Algolia Agent Studio Challenge Submission

Sundaram Kumar Jha — Wed, 04 Feb 2026 22:43:43 +0000

This is a submission for the Algolia Agent Studio Challenge: Consumer-Facing Conversational Experiences

What I Built

ShopMate is an intelligent, conversational shopping assistant designed to replace rigid filter menus with a human-like advisory experience.

Most e-commerce search bars force users to think in keywords ("gaming laptop 16gb ram") rather than intent ("I need a powerful laptop for playing Cyberpunk 2077"). ShopMate solves this by allowing users to express complex needs naturally. It acts as a knowledgeable sales associate that can understand specific criteria (budget, brand, features), retrieve real-time inventory, and present comparisons in a friendly, conversational format.

Demo

Live Link: [https://shopmate-theta.vercel.app/]
Source Code: [https://github.com/sundaram2021/shopmate]
Demo Link: [https://github.com/sundaram2021/shopmate/blob/main/README.md]

How I Used Algolia Agent Studio

I leveraged Algolia as the critical grounding layer for my AI agent, ensuring hallucinations are impossible and product data is always accurate.

Data Indexed: I indexed a comprehensive catalog of consumer electronics (laptops, cameras, drones, etc.) into an Algolia index named styles. This data includes structured attributes like price, rating, brand, and rich descriptions.

Data Schema:

{
  "name": "360fly - Panoramic 360° HD Video Camera",
  "description": "This 360fly panoramic 360° HD video camera features Wi-Fi...",
  "brand": "360fly",
  "categories": ["Cameras & Camcorders", "Digital Cameras"],
  "price": 399.99,
  "price_range": "200 - 500",
  "image": "https://cdn-demo.algolia.com/...",
  "rating": 5,
  "objectID": "9131042"
}

Agentic Retrieval: I built a custom agent using Google Gemini 2.0 Flash. Instead of relying on the model's internal training data (which is outdated and generic), I gave the model a "Tool" called searchProducts.
Prompt Engineering: My system prompt explicitly instructs the agent: "ALWAYS use the searchProducts function when users ask about products."
Workflow:
1. User asks: "Show me 4K drones under $1000."
2. The Agent parses this intent into an Algolia query (query: "4K drone", filters: "price < 1000").
3. Algolia's search engine executes the query and returns exact, ranked matches.
4. The Agent summarizes these specific results back to the user.

Why Fast Retrieval Matters

In a conversational interface, latency kills the experience. If an AI takes 5 seconds to "think," it feels robotic.

Algolia's search is uniquely suited for this because of its speed. The retrieval step typically takes milliseconds, meaning the "tool execution" phase of the LLM pipeline is virtually instantaneous. This allows ShopMate to feel fluid and responsive, maintaining the illusion of talking to a real person who knows the inventory by heart. Furthermore, Algolia's typo tolerance ensures that even if a user types "droon" or "labtop," the correct structured data is retrieved for the AI to process.

Submission for Portfolio Challenge

Sundaram Kumar Jha — Fri, 23 Jan 2026 12:28:59 +0000

This is a submission for the New Year, New You Portfolio Challenge Presented by Google AI

About Me

Hi, I'm Sundaram, a Backend Engineer based in New Delhi (GMT +5:30). I have a passion for building robust systems and believe that "Systems should feel easy."

My work spans across full-stack development, distributed systems, and AI agent architectures. I enjoy creating tools that improve developer experience and exploring the intersection of systems engineering and artificial intelligence.

Portfolio

Link to Portfolio App

The portfolio showcases my journey and projects, wrapped in a unique hand-drawn aesthetic that breaks away from standard corporate designs.

How I Built It

My portfolio is a modern web application built with performance and design in mind.

Tech Stack

Framework: Next.js 16 (App Router) for server-side rendering and performance.
Language: TypeScript & React 19.
Styling: Tailwind CSS v4 for rapid styling, coupled with Framer Motion for fluid animations.
Deployment: containerized with Docker and deployed on Google Cloud Run for scalability and ease of management.

Google AI Integration

Antigravity: This Portfolio project uses Gemini Flash 3 (via Antigravity) alongside agent skills to build the best frontend design.
Google Cloud Run: The portfolio is hosted on Google Cloud Run, leveraging its serverless container platform for reliable, scalable delivery.

Design Decisions

I chose a Neo-Brutalist / Hand-Drawn aesthetic to make the site feel personal and creative.

Sticky/Badge Elements: Used to give a playful "notebook" feel.
Dynamic Animations: Elements float, rotate, and react to hover, making the interface feel alive.
Custom Illustrations: SVG doodles that reinforce the "sketchbook" vibe.

What I'm Most Proud Of

The Unique Aesthetic: I'm proud of stepping away from generic templates to create a design that truly reflects my personality—fun, creative, but technically grounded.
Next.js 16 Adoption: Implementing the latest features of Next.js 16 and React 19 ensures the site is future-proof and blazing fast.
The "Feel": I stayed true to my motto: "Systems should feel easy." The navigation is intuitive, and the content is presented in a way that is easy to digest despite the technical depth.

DEV Community: Sundaram Kumar Jha