Ask My Work

Ask questions about projects, architecture decisions, and reliability judgment.

Use focused questions to explore how the work is reasoned about. Answers are designed to cite the underlying material, connect related projects, and stay within the evidence available.

Ask a question

Starter questions

Source-backed answer

confidence: medium

This project chooses RAG instead of fine-tuning because the corpus should remain the source of truth. Retrieval keeps answers reviewable, fresh, and citable, while fine-tuning is better suited for behavior or style changes than for storing changing portfolio or architecture facts.

Sources

RAG vs Fine-Tuning: Choosing the Right Tool for the Problem
One of the most common questions in modern AI architecture is:
Corpus Design Principles for AI Systems
Many AI discussions focus on model selection, prompting techniques, vector databases, and agent frameworks.
Operational AI and the Importance of Trust
Much of the discussion around artificial intelligence focuses on model size, benchmark scores, reasoning capabilities, and rapid feature development.

Related projects

Ask My Work, Architecture Explainer, and Operational Intelligence Platform.

How this works

The portfolio is designed as an engineered AI system, not a generic chatbot. Questions are answered from the site's writing, case studies, architecture notes, and synthetic incident material, with citations and confidence boundaries used to keep answers inspectable.

The deeper architecture uses retrieval, source metadata, model abstraction, and bounded workflows so implementation details can be evaluated as a case study instead of distracting from the visitor experience.