Build Progress

Kindant

A living record of design decisions, components, and progress. Updated as we build. Bookmark this page.

p0stman for ThynkNu / Last updated: 15 May 2026

Talk to Vera

01

Design Direction

Warm Guide, confirmed 23 April

Confirmedby Sarah, 23 April

Warm Guide

Human, approachable, modern wellness. A friend who happens to understand insurance. Rounded corners, generous spacing, conversational tone. Think Headspace meets Monzo. Accessible without being childish.

Product

Kindant

Kind + ant. Care, community, diligence. The platform users trust with their health insurance decisions.

Agent

Vera

Latin for “truth”. The conversational AI agent users interact with. Warm, human, bilingual-safe.

Typography

Display / 48px / Bold

Kindant

H1 / 36px / Bold

Your health, clearly understood.

H2 / 24px / Semibold

Insurance without the fine print.

Body / 16px / Regular

Vera is your personal health insurance guide. She understands your cover, remembers your history, and explains everything in plain language. No jargon, no forms, no call centres.

Caption / 12px / Medium

Rules engine verified. Last updated 23 April 2026.

Font: DM Sans (400, 500, 600, 700). Unified sans-serif with weight contrast for warmth. Modern, friendly, highly readable at all sizes.

02

Colour System

Emerald primary, warm stone neutrals

Light Mode

Primary

#059669

Actions, agent accent, CTAs

Primary Dark

#065F46

Strong emphasis, depth

Background

#FAFAF9

Page background

Surface

#FFFFFF

Cards, panels

Agent Wash

#ECFDF5

Agent bubbles, highlights

Text

#1C1917

Primary copy

Muted

#78716C

Secondary text

Border

#E7E5E4

Dividers, card borders

Dark Mode

Primary

#34D399

Actions, agent accent

Primary Dark

#059669

Strong emphasis

Background

#0C0A09

Page background

Surface

#1C1917

Cards, panels

Agent Wash

#052E16

Agent bubbles, highlights

Text

#F5F5F4

Primary copy

Muted

#A8A29E

Secondary text

Border

#292524

Dividers, card borders

Semantic Colours

Success

Warning

Error

Info

03

Chat Preview

How Vera talks to users

V
Hey! I found three plans that match what you're looking for. Want me to walk you through each one?

Vera, just now

Yes please, start with the most popular
V
Compared 12 plans from 4 providers
The most popular with families in HK is the Premier Health Plus. It covers outpatient visits, dental, and maternity with no sub-limits. Want me to break down the key numbers?
AI guidance
Yes, break it downCompare with othersWhat about pre-existing conditions?
Ask Vera anything...

Simulated conversation showing Vera's tone, action cards, source labels, quick replies, and multimodal input.

04

Component Library

19 components built, rendered live below

Shared UI

Button

Card

Policy Summary

Bupa International Premier, active until Dec 2027. Family plan covering 4 members.

HK$12,500

Annual premium estimate

Badge

DefaultPrimarySuccessWarningErrorInfoRules engineAI guidance

Avatar

V

Agent sm

V

Agent md

V

Agent lg

SP

User sm

SP

User md

SP

User lg

Spinner and IconButton

Agent Chat

MessageBubble

V

I can see you have a family plan. Let me check what your outpatient coverage looks like for specialist visits.

Vera, just now

Yes, we need to see a dermatologist for my daughter

You, just now

V

Your plan covers specialist consultations at 80% after a HK$500 deductible per visit. Shall I find dermatologists in your network near Central?

TypingIndicator

V

ActionCard

Checking your policy terms...

Found 3 relevant clauses

Outpatient, specialist referral, and deductible sections

Could not verify provider network

The insurer's directory is temporarily unavailable

MemoryPill

Tap any pill to edit. These show what Vera remembers about you.

CheckpointCard

Ready to submit your health assessment

  • No pre-existing conditions disclosed
  • Non-smoker, no hazardous activities
  • Family plan: 2 adults, 2 children

SourceBadge and SourceAnchor

Rules engineAI guidance

QuickReplyChips

InputBar

DocumentConfirmation

Bupa-Premier-Policy-2026.pdf

PDF, 2.4 MB

I can see this is a Bupa International Premier policy, active until December 2027. Family plan covering 4 members with worldwide coverage.

PaywallGate

The Trusted Guide

This feature is part of the premium experience. Upgrade to unlock care navigation, claims assistance, and more.

HumanEscalation

This needs a human expert

This claim involves a dispute with the insurer that needs specialist review. I have prepared a summary of your case.

05

How Vera Knows Things

Three layers, zero guessing

Vera never answers from general AI knowledge. Every response is grounded in one of three verified sources. If none of them have the answer, she says so.

User

Asks insurance questions via text, voice, or document upload

V

Vera

Listens, calls the right source, explains clearly, cites everything

1

Rules Engine

Deterministic

Michael's underwriting decision trees. Pure TypeScript. 234 conditions across all 15 categories. Every decision is testable and auditable. No AI involved.

2

Knowledge Base

Verified

Structured domain knowledge: insurance glossary, HK market context, condition guides, policy terms. Vera reads and cites these files. Updated without retraining.

3

Refusal

Safety net

If neither the rules engine nor the knowledge base has the answer, Vera says so clearly and suggests next steps. She never guesses.

Why this matters: In health insurance, a wrong answer is worse than no answer. This architecture means Vera can explain a complex exclusion clause and trace it back to the exact rule that applied, or tell you she does not have enough information to answer. There is no middle ground where she guesses and sounds confident.

Vera's Toolbox

Vera is not a chatbot. She is an agent that reasons about your question, decides which tools to use, calls them, and synthesises the results into a clear answer. Here are the 9 tools she has access to today.

listCategories

Rules Engine

Lists all 15 disease categories and condition counts. Vera calls this when a user asks “What conditions can you assess?”

listConditions

Rules Engine

Lists all conditions in a specific category. When a user mentions “diabetes”, Vera searches the endocrine category to find the right decision tree.

lookupCondition

Rules Engine

Retrieves the full underwriting decision tree for a specific condition: the questions that would be asked, possible outcomes (standard, exclude, decline, postpone), and the decision logic. Every answer is deterministic.

lookupKnowledge

Knowledge Base

Reads verified knowledge files: insurance glossary (30+ terms), HK market overview, underwriting basics, condition guides, and what Kindant offers. Vera cites the source in her response.

evaluateCondition

Rules Engine

Runs the deterministic underwriting evaluator from within chat. Takes a condition ID and user answers, walks the decision tree, returns a binding outcome (standard, exclude, decline, postpone). Auto-persists an audit log to Supabase.

readPolicy

Knowledge Base

Reads user-uploaded policy PDFs that have been processed through the ingestion pipeline. Claude extracts structured data from the document. Vera can then answer questions about the user's specific cover, exclusions, and benefits.

escalateToHuman

Escalation

When Vera encounters a question beyond her knowledge or a nuanced case that needs human judgement, she escalates to Sarah or Michael. An inline EscalationCard appears in the chat, and the case is routed to the admin dashboard via /api/escalate.

readDocument

Vision

Reads uploaded images (receipts, medical reports, insurance cards). Claude vision extracts text and key details automatically on upload.

Voice I/O

ElevenLabs

Browser speech recognition for voice input, ElevenLabs TTS for voice output. Vera speaks with a warm British accent (Alice voice). Toggle voice mode via the mic button.

Example: “I have diabetes, what happens with my application?”

1

Vera calls lookupKnowledge('endocrine') to understand diabetes in the context of insurance

2

Vera calls listConditions('Q2') to find all endocrine conditions in the rules engine

3

Vera calls lookupCondition('Q2', 'Q2_1_DIABETES') to get the full decision tree

4

Vera explains: which questions would be asked, what the possible outcomes are, and what factors matter (e.g. HbA1c level, medication, complications)

5

Every fact is traced to a verified source. Nothing is guessed.

Coming next

searchProviders

Find healthcare providers by location, speciality, and network

comparePlans

Side-by-side comparison of insurance plans based on user needs and conditions

fileClaim

Guide users through the claims process with document collection and status tracking

06

Design Principles

The rules Vera lives by

01

Conversation is the product

The chat is not a feature of Kindant. It is the entire experience. Every interaction, from researching cover to filing a claim, happens through a natural conversation with Vera. No forms, no dashboards, no buried settings.

02

Warm, not clinical

Insurance is intimidating. Kindant should feel like talking to a knowledgeable friend, not filling out a medical form. Emerald greens, warm stone tones, rounded edges, generous spacing. Think Headspace meets Monzo.

03

Transparency builds trust

Every recommendation shows its reasoning. Underwriting decisions cite the specific rules that were applied. When Vera does not know something, she says so. No black-box moments.

04

Rules engine, not opinions

Underwriting decisions are made by a deterministic rules engine, not AI. The decision tree Michael built is converted into structured data that a system walks step by step. Every path is testable, auditable, and explainable.

05

Mobile-first, always

80%+ of HK internet use is mobile. Every component is designed for a thumb first, mouse second. Bottom-anchored input, swipeable cards, voice as a first-class input method.

06

Progressive complexity

Start simple: 'What are you looking for?' End sophisticated: deterministic underwriting, plan comparison, claims filing. The interface grows with the user's needs, never front-loads complexity.

07

Build Log

What has been shipped so far

View full build log

12+ sessions, from project foundation to production handover. Every feature, every decision, tracked chronologically.

08

Project Status

Ready for handover, 22 May 2026

Phase3 of 3 complete
Automated tests250 passing
Underwriting conditions234 across 15 categories
Decision tree nodes1,373 verified against source
Agent test scenarios17 multi-turn, all passing
Knowledge base22 files

09

Key Decisions

Confirmed across kickoff and build

UK first, Hong Kong ready

UK primary market. Bilingual support (EN + zh-HK Traditional Chinese) shipped. Underwriting data already bilingual.

Invite-only closed beta

Working moms and busy professionals with unused policies. 20 invite codes ready. Google SSO also available.

Companion, not comparison

Kindant is a navigator and guide, not a comparison engine. No insurance sales, no kickbacks. Insurer-agnostic.

Human-in-the-loop is the USP

AI handles 90-95%. Sarah and Michael handle nuanced cases via the admin escalation dashboard.

All 4 journeys live

Guided Choice, Living Protection, Trusted Guide, and Transparent Resolution. Voice, image upload, PDF analysis all active.

250 automated tests

Deterministic underwriting engine validated against every condition path in all 15 disease categories. 17 agent scenarios pass.