Designing Learning That Scales, Engages, and Delivers Results
Here is a quick glimpse of my portfolio
Learning with AI
(30% Increase in Knowledge Application)
The Problem:
AI-driven individualized learning is often discussed conceptually but rarely shown in a tangible, performance-based format. Stakeholders struggled to visualize how AI could move beyond content generation to diagnose learner gaps, adapt instruction in real time, and improve transfer.
In the current role, a cohort compared AI-supported practice vs. traditional approaches. Adult learners brought a wide range of prior skill and knowledge — so static, one-path training underused what training could do.
Goals:
After the experience, learners / stakeholders could:
See how adaptive feedback responds to misconceptions in the moment
Practice decision-making in a branching scenario (not only read about AI)
Give leaders a concrete model of AI as an instructional layer inside structured eLearning
Success looked like stronger knowledge application on post-scenario tasks, faster paths to competency via remediation, and clearer stakeholder understanding of AI’s role.
Approach:
Framed the business/learning problem: stakeholders couldn’t see individualized AI instruction.
Designed an AI-enhanced branching scenario in Storyline that could diagnose misconceptions, adjust difficulty, deliver contextual feedback, require remediation before progression, and modify dialogue paths via variables.
Engineered branching architecture, variable structure, feedback logic, and prompt frameworks to simulate adaptive behavior in a controlled SCORM environment.
Used SchoolAI and ChatGPT to generate differentiated feedback paths, misconception-based responses, and layered remediation prompts.
Deployed via LMS (SCORM); encouraged use as PD hours; monitored engagement/completion.
Briefed instructional leaders on interpreting decision-path data, monitoring adaptive feedback, spotting knowledge gaps, and supporting learners who needed more remediation.
Implementation:
The module was deployed within the building LMS using SCORM tracking. Staff were encouraged to use the AI tool as part of professional development hours, with engagement and completion monitored through LMS analytics.
I also provided brief guidance to instructional leaders on:
Interpreting learner decision-path data
Monitoring adaptive feedback effectiveness
Identifying knowledge gaps revealed through branching outcomes
Supporting learners who required additional remediation
This ensured the tool was positioned as a performance-support system rather than a novelty technology.
Results
The AI-enhanced scenario demonstrated measurable performance gains:
→ 30% increase in learner knowledge application (measured through post-scenario applied performance tasks)
→ Significant reduction in time-to-competency due to targeted remediation pathways
→ Improved learner engagement through dynamic, non-static content experiences
Reflection & Lessons Learned
This project reinforced several key instructional design principles:
Adaptive feedback significantly improves knowledge transfer compared to static correction
AI is most effective when embedded within intentional instructional architecture
Scenario-based learning amplifies the impact of individualized instruction
Real-time performance data provides actionable insight into learner misconceptions
Most importantly, the demo clarified for stakeholders that AI is not a replacement for instructional design — it is a force multiplier when structured correctly.
Tools Used
Articulate Storyline 360 · SCORM · WCAG 2.2 AA · SchoolAI · ChatGPT · Variable-Based Branching Logic · LMS Analytics