Build a Offline, Privacy-first Personal Finance Assistant with LiteRT JS and Gemma 4

Get hands-on with LiteRT.js and Google's open-source Gemma 4 models. Learn to retrieve models from Hugging Face and leverage WebGPU for high-performance in-browser inference.

Key Takeaways: Setting up LiteRT-LM; optimizing WebGPU for browser acceleration; designing offline-first security.

Slide Deck: https://docs.google.com/presentation/d/1uurdocDeLhBKhYf1K4IKFg066LD5v-VFAQbskWA18DA/edit?usp=sharing

YouTube: https://youtu.be/shFsYiugCjE?si=_pPx1TwbItNJopUS

In-Browser AI Meets the Cloud: Building Smarter Web Apps with Firebase

To build fast and cost-effective web applications, developers can split AI workloads between the user's browser and the cloud using Firebase. This talk demonstrates this hybrid approach through a live web app demo: we use a lightweight, in-browser model (Gemini Nano) to quickly handle simple client-side tasks like generating image descriptions and alt text, while routing complex demands—like live web searches and image generation—to powerful cloud-based models like Gemini Flash. Attendees will learn how to implement this practical workflow to balance performance, cost, and user experience in their own web projects.

Agentic Auditor: Spotting the Gaps with AI Reasoning

Most AI implementations focus on retrieval—finding information that exists. But in high-stakes industries like compliance, legal, and ESG, the most critical question isn't "What is there?" but rather "What is missing?"

Traditional RAG (Retrieval-Augmented Generation) patterns often fail at gap analysis because they rely on semantic similarity, which struggles to identify incomplete information. To solve this, we need to move from simple pipelines to Agentic Reasoning.

In this session, I will demonstrate an Agentic Auditor that performs automated gap analysis of an answer against a structured checklist. We will dive deep into how an agent can "reason" through a checklist to identify semantic discrepancies and missing requirements.

Go deep with Nano Banana - Use Angular + Firebase AI Logic to build a Photo Edit App

In this session, I want to show that Firebase AI Logic, Angular and Nano Banana make photo editing easy.

in the session, I can show photo creation, editing, fusing, restoration, and 2D-to-3D transformation.

https://youtu.be/oIGuUgum3Ws?si=Jc4GSRAtNNZw72QJ

Build Dynamic Apps in AI: Decouple Prompts with Firebase & Angular

Hardcoding AI prompts in frontend JSON files creates a deployment bottleneck every time you need to tweak an image style or fix a hallucination. In this session, we will build a scalable Angular v21 app that decouples its AI logic using Firebase Server Prompt Templates. Learn how to move Nano Banana 2 prompts to the cloud, manage versioning with Remote Config, and connect real-time `onConfigUpdate` listeners to Angular signals to push live AI updates instantly - zero redeployments required.

Slide Deck: https://docs.google.com/presentation/d/1CNvkiGkMMhFk3NLa9zvV121QFZ6VoDw9IKIPcBSEM7w/edit?usp=sharing