Case study / product design + WordPress AI

Think it.
Build it here.

ZenCode AI turns a WordPress installation into a project-aware coding workspace—with a public showcase, isolated guest access and private administrator projects.

ZenCode AI homepage with a project workspace interface
RoleConcept, direction, review and iteration
FormatWordPress plugin + showcase theme
Core AIGoogle Gemini API
StatusWorking public demo and private product

The challenge

Move beyond a chatbot-shaped interface.

The goal was not to add a chat box to WordPress. It was to create a place where an idea could become files, a structured plan, reviewable code and restorable versions without losing project context.

That meant treating the plugin as an application: project ownership, file state, mobile layout, user feedback, AI request boundaries and upgrade safety all mattered as much as the model response.

The product decisions

Projects, not isolated prompts

Files, messages, plans and versions stay attached to a project. Users can choose which files enter context instead of sending everything on every request.

Planning before execution

Plan Mode turns a broad request into executable steps. A user can run one step, continue through the plan or revisit the structure before changing code.

Visual input as a real workflow

Image-to-plan accepts PNG, JPEG and WebP screenshots as implementation briefs, while keeping private administrator requests separate from the public showcase.

Two deliberately different access modes

Administrators keep server-side projects, versions and learning memory. Guests receive an isolated browser-saved project and rate-limited AI access without needing a WordPress account.

What the finished product demonstrates

01 / DEPTHA real project-aware workflow rather than a single prompt form
02 / RESPONSIBILITYOwnership checks, nonces and separation between guest and private data
03 / DELIVERYA public showcase, working plugin and versioned releases

ZenCode AI is also evidence of the way I work with modern models: define the product, direct the build, inspect the output, test edge cases and keep iterating until the experience behaves coherently.

ZenCode AI public product page
Public showcase: the product is explained through real workflow rather than invented metrics.
Responsive ZenCode AI coding workspace
Working application: project files, editor, planning and AI assistant in one responsive workspace.

Design judgement

The hard part was not generating code. It was shaping a coherent product.

Hundreds of small decisions separate an impressive prototype from something people can understand and use: what is private, what persists, what happens on mobile, how errors appear, how long-running requests communicate progress and what survives an update.

01Repeated responsive testing across desktop and mobile
02Clearer public-versus-private product boundaries
03Versioned iteration instead of one-shot generation
04Honest product copy without invented social proof

Need this combination?

Product thinking, interface design and practical AI delivery.

Tell me about the workflow you want to improve.

Start a conversation