Simar Preet Singh
Senior Software Engineer | Web AI Tech Speaker | Web - Angular - React | Full Stack
Mohali, India
Actions
Simar Preet Singh is a dynamic, motivated and result oriented professional with more than 8 years of experience in the Software Engineering industry and loves contributing to the Dev Community. His motto is "Thrive and Uplift". He is skilled in Node.js, Angular, Reactjs, Ionic, Capacitor, Nodejs and Firebase. Currently, he is working as a Senior Software Engineer Freelancer and consulting multiple clients. He is also the organiser of GDG Jalandhar.
Area of Expertise
Topics
Offline Capable ChatBots with Prompt API
1. Talk Details: Offline-Capable Chatbots with Prompt API
2. Why On-Device AI Matters
Explain how AI is moving from cloud-based systems to on-device intelligence.
Introduce Gemini Nano, Chrome’s built-in language model.
Highlight its benefits: faster speed, stronger privacy, and lower cost.
3. Meet Chrome’s Prompt API
Show how developers use the Prompt API to connect directly with Gemini Nano.
No API keys. No latency. No external calls.
The AI runs entirely inside the browser.
4. AI in Your Browser: Simple, Fast, and Private
Explain how developers build chatbots, writing tools, and assistants that run offline.
Focus on three main benefits: instant response, full privacy, and zero API cost.
5. How It Works (Without a Live Demo)
Walk attendees through setup.
1. Enable the Prompt API.
2. Access Gemini Nano using JavaScript.
3. Send prompts locally.
Provide a “Try It Out” link and GitHub code for attendees to test it themselves.
6. On-Device vs Cloud LLMs
Clarify when to use each option.
• On-Device: fast, private, offline-ready.
• Cloud LLMs: powerful, large context, scalable.
7. The Future of Web AI
Show how on-device AI is changing web development.
Web apps will be AI-native, privacy-first, and fast.
The Prompt API is where this transformation begins.
Make your web app agent-ready with WebMCP
AI agents can browse the web but they don’t truly understand it.
Most current solutions rely on screen scraping or vision models that interpret UIs as images. The result is slow, fragile systems that break on dynamic interfaces. Custom backend integrations improve control but introduce setup complexity and eliminate real-time discoverability.
What if the web itself could expose structured capabilities directly to AI agents?
In this talk, we introduce WebMCP, a new approach where web applications define native, structured tool contracts inside the browser, enabling agents to interact with them reliably without scraping or custom integrations.
You will see how agents can discover tools on the fly, execute actions through JSON schemas, and stay in sync with application state, all mediated securely by the browser.
We will walk through real implementation patterns using Reactjs, explore how to design effective tool contracts, and cover authentication, debugging, and production considerations.
If you’re building modern web apps or working with AI agents, this session will give you a practical blueprint to move from fragile automation to scalable, AI-native web experiences.
What participants build: a working set of WebMCP tools registered on the starter app, plus one agent-driven task run end to end.
What they take home: a reusable pattern for turning any app action into an agent-callable tool, and a checklist for deciding which actions are safe to expose.
Prerequisites: basic React, JavaScript or TypeScript
Function Calling with Gemini: Let Your App’s Features Become Tools
A chatbot that only talks is a demo. A chatbot that can act inside your app is a product. In this station, participants connect Gemini to the starter app using function calling. You define a few app functions, describe them to the model, and let it decide when to call them based on what the user types. We’ll cover writing good function descriptions, handling the model’s arguments safely, and showing the user what the AI did. We’ll use a bring-your-own-key setup with a model selector, so nothing sensitive sits on a server.
What participants build: a small AI assistant inside the starter app that can call two or three of its functions from natural-language requests.
What they take home: a working function-calling loop they can copy into their own projects, plus a short list of guardrails (validation, confirmations, limits).
Prerequisites: basic React (JavaScript or TypeScript), and a free Gemini API key from Google AI Studio. No other stations needed.
Beyond the Cloud: Running On-Device AI in the Web and Mobile
Cloud-hosted LLMs and vision models have simplified AI integration, but they introduce heavy trade-offs: continuous API expenses, high latency over mobile networks, mandatory internet connectivity, and data privacy concerns.
Running inference directly on consumer client devices, utilizing client-side GPUs, NPUs, and CPU threads, solves these pain points. However, shipping on-device AI requires balancing hardware limitations, binary sizes, thermal throttling, and model quantization.
In this deep-dive joint session, two engineers will walk you through the practical reality of local inference across the two largest client frontiers: the Modern Web and Cross-Platform Mobile (Flutter).
What We’ll Cover:
1. Foundations of Local Inference
2. Local AI in the Browser with Transformers.js
3. On-Device AI on Mobile with Flutter & LiteRT-LM
4. Web vs. Mobile: Architectural Comparison & Hybrid Patterns
AI That Runs Offline: In-Browser offline Models with Transformers.js and Gemma
Not every user has fast internet, and not every feature should send data to a server. In this station, participants add an on-device AI feature to the starter app using Transformers.js. The model downloads once, runs in the browser on WebGPU, and falls back to WASM on weaker devices. You’ll learn how to pick a model size for the device in front of you, how caching works so the download only happens once, and where small models fall short. The pattern comes from an offline recipe generator I built that runs entirely in the browser with no server round-trip.
What participants build: an offline AI feature (such as summarising or classifying text) with a model loader, a progress indicator and a WebGPU-to-WASM fallback.
What they take home: a working in-browser inference setup, plus a rule of thumb for choosing between small and larger models per device.
Prerequisites: basic React or JavaScript. A laptop with a recent Chrome or Edge is recommended.
Notes for organisers: the first model download is the slow part. I can point to a smaller model for low-bandwidth venues. Please confirm that the venue Wi-Fi can handle it.
Offline Chatbots with WebLLM
Modern web applications rely heavily on cloud-based AI, but this comes with trade-offs: latency, cost, and privacy concerns. What if powerful AI models could run entirely inside the browser, even without an internet connection?
In this talk, we’ll explore WebLLM, a cutting-edge approach to running Large Language Models directly in the browser using WebGPU. You’ll learn how offline-capable chatbots can be built using JavaScript: no servers, no API keys, and no data leaving the user’s device.
This session is designed for web developers curious about the future of privacy-first, offline-ready AI experiences on the web.
Firebase Genkit: Power your Apps with AI
This session will help the audience understand how they can easily build their web apps using Firebase Genkit which uses Gemini/VertexAI/OpenAI APIs with ease. Users of GenKit can either integrate Genkit in their Nodejs based Backend or Firebase Cloud Functions for serverless approach.
This session will be a 30-40 minutes session which will include, what, why and how of Genkit. It will also include basic intro to prompt engineering and the topic of Genkit Flows and Genkit CLI.
What's new in Angular 18
A brief session discussing the latest updates in Angular including small examples about topics:
1. Angular V18
2. How to update?
3. Signals in Angular
4. Hydration in Angular
5. Going Zoneless etc.
Offline ChatBots and Agents with Prompt API
1. Talk Details: Offline-Capable Chatbots with Prompt API
2. Why On-Device AI Matters
Explain how AI is moving from cloud-based systems to on-device intelligence.
Introduce Gemini Nano, Chrome’s built-in language model.
Highlight its benefits: faster speed, stronger privacy, and lower cost.
3. Meet Chrome’s Prompt API
Show how developers use the Prompt API to connect directly with Gemini Nano.
No API keys. No latency. No external calls.
The AI runs entirely inside the browser.
4. AI in Your Browser: Simple, Fast, and Private
Explain how developers build chatbots, writing tools, and assistants that run offline.
Focus on three main benefits: instant response, full privacy, and zero API cost.
5. How It Works (Without a Live Demo)
Walk attendees through setup.
1. Enable the Prompt API.
2. Access Gemini Nano using JavaScript.
3. Send prompts locally.
Provide a “Try It Out” link and GitHub code for attendees to test it themselves.
6. On-Device vs Cloud LLMs
Clarify when to use each option.
• On-Device: fast, private, offline-ready.
• Cloud LLMs: powerful, large context, scalable.
7. The Future of Web AI
Show how on-device AI is changing web development.
Web apps will be AI-native, privacy-first, and fast.
The Prompt API is where this transformation begins.
Devfest Jaipur 2025 Sessionize Event
DevFest Jalandhar 2025 Sessionize Event
Google I/O Extended Kathmandu LITE 2025 Sessionize Event
Google I/O Extended 2024 Jalandhar Sessionize Event
Google I/O Extended Kathmandu Sessionize Event
GDG Ludhiana DevFest 2022 Sessionize Event
Simar Preet Singh
Senior Software Engineer | Web AI Tech Speaker | Web - Angular - React | Full Stack
Mohali, India
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top