← Selected work
CASE 03Training & reusable engineering practices / 2026

The handoff is part of the product.

Runnable reference projects, focused training, and reusable playbooks that help engineers build with AI and validate the result.

MY ROLE

Reference implementation & instructional design

JavaAEMMavenAI workflowsTechnical teaching

01 / The challenge

Where the work began.

A demonstration can make AI-assisted development look easy without teaching the engineer how to constrain the task, inspect the result, or recover when the output is wrong. Enablement needs a working environment and a repeatable learning loop.

02 / The approach

Developer enablement, end to end.

I created a pinned, multi-module AEM training repository, validated its build and Java tests, and paired it with concise demonstrations and captioned tutorials. The teaching sequence moves through constraints, planning, generation, critique, and validation.

03 / Engineering decisions

The choices that mattered.

01

Start with something runnable

A known project, pinned dependencies, and a validated build keep the lesson focused on engineering practice rather than setup friction.

02

Make critique a normal step

Code generation is one stage in the workflow. Engineers practice inspecting assumptions and validating behavior before treating the output as complete.

03

Make teaching reusable

Shared capabilities cover discovery, spec-driven delivery, code review, human validation, Jira, and pull-request practices.

04 / The result

What shipped.

  • Delivered a runnable AEM training environment with a validated 11-module Maven build and Java tests.
  • Produced focused training videos with synchronized narration and captions.
  • Created reusable training-production and engineering-workflow capabilities.
  • Condensed training documentation while preserving the prompts, build steps, and validation material learners need.

Internal enablement work. No unsupported claims about learner counts or measured adoption are included.

05 / What stayed with me

A good accelerator is one that the next engineer understands well enough to change.
Keep exploring / 04Enterprise engineering

Start a conversation

Talk about the work.

AI engineering, agentic systems, developer tooling, or a problem worth thinking through.

A little context goes a long way.

Opens your email app with a draft. Nothing is sent or stored by this site.