Tyren Temple
Tyren Temple, photographed in profile at golden hour
Tuned for

Design and build.Same hands.

Product design & AI  |  Fintech, GreenTechWellington → Sydney
Who I am

Different domains, same engine underneath.

I'm a Senior Product Designer who doesn't stay in one lane. The constant isn't a specialism, it's curiosity, following a problem into whatever skill it needs.

Selected work

2026

AI-powered vetting platform · Brighte

Vetting installers took a month. Now half a day.

Product designAgentic workflow
Challenge
Vetting took up to a month across four systems, with 58 minutes of manual work per application and a backlog building. Worse: more than half of accredited vendors never went on to write a single deal.
Solution
Reframed the brief from "redesign the form" to designing the data layer for an AI system. Vendors move through a structured intake that hands the agent clean data, while the admin portal surfaces the results so humans keep the judgment calls.
Role
Product Designer at Brighte. Owned every vendor and admin surface end to end, in a pod working hand in hand with engineering.
Impact
Approval to accredited went from 17.5 days to half a day, and decisioning from 58 minutes of manual work to under 4. 89% of vendors who started the form finished it.
2026

Design-system infrastructure · Brighte

AI agents kept guessing at our UI. Now they read from a source of truth.

Design systemsAI
Challenge
The component library worked for humans, but an AI coding agent had no reliable source of truth to read. Point one at the system and the output was inconsistent, throwaway code that needed correcting everywhere.
Solution
Built a context and semantic layer on top: every component specified with the tokens it uses, how it composes, and what an agent must never generate. Pattern rules above describe how components assemble into whole surfaces, so agents read the layers in sequence instead of inventing.
Role
Product Designer and design-system custodian at Brighte. My idea, led end to end, working hand in hand with engineering.
Impact
The same brief run through independent agents in fresh sessions now lands consistent structure, components and tokens: close to draft feature code where there was throwaway output before, with far less rework.
Coming soon
Coming soon
Coming soon
Coming soon
2025

Design system · AddressFinder

Figma said one thing. The code said another.

Design systemsTokens
Challenge
The portal redesign was stuck because design didn't match the build. Designers and developers were describing the same components in different languages, with no shared source of truth to settle it.
Solution
Audited how their site was actually built in Tailwind, then built the system on that reality: 240+ tokens and 85+ components named to the code's conventions, so the thing in Figma and the thing in production are finally the same thing.
Role
Product Designer (freelance). Owned the audit, the token architecture, the component library and the handover.
Impact
The team designed 30-40% faster, the Head of Product's estimate from daily use, and a non-designer marketer shipped on-brand pages without waiting on design.
2023

Impact dashboard · Trees That Count

One dashboard, two users who wanted opposite things

Product designDual-sidedData viz
Challenge
Planters needed project tools and compliance; funders needed impact they could report on, and were requesting manual reports just to get it.
Solution
Same data underneath, so forking the product was off the table. One source of truth, surfaced differently for each side, shipped incrementally so value landed early instead of one big bang.
Role
Product Designer at Trees That Count. Led the redesign end to end: research, strategy, design, delivery.
Impact
Planter task completion went from 73% to 96%, funder engagement lifted 115%, and average session time tripled from 30 to 90 seconds.
2026

Card game · Personal project

Financial lessons don't stick, so losing becomes the lesson

Game designSystemsPrint
Challenge
Financial literacy gets taught and doesn't land: around 70% of NZ schools teach it, but only 19% of students feel they learn anything. It arrives as homework, not as something relevant to your actual life.
Solution
A card game you learn by losing. Take a risk, occasionally get burned, and the consequence does the teaching, no lecturing required. Balanced across 12-plus rounds of playtesting with 50-plus people.
Role
Solo designer. Concept, mechanics, balance and production, publishing in 2026.
Impact
Over 90% of players who started high-risk shifted to cautious play after a few games, and players could explain dividends, interest and debt in their own words afterwards.
2025

Quit-vaping web app · Personal project

Designed it in 2023. Built it myself in 2025.

Product designDesign to codeBehaviour change
Challenge
Quitting vaping myself, the apps I leaned on were joyless streak-counters where one slip felt like failure. A warmer design existed, sketched back in 2023, but it had never left Figma: just screens, not a thing anyone could actually use.
Solution
Picked the 2023 design back up and built it for real. A live web app at breakthevape.app with a progress dashboard, a milestone tracker, mood check-ins and a quit-buddies layer, framed around motivation and small wins instead of shame. Designed and coded end to end.
Role
Solo, end to end. Product design in 2023, then the front-end build and ship in 2025, working across design and code.
Impact
A real, live product at breakthevape.app rather than a prototype. It did the job it was built for, I quit, and it is the clearest proof of taking something from design file to shipped product single-handed.

What I'm known for

Design systems

Systems built for machines to read

My sharpest work is making design systems machine-readable, so AI tools build from them consistently instead of guessing.

Reframing

A vague brief, taken to a shipped AI workflow

I took a "redesign the form" brief, reframed it as the data layer for an agentic system, and owned it end to end. 208 reviewed, 89% completion.

Builds, not just designs

I ship real front-end PRs

I work close enough to engineering to ship my own UI changes as reviewed pull requests, so the engineers stay on the harder problems.

Honest about the edges

Calibrated, not overclaimed

I'm clear about where my depth ends. Being honest about the line is part of what makes the rest credible.

The whole point of this page

Scrolled this far? Surely you've got questions.

Everything here is answerable in Tyren's own words. Ask the brain directly, or paste a job description for an honest fit read.

Ask anything, or paste a job description for an honest fit read. Pasted JDs aren't stored.