Obai Ibrahim Back to Portfolio
Product Design · AI-Assisted Development · Web

Kalimaty Website - From Design to Production

Designing and launching a new web experience for Kalimaty while using an AI-assisted development workflow to move from product thinking and interface design to code, version control, deployment, and continuous iteration.

Role
Product Design Lead · Builder
Scope
UX, UI, Front-end & Release
Workflow
Paper Sketching · Codex · GitHub
Launch
Vercel · Production
Kalimaty website initial paper sketch
01 · Context

A product that needed a website built with the same product thinking.

Kalimaty had an established mobile product and brand. The next challenge was to create a web experience that explains the product clearly, supports acquisition, and communicates the product value without turning the site into a static marketing layer disconnected from the actual experience.

01

Turn product value into a clear story

Translate a feature-rich language-learning product into a focused web narrative that quickly communicates what Kalimaty is, who it is for, and why the personal-dictionary model matters.

02

Keep the experience consistent

Extend the product's visual language into the website while keeping the interaction model, typography, spacing, imagery, and content hierarchy coherent.

03

Reduce the handoff between design and code

Use a modern, AI-assisted workflow to move from design decisions to working code, validate the result, and iterate without treating development as a separate phase.

02 · The Approach

Designing the experience and building the system that ships it.

The project was intentionally treated as an end-to-end product workflow. The goal was not only to design the pages, but to establish a practical path from interface decisions to a live production experience.

Step 01

Design

Define the information architecture, page hierarchy, content structure, responsive behavior, and visual language before implementation.

Paper Sketching · UX/UI · Design decisions
Step 02

Build with AI assistance

Use Codex as a development partner to translate design intent into code, iterate on structure and styling, and solve implementation details through short feedback loops.

Codex · Prompting · Code iteration
Step 03

Version & review

Keep the work organized in GitHub using branches, commits, pushes, merges, and a controlled main branch as the source of truth.

GitHub · Branches · Commits · Merge
Step 04

Release

Connect the repository to Vercel so approved changes can move from source control to preview and production with a repeatable release workflow.

Vercel · Preview · Production
03 · Process

One workflow, from the first screen to the live URL.

Instead of separating design, development, and release into disconnected stages, the workflow stayed iterative. Each stage produced something testable that informed the next decision.

Define

Start with the product story

Clarify the site's role in the broader product ecosystem, identify the primary user questions, and structure the experience around the jobs the website needs to perform.

Design

Translate the product into a responsive interface

Sketch the page layouts, content hierarchy, key components, and user journeys on paper. Use these sketches to clarify the experience before moving into implementation.

Implement

Use Codex to accelerate the build

Write precise prompts, inspect the generated code, test the output, and make targeted iterations. AI accelerates implementation, while design judgment remains the quality filter.

Control

Manage change through GitHub

Use isolated branches for changes, meaningful commits for traceability, and merge only after the work is reviewed and ready to become part of the main product.

Release

Ship through Vercel

Use the GitHub-to-Vercel connection to turn accepted repository changes into deployments, making the production release part of the same workflow rather than a separate manual step.

Iterate

Improve the live experience continuously

Once live, the same loop can continue: identify an issue or opportunity, make the change, validate it, push the update, and release the next version.

04 · Evidence

Show the work behind the final interface.

The strongest version of this case study should show the actual workflow, not just the finished website. These four visuals are the screenshots I recommend adding.

Kalimaty website initial paper sketch

From paper sketches to interface

Codex

Codex - AI as a development partner

Codex

Github - Design decisions translated into managed changes

Codex

Vercel - From repository to production

05 · Product Continuity

The website is an extension of the product, not a separate artifact.

Kalimaty's website needs to explain the same product users encounter inside the app: a personal vocabulary system, contextual learning, practice tools, and an AI-supported learning experience.

Kalimaty app home screen
Kalimaty flashcards screen
These are existing Kalimaty app visuals. They can remain here as product context, while the new website screenshots become the main case-study evidence.
06 · What I Owned

Expanding the role from interface designer to end-to-end product builder.

This project is useful in the portfolio because it shows a broader responsibility model than a traditional design-only case study.

Product & UX

Defined the website's role, information architecture, page hierarchy, user flows, content priorities, and overall experience.

UI & Design System

Established the visual direction, responsive layout decisions, reusable patterns, typography, spacing, and component behavior.

AI-Assisted Development

Used Codex to accelerate implementation and iteration while personally reviewing, directing, testing, and refining the generated work.

Source Control & Release

Managed the project through GitHub and connected the repository to Vercel for preview and production deployment.

07 · Outcome

A repeatable design-to-release workflow.

The primary outcome is not a single webpage. It is a working model for how a designer can use modern tools to own more of the product lifecycle - from design intent to implementation, version control, and production release.

Live production experience

The new Kalimaty website is deployed and available to real users.

Shorter design-to-code loop

AI assistance reduces the distance between a design decision and a working implementation.

Structured change management

GitHub provides a clear path for isolated changes, review, merging, and traceability.

Repeatable deployment

Vercel turns repository updates into a consistent preview-to-production workflow.

The value of AI-assisted product development is not replacing design judgment. It is extending what a designer can personally take from concept to a live, maintainable product.