Phraseq — cover image

Phraseq

Learn words by living them — an AI-native vocabulary app built end-to-end, solo

Phraseq teaches words through contextual usage, not definitions. Where Anki shows you a card, Phraseq shows you 25 sentences tuned to your profession and register. Where Quizlet tests recall, Sentence Lab grades your writing and explains errors in plain English. Designed, built, billed, and deployed by one person.

Industry / domainConsumer EdTech · AI-native vocabulary
PlatformWeb App — Next.js 14 · Supabase · Claude API · Stripe · Vercel
Timeline2026
My roleLead UX Designer & Founder — Strategy, Research, UX, Visual system, Full-stack build, Stripe billing, Deployment
StatusLive on Vercel — phraseq.vercel.app
6 Feature modules Word Vault · Sentence Lab · IELTS Bands · Quiz · Daily Words · Streak
5×5 Context per word 5 sentences across 5 professional registers
Band 9 IELTS engine Band 5 / 7 / 9 shown simultaneously
BYOK Free tier model Bring your own key — zero API cost until retention proven

02

You can define the word.
You still can't use it.

Flashcard tools are optimised for recognition, not production. The gap between knowing a definition and deploying a word naturally in writing is where learners stall — and where every major vocabulary app stops helping.

The standard vocabulary loop — see word, see definition, see one example, flip card — teaches recognition. You learn to match "ephemeral" to "short-lived." You don't learn that "ephemeral" belongs in literary prose and sounds affected in a work email. You don't learn the register.

For IELTS candidates, this gap is high-stakes. Band 7 and above requires demonstrating that you can use vocabulary flexibly in context — not just accurately, but appropriately. A Band 5 response uses words correctly. A Band 9 response uses them with precision and control. No flashcard app teaches the difference between those two things.

The core failure: existing tools treat vocabulary as a retrieval problem. It's a production problem. Users need practice reaching for words in context, not practice recognising them on a card.

No register awareness
Duolingo, Anki, and Quizlet show one example sentence per word — often generic dictionary text. No indication of whether a word belongs in an email, an essay, a speech, or casual conversation.
No profession context
A doctor and a marketing manager use "efficacy" in completely different sentence structures. No vocabulary tool generates examples for your professional context. Every learner gets the same sentence.
No production feedback
None of the major tools ask users to write with the words they're learning and give feedback on the output. Recognition and production are treated as the same skill. They are not.
No IELTS-specific scaffolding
IELTS preparation apps focus on practice tests, not vocabulary building. There is no tool that shows what a sentence looks like rewritten at Band 7 versus Band 9 — the most actionable feedback an IELTS candidate can receive.

03

Four calls that defined what Phraseq is

Each decision is explained through the tradeoff it resolved, what was designed, and what it produced.

01 Word Vault: profession-aware 5×5 generation vs. a single dictionary example
Tradeoff
A single high-quality example sentence per word is simpler to generate, faster to display, and cheaper on tokens. The standard dictionary approach is familiar and requires no explanation of what a "register" is.
What was designed
Word Vault generates 5 sentences × 5 registers (formal, academic, conversational, creative, professional) — 25 sentences per word — all tuned to the user's stated profession. A doctor gets medical-context formality. A lawyer gets legal-register precision.
Why it mattered
Register is the invisible knowledge that separates fluent writers from accurate-but-stiff ones. 25 examples instead of 1 gives learners the pattern recognition they need to internalise when and where a word belongs — not just what it means. This is the core product differentiation.
02 IELTS Band engine: Band 5/7/9 shown simultaneously — density over minimalism
Tradeoff
A minimal approach would show Band rewrites one at a time — the user selects a target band, gets one rewrite. Cleaner, less cognitive load. The counter-argument: learners can't understand what "Band 9" means without seeing it next to "Band 5."
What was designed
All three band rewrites shown simultaneously in a three-column layout: Band 5 (left), Band 7 (centre), Band 9 (right). Each column highlights the specific vocabulary and structural changes that moved the score. The comparison IS the value.
Why it mattered
Density was the deliberate choice because the three-way comparison makes the upgrade path legible. A learner scans left-to-right and sees exactly what changes at each band level. This is the only tool that makes the Band 5→9 gap concrete and visible in a single view.
03 Sentence Lab: plain-English error explanations, no grammar jargon
Tradeoff
Grammar correction tools traditionally use technical terminology: "dangling modifier," "passive voice," "subject-verb agreement." Precise for trained linguists. For vocabulary learners — especially non-native English speakers — it creates a comprehension barrier on top of a language barrier.
What was designed
Sentence Lab grades submitted writing and returns feedback in plain English: "This sentence is too long and loses its point in the middle — try splitting it at 'however.'" Not: "Run-on sentence with coordinating conjunction misuse." The AI is explicitly prompted to explain errors the way a patient tutor would.
Why it mattered
The target user is not a linguistics student. They're a professional or student trying to write better English under exam or work conditions. Feedback they can immediately understand and apply is more valuable than technically accurate feedback they need to translate.
04 BYOK free tier: validate retention before absorbing API cost
Tradeoff
A fully managed free tier removes all signup friction and is the standard growth model for AI consumer apps. The cost: at Claude API pricing, every active free user generates real cost before revenue is proven. Unacceptable burn rate for a solo-built product at zero retention signal.
What was designed
BYOK (Bring Your Own Key) tier: free users provide their own Anthropic API key. The app stores it encrypted and uses it on their behalf. All features available. The paid subscription removes the key requirement — the product provides managed API access at a margin-positive price point.
Why it mattered
This is a business decision, not a UX compromise. BYOK filters for motivated users — a low bar compared to premium pricing, but high enough to signal intent. It identifies learners most likely to convert to paid, without burning API budget on casual browsers. Now an established low-cost launch pattern for solo AI product builders.

04

Six modules, one through-line

Every feature is a different attack on the same problem: get the learner using words, not just recognising them.

Module Core job Key UX decision Type
Word Vault Enter any word, select your profession, get 25 AI-generated sentences across 5 registers tuned to your professional context Profession selector is required before generation — register context is structural, not optional Core
Sentence Lab Submit a paragraph, receive a score, plain-English error explanations, and a suggested rewrite with changes highlighted AI prompted to explain errors as a tutor would — not as a grammar checker. Jargon-free by design Core
IELTS Bands Submit a sentence, get simultaneous Band 5/7/9 rewrites with per-column vocabulary and structure annotations All three bands shown together — learners need the contrast to understand what "Band 9" means in practice Core
Quiz Engine Auto-generated vocabulary quizzes derived from the user's Word Vault history — tests contextual usage, not definition matching Quizzes generate from the user's own saved words — every quiz is directly relevant to their personal vocabulary Engagement
Daily Words One curated word per day with full Vault-style generation — seeded from the IELTS Academic Word List Daily word is shown before the user reaches their saved vault — creates an entry habit separate from active study Engagement
Streak Engine Tracks consecutive days of active learning — vault lookups, Sentence Lab submissions, or quiz completions count Streak counts any productive action, not just logins — prevents the Duolingo failure mode of opening the app to tap one button and leave Engagement

05

Strategy to deployment — no handoff

Every decision in this product is a design decision made visible through code. There was no engineering team to translate intent. What shipped is what I built.

Phraseq is the product I point to when the "designer who can build" question comes up — not because it demonstrates technical complexity, but because every UX decision has a direct implementation consequence I owned personally.

The BYOK model required encrypted API key storage in Supabase with row-level security policies. The IELTS band comparison required a carefully designed prompt returning three structured outputs in one API call. The Sentence Lab's plain-English feedback required a system prompt tested across hundreds of iterations to strip jargon without losing precision. These are design-build problems, not handoff problems.

Stripe billing is live. Users can subscribe, see their plan, and manage billing through a Stripe-hosted portal. The subscription unlocks the managed API tier. The BYOK tier remains free indefinitely as a retention-first acquisition model.

BYOK + managed subscription is a viable launch model for solo AI product builders who need to prove retention before absorbing AI infrastructure cost. The lesson generalises beyond Phraseq.

Stack
Frontend Next.js 14 · App Router
AI Claude API (Anthropic)
Database Supabase (PostgreSQL + RLS)
Auth Supabase Auth
Billing Stripe · Subscription + Portal
API tier BYOK (free) + Managed (paid)
Deploy Vercel (live)

06

Live product. Shipped solo.

What Phraseq delivered — measured by product completeness, design quality, and the patterns it proved.

Live In production on Vercel — working auth, billing, and AI features, not a prototype
0→1 Solo end-to-end: strategy, UX, code, Stripe billing, and deployment — no handoff at any stage
Unique IELTS Band 5/7/9 simultaneous comparison — no other vocabulary tool shows this
BYOK Validated bring-your-own-key as a low-cost AI product launch pattern
5×5 25 profession-aware sentences per word — highest contextual density of any vocabulary tool
Stripe Live subscription billing with customer portal — a real revenue model, not just a feature list

07

What I would do differently

BYOK needs a no-auth demo moment first. New users hit an API key setup screen before they've experienced the product. The fix: let users run Word Vault once on a pre-seeded key before asking them to set up their own. Lower the first-value moment dramatically, then ask for the key. The current flow asks for commitment before delivering proof.

Streak needs a social share mechanic. The streak and daily word features are retention mechanics that stay entirely inside the app. The missing piece is a one-tap export of a Word Vault result or a Band 9 rewrite that a learner can post on LinkedIn or Twitter. Retention inside the app is valuable. Retention that becomes acquisition is how a solo product grows without a marketing budget.

"The vocabulary tools that exist are optimised for the test they were designed to pass — the flashcard recall test. Phraseq is optimised for the test that matters: can you write a sentence that lands? The gap between those two things is where I built. Designing and shipping this solo taught me that the most powerful design decisions are the ones you're also accountable for implementing."

Samsad Rashid · Lead UX Designer & Founder · Dhaka, Bangladesh · 2026