Problem
Important production work was still being done with slow, manual, or repetitive workflows.
Case Study
AI-assisted
workflow tooling
I built GPT-powered WordPress tools, Claude-based agent workflows, and live prototyping systems to improve content production, site analysis, development speed, and team adoption of AI-assisted work.
Result: faster production, useful internal tools, and broader team adoption of LLM-assisted workflows.
Work
GPT-powered WordPress plugins, Liquid text variation, Claude agents, content analysis tools, and live HTML/CSS prototyping.
Outcome
Practical AI tooling that improved speed, expanded capability, and helped normalize LLM use on the team.
What was missing
- Content, QA, SEO, and production workflows had repeated tasks that were good candidates for AI assistance.
- The team did not yet have practical internal tooling that connected LLMs to real WordPress and content workflows.
- AI was available in theory, but someone still had to turn it into usable production systems.
What I built
GPT-powered WordPress tools.
Built plugins that could pull from RSS feeds and website elements to generate reports, summaries, and content support.
Liquid text variation tooling.
Spearheaded a GPT-powered system for generating controlled text variation inside Liquid-based content templates.
Layered Claude agent workflows.
Created a capability-based agent framework with skills for UX, SEO, accessibility, schema, and HTML validation analysis.
Live prototyping support.
Built a local Claude-assisted viewer that displayed changes as HTML and CSS files were edited, making iteration faster.
Result
Self-started
AI tooling that improved real production work.
- I built these tools without being asked because I saw ways to improve the work.
- The tools helped speed up content, analysis, prototyping, and production workflows.
- The work helped inspire broader LLM adoption across the team.
What this shows
This project shows how I use AI as a practical production layer: not as a gimmick, but as a way to build tools, reduce repetitive work, improve judgment-heavy workflows, and help teams move faster.
Want to talk?
If you need someone who can improve a website without losing sight of users, revenue, content, code, or production reality, I’m probably worth a conversation.