AI Product Designer & Applied AI Engineer

I design the interface, then build what runs behind it 

Thirteen years designing enterprise software for network engineers at HPE, Juniper Networks, Riverbed, and Cisco. Now applying that same rigor to RAG systems, AI agents, and MCP integrations — one person doing the research, the interaction design, and the implementation.

Fig. 0 — Typical Agent Pipeline USER RETRIEVE REASON REPLY query context answer VECTOR STORE · TOOLS · MCP SERVERS

About

Fig. 1

I'm Melinda Arora, a UX designer turned AI product builder, based in Bengaluru. For over a decade I've led interaction design across some of the most technically dense domains in software — network management, cybersecurity, and enterprise infrastructure — shipping products that engineers actually trust in high-stakes environments.

In 2026 I started closing the loop between design and implementation: learning to build the RAG pipelines, AI agents, and MCP-connected tools that used to sit on the other side of a handoff. I now take AI-powered products from research through to a working build — one person, one throughline, no translation loss between the design and the code.

I'm HFI-certified in usability analysis and experience design, IDEO-certified in Design Thinking, and hold four U.S. patents for interface and security-tooling inventions built during my time at HPE and Juniper.

Patents on Record
  • In-context chatbot guidance — method for interactive, contextual user assistance
  • Firewall rule analysis — interface for evaluating rule conflicts
  • Firewall policy management GUI — visual system for enterprise policy control

Capabilities

Fig. 2
Design
  • Field research & competitive analysis
  • Persona development & journey mapping
  • Information architecture
  • Interaction design & prototyping
  • Usability testing & heuristic evaluation
  • Design systems
Build
  • RAG pipeline architecture (LangChain, vector search)
  • Multi-agent orchestration (LangGraph)
  • MCP server design & deployment
  • Prompt engineering & evaluation
  • Vision-LLM & document AI (Claude, GPT-4o)
  • Workflow automation (n8n)

Credentials

Fig. 3
Human Factors Int'l Certified Experience Analyst (CXA) 2021
Human Factors Int'l Certified Usability Analyst (CUA) 2019
IDEO Foundations in Design Thinking 2013
DeepLearning.AI LangChain for LLM Application Development 2026
DeepLearning.AI Building & Evaluating Advanced RAG 2026
DeepLearning.AI × Anthropic MCP: Build Rich-Context AI Apps 2026
DeepLearning.AI × LangChain Long-Term Agentic Memory with LangGraph 2026
Udemy Machine Learning A-Z: ML, DL, AI with AWS 2026
University of Michigan Python for Everybody (Specialization) 2026

Selected Work

Fig. 4
01 / DocMind

A RAG assistant for buried documentation

Internal teams asked plain-language questions against years of scattered docs and got answers with citations back to source, instead of another folder to search manually.

LangChain Pinecone React
02 / Relay

A multi-agent research orchestrator

A supervisor agent plans a research task, delegates it to worker agents, and routes the result through a human approval step before anything ships.

LangGraph MCP Python
03 / FieldLens

A vision-LLM estimating assistant

Photos and blueprint scans become structured takeoffs and cost estimates for trade contractors, replacing manual line-item entry from a PDF.

Claude Vision RAG PDF Parsing
04 / Anchor

An MCP-connected research copilot

A desktop assistant reaches into a team's live docs, tickets, and calendars through custom MCP servers, so answers stay current without copy-paste.

MCP FastMCP Claude

How I Work

Fig. 5
01

Research & define

Field research, user interviews, and a scoped problem statement before any architecture gets picked.

02

Architect

Data sources, retrieval strategy, and agent design mapped out — the decisions that are expensive to change later.

03

Prototype & build

Working interface and working pipeline, built together so neither one gets designed in a vacuum.

04

Evaluate

Usability testing alongside model evals — accuracy and groundedness checked the same way heuristics are.

05

Ship & monitor

Deployed, instrumented, and watched — with a plan for what happens when the model or the data shifts.