01 / COMPANY PRODUCTONGOING
Maphood
Product design, UI/UX and visual communication in an existing live product ecosystem, alongside its founder and engineering team.
PRODUCT DESIGNER · AI PRODUCT BUILDER
Making complex
things feel clear.
I’m Ram, a Product Designer and AI Product Builder. I design practical digital products and AI-assisted experiences, combining product thinking, UI/UX, interaction and visual craft.
Currently working across product/UI/UX and visual communication at Maphood, alongside independent AI-product work.
01 / SELECTED WORK
Work at its
actual stage.
Real company product work, an independently built AI-product project and a visual-design foundation. Unfinished evidence is labelled clearly.
+
02 / INDEPENDENT AI PRODUCTWORKING DEMO
Riya AI
Catalogue-based jewellery assistance with mandatory human handoff for discounts. Explore the product decisions and verified sample interaction.
03 / SELECTED VISUAL WORK · FIRST PROJECT AVAILABLEView visual practice
01 / COMPANY PRODUCT · ONGOING
Maphood.
Designing within a live product ecosystem.
The context
Maphood is a location-aware social product built around communities called Hoods, visual posts, reactions and place exploration. My work takes place within an existing company product alongside its founder and engineering team.
My contribution
My contributions span social and campaign graphics, print and promotional collateral, icons and visual assets, selected app and web interface work, and product-design discussions.
The structured UI/UX work is ongoing. This case study will document specific contributions and distinguish existing product behavior from proposed changes and verified implementation.
VISUAL COMMUNICATION
Across product and promotion
Social, campaign, print and icon work supporting Maphood’s visual identity. A curated selection will show the brief, my contribution and the final artwork.
Published
Social covers and print
Published platform covers and a printed 2 × 2 inch handout, presented as separate visual-communication projects.
View the visual workThe product story is taking shapeComing soon · See what will be added
The fuller case study will follow one focused journey. These sections will be added as their content and evidence are reviewed.
The existing experience
Annotated current-product screens and flows, with existing company design clearly credited.
A focused journey
One user task, its starting experience, design questions and constraints.
Research and decisions
Traceable findings, alternatives and rationale, with open questions kept visible.
Interfaces and interaction
Current and proposed comparisons, components and a reviewed interactive prototype.
Collaboration and delivery
Team feedback, approvals, handoff and implementation evidence where available.
Results and learning
Runtime checks and supported outcomes. No impact metrics are claimed at this stage.
The live company product and a proposed design are different stages. Released changes will be shown only after their implementation is verified.
02 / INDEPENDENT PRODUCT · INTERACTION CASE STUDY
Riya AI.
Help customers find products.
Keep commercial decisions human.
CONTEXT & SCOPE
A focused WhatsApp sales assistant
I conceived Riya for jewellery businesses handling product inquiries over WhatsApp. Customers would discover available products by budget, material and category; staff would retain control of discounts, negotiation and sensitive requests.
The starting problem—repeated inquiries and inconsistent responses—was a product hypothesis. Customer demand and commercial value still need independent validation. Payments, CRM, voice and inventory integrations were outside the initial scope.
THE AUTHORITY BOUNDARY
A discount is always a human decision.
Riya cannot offer, promise or approve discounts or similar concessions. These requests must escalate regardless of confidence. Product responses must stay within the business’s available catalogue; missing or unsupported data should lead to human help.
INTENDED END-TO-END JOURNEY
- DiscoverCustomer asks for gold rings within an INR budget.
- MatchRetrieve available catalogue items meeting supported constraints.
- EscalateA discount request moves to staff without a concession.
- Take overStaff reply while AI stays paused until deliberately resumed.
This is the intended WhatsApp journey. The public demo below verifies the browser-local review portion; it does not send customer messages.
VERIFIED INTERACTION / BROWSER SAMPLE
From a paused request to a recorded reply
Four states captured from the working demo. Open an image for a closer look.
Understand why it paused
Request, reason and context appear together. No discount is approved; an empty reply cannot be saved or resolved.
A draft is not a response
“Use as draft” fills the composer. Saving becomes available; resolution still requires a recorded reply.
Make the saved state explicit
The reply is labelled as recorded locally, not delivered. The resolve action becomes available.
Retain the workspace record
Resolution clears the queue. Refresh preserved the resolved status and saved reply in the sample conversation.
DESIGN REASONING
Boundaries before automation
Put the reason beside the request
Staff should see what needs attention and why before deciding how to respond.
Separate draft, save and delivery
Composing a message is not proof it reached a customer. The sample makes that distinction visible.
Keep ownership explicit
The backend pauses AI during human ownership and requires deliberate resumption, preventing competing replies.
Constrain product responses
Catalogue-rendered replies limit invented prices and promises, trading expressive freedom for control.
This explains the current design; it is retrospective analysis, rather than a claim that every decision was independently user-tested.
What works—and what is still unprovenImplementation evidence, tradeoffs and next validation
- Browser demo · verified
- Draft, saved reply, resolution and reload persistence checked on 3 October 2026. Sample data stays in this browser; WhatsApp and AI services are disconnected.
- Backend · implemented and merged
- Catalogue constraints, restricted-request escalation, human ownership and allowlisted sending are in the merged FastAPI repair. Sending is disabled by default. The repair passed 36 backend tests; this is not live WhatsApp delivery evidence.
- Operational verification · pending
- Deployed private frontend, real WhatsApp receipt, delivery tracking, independent staff alerts and recovery still need work or verification.
- User and business validation · pending
- No independent usability study, merchant adoption, sales uplift or achieved automation target is claimed.
What the walkthrough revealed
The sample allows resolution after a reply that only promises further review. Recording a response does not mean the customer’s request is settled. A follow-up should distinguish acknowledgment from completion and test those states with staff.
Next validation
Observe jewellery or customer-service staff reviewing a restricted request: do they understand the pause reason, what saving does, and when the request is truly resolved? Separately, verify the connected WhatsApp loop in isolated staging.
My contribution: sole human creator and product lead for the concept, research, scope, assistant rules and UX direction. ChatGPT, Codex and other software supported planning and implementation. This does not imply I personally wrote every line of code.
03 / SELECTED VISUAL WORK
Visual craft.
The foundation underneath my interface work.
MAPHOOD / VISUAL COMMUNICATION
Social Cover System
A social-cover system for Maphood, using bold typography, orange and black, and map-inspired routes and pins to communicate its real-life discovery theme across platform formats.
MAPHOOD / PRINT COLLATERAL
Offline Promotional Handout
A compact, two-sided handout for offline promotion. The front introduces Maphood’s “social map of real life” message; the reverse presents the app-download prompt, store badges and QR code.
Final artwork shown. Printed at 2 × 2 inches; images are enlarged here for viewing.
More visual work coming soon
Further branding, campaign, presentation and icon selections will be added as final artifacts and project context are reviewed.
02 / ABOUT
Visual craft,
growing into product.
I’m Ram Mishra, a Product Designer and AI Product Builder based in Jaipur. My background began in graphic and visual design and expanded into UI/UX, interaction design, product thinking and AI-assisted product building.
That progression gives me a combination of visual craft and product reasoning: I care about how an interface looks, how it behaves, why it exists and whether it solves the intended problem.
I’m particularly interested in practical digital products and teams where design works closely with product and engineering.
See the work
THE THREAD THROUGH THE WORK
01Visual communicationClarity, composition and craft
02UI/UX + interactionFlows, states and useful interfaces
03Product + AIDecisions, boundaries and working prototypes
03 / EXPERIENCE
Where and how
I’ve worked.
Real company context, independent AI-product building and a visual-design practice that supports both.
01 / COMPANY WORK · CURRENT
Maphood
Visual communication plus an increasing product/UI/UX contribution around the live product: interface analysis and design, interaction thinking, product discussion, social collateral, icons and collaboration with the founder and engineering team.
02 / INDEPENDENT PRODUCT
Riya AI
Concept, research, product scope and UX direction for an AI-assisted human-review workflow. A working portfolio demo exists; independent user validation and commercial outcomes remain open.
03 / FREELANCE DESIGN
Visual practice
Graphic design, branding, campaign collateral, presentations and selected digital work. A focused portfolio selection is currently being curated.
04 / CONNECT
Let’s talk about
useful work.
Open to Product Design and UI/UX opportunities in Jaipur or remote, plus selected freelance work and relevant collaborations.
rammishra.design@gmail.com