Project

Applied AI Workflows

Practical AI-assisted systems for research, teaching, public communication, and mission-driven knowledge work — built around documented processes a human user can understand, verify, and maintain.

Grid diagram representing a structured workflow system with structured inputs, review steps, and documented outputs. — Applied AI workflows are structured processes, not automation. Each workflow documents inputs, review steps, human judgment points, and what should not be automated.

Role
Workflow designer and human-in-the-loop practitioner
Areas
Teaching & Learning / Research / Public Scholarship
Skills
AI-assisted research, Workflow design, Prompt engineering, Human-in-the-loop systems, Instructional design

Overview

AI tools are most useful when the process is documented — when the human role is explicit, the review steps are defined, and the boundaries around what should not be automated are stated in advance.

These four workflow case studies show how that kind of structured AI use applies across research, teaching, and public communication problems: a writing center triage workflow, a Huruf La'b teacher support system, a historical research-to-script pipeline, and an African airlines data extraction workflow.

How I work with AI

Four principles organize the work. Delegation: decide what belongs with AI and what must remain human-led. Description: turn vague problems into context, constraints, examples, and workflows. Discernment: check outputs against sources, users, and goals. Diligence: document the process so someone else can maintain it.

Why it matters

Applied AI fluency is not about using every available tool. It is about knowing which steps benefit from assistance, which require human judgment, and how to document the difference so someone else can maintain the system.

The point is not to automate judgment. The point is to make complex work easier to understand, verify, teach, and hand off.