reasoning holds—and where its pattern-based “thinking” leads to contradictions. The results highlight why human oversight and well-structured prompts remain essential.
How does persistent user context change the way AI handles moral dilemmas? This experiment with GPT-4o explores how prompting structure and personalization shape ethical reasoning—using the classic trolley problem as the test bed.
Testing the ReAct prompting framework in real-world conditions using local models. This post walks through the experiment setup, key observations, and what the results reveal about building more thoughtful AI workflows.
A personal reflection on the real-world gaps in AI adoption that inspired the creation of Shinros. This post explores what it feels like to work with AI without guidance—and why trusted prompting expertise is the missing link.