Beyond the roadmap

A growing collection of things I've explored, designed, built, and occasionally broken outside of work.

Below you'll find personal projects, AI experiments, creative prototypes, and the occasional oddity—built out of curiosity, necessity, or both.

Deskbud

Check it out

A Tamagotchi-inspired productivity companion that helps remote workers and students stay focused, hydrated, and active while tracking time across projects. Designed and built by me in Lovable.

Testing details: Email: deskbudtest@gmail.com PSW: Hellocaktus1!

Budget Wizard

Check it out

A personal finance planning tool I designed for myself, to make investing feel less intimidating. It can help you explore different saving and investment scenarios and see how today's decisions could shape your future finances. Designed in Claude Design. Built in Claude Code.

Turbio-Zine

Check it out

Turbio Zine is an AI-assisted cultural discovery platform focused on alternative and underground events. The concept combines automated event gathering with human curation to surface concerts, club nights, and DIY cultural experiences that are often fragmented across social media, flyers, and local scenes.

The project explores how AI can support more human-centered cultural discovery by helping identify, structure, and curate underground signals that traditional algorithms and mainstream event platforms frequently overlook.

Turbio-Zine

Check it out

Macros Plates

Check it out

A personal experiment in behavior design and nutrition. Generate meal alternatives that match your calories and macros without sacrificing variety. Designed and built by me in Lovable.

Check out more projects

Ekho: an agent that keeps teams aligned, while the decision stays human

Multi-agent system design

Responsible AI

Human in the loop

Ekho: an agent that keeps teams aligned, while the decision stays human

Ekho AI was designed to catch team misalignment before it turns into rework, by acting as a project memory system that makes a team's decisions and their lineage visible across messy, fast-changing sources of information.

Multi-agent system design

Responsible AI

Human in the loop

What an AI sales tool taught me about trust and adoption

Time from lead to first offer dropped

Uncovered AI adoption barriers

What an AI sales tool taught me about trust and adoption

I designed an AI tool to help sales reps create learning recommendations faster and reduce reliance on SMEs. Early adoption was promising, but over time the project revealed bigger challenges around trust, workflows, and product adoption.

Time from lead to first offer dropped

Uncovered AI adoption barriers

From manual curation to self-service: an AI advisor that improved learning adoption and retention

63%

Adoption of AI generated programs

2.9X

Higher retention than standard programs

From manual curation to self-service: an AI advisor that improved learning adoption and retention

Enterprise learning relied heavily on admins to curate and assign training, which made personalization hard to scale. We used existing AI infrastructure to let learners create personalized learning paths based on their career goals, shifting learning discovery from an admin-led process to a more scalable, self-service experience.

63%

Adoption of AI generated programs

2.9X

Higher retention than standard programs

From guesswork to guardrails: a panel redesign that cut client setup errors by 26%

Drop in support tickets tied to misconfiguration

New CSMs reporting higher confidence earlier

From guesswork to guardrails: a panel redesign that cut client setup errors by 26%

I redesigned a complex admin tool used daily by Sales and Customer Success teams to configure enterprise client settings. The legacy system made critical errors easy. I rebuilt it around clarity, feedback, and safer workflows, reducing support needs and user stress.

Drop in support tickets tied to misconfiguration

New CSMs reporting higher confidence earlier

Helping QA learners learn more confidently with an AI tutor built for trust

4.5/5

Avg. Rating

1,178

Client Accounts

34%

Adoption Growth

Helping QA learners learn more confidently with an AI tutor built for trust

I led the end-to-end design of Ela, QA’s AI-powered learning assistant, transforming an inherited prototype into a trusted and scalable product in just two months. Designed to reduce friction and support learning momentum, Ela is now adopted by 80+ client accounts, holds a 4.5/5 satisfaction score, and has influenced the development of new AI capabilities across the platform.

4.5/5

Avg. Rating

1,178

Client Accounts

34%

Adoption Growth

I redesigned QA's platform navigation to keep learners on track

53%

users exiting lessons to track progress

28%

Reduction in fullscreen toggling to study

I redesigned QA's platform navigation to keep learners on track

I designed a universal sidebar to unify all content types during a major content merger. Learners can now track their progress without leaving the lesson, reducing distractions.

53%

users exiting lessons to track progress

28%

Reduction in fullscreen toggling to study

Helping Circus Street learners feel at home after a platform transition, without increasing support burden

increase in helpdesk tickets

20%

reliance on secondary tabs after redesign

Helping Circus Street learners feel at home after a platform transition, without increasing support burden

I unified QA Learning’s Course and Lesson experience during the merger of Circus Street and Cloud Academy into a single platform, helping Circus Street learners adapt to a more complex UX without increasing support burden or disrupting engagement.

increase in helpdesk tickets

20%

reliance on secondary tabs after redesign