WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
Dec 12, 2024

Exploring Google Gemini and Generative AI

Connecting to Gemini is simple, but reliable prompt engineering is the real challenge. Learn to enforce JSON schemas and run zero-latency, offline AI natively in Chrome.

Pause
Mute Enter Fullscreen
#1 about 3 min

Establishing core paradigms for building generative applications

Establishing expectations around technical complexity versus the required logic abstraction needed for constructing intelligent models.

#2 about 4 min

Understanding Google Gemini history and available context models

Analyzing the differences in reasoning models and parsing capabilities when determining computational power tradeoffs.

#3 about 4 min

Accessing the generation systems through SDKs and platform keys

Evaluating ecosystem integrations and generating initial authentication keys without touching broader cloud platform provisioning.

#4 about 3 min

Testing logical instructions visually using automated source generation

Using visual sandbox tools to evaluate model reasoning and exporting the subsequent requests directly into source files.

#5 about 2 min

Implementing dynamic text flows using the Node SDK

Creating modular query scripts that process dynamic terminal inputs and parse variables efficiently against system logic.

#6 about 6 min

Evaluating diverse media sources via the multimodal interfaces

Uploading various media formats for robust analysis alongside automating file management structures based on internal logic.

#7 about 3 min

Maintaining context through conversational parameters and external histories

Implementing programmatic conversations by transmitting historical dialogues to explicitly manage continuous state transitions.

#8 about 3 min

Restricting operational profiles using precise system instruction configurations

Imposing rigid operational contexts and tone adjustments to shape specific personas suited for strict business requirements.

#9 about 4 min

Structuring model payloads precisely with custom JSON schemas

Replacing verbose markdown strings with explicitly structured payload arrays to mandate strictly parsed software outputs.

#10 about 3 min

Testing boundaries with generic application logic and failures

Assessing applied use cases ranging from algorithmic recommendation systems to uncovering critical failures inside deterministic probability trees.

#11 about 2 min

Reviewing supplementary platform features and secured enterprise environments

Evaluating deeper platform offerings such as corporate tier access and model grounding solutions to handle sensitive logic.

#12 about 8 min

Executing localized intelligence via Google Chrome platform implementations

Deploying localized native computation scripts entirely contained in browser clients without relying upon external network requests.

Matching moments

2:54 min

Leveraging Chrome AI and nano models for web applications

Raymond Camden · Perf + AI

50 sec

Building agentic artificial intelligence applications using Node.js

Julián Duque Julián Duque · WWC 2025

5:47 min

Integrating native generative artificial intelligence APIs into browser engines

Chris Heilmann +9 · LIVE

4:41 min

Exploring agentic browsers and artificial intelligence generation

Chris Heilmann +2 · LIVE

2:46 min

Enhancing native browser experiences with on-device generative AI

Chris Heilmann +2 · LIVE

5:05 min

Exploring popular generative AI models and applications

Mary Grygleski Mary Grygleski · LIVE

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

Beyond Vibe Coding: Using CLI Tools as Your AI Counterpart in Pair Programming

Ron Veen

Java enthusiast and Special agent for Team Rockstars IT

Ron Veen
Open session

World Congress 2026 North America

AI-Driven API Design

Mike Amundsen

Author, Adviser, Trainer

Mike Amundsen
Open session

World Congress 2026 North America

Small LLM in your Browser: Huge Opportunities for Web Applications

Daniel Ostrovsky

UI/UX Architect at Payoneer | AI Architect | Full Cycle Development Expert | Public Speaker | Open Source Contributor |

Daniel Ostrovsky
Open session

World Congress 2026 North America

The Broken Rung: How AI is Rebuilding Software Development from the Ground Up

Tomislav Tipurić

Chief Technology Officer, Nephos

Tomislav Tipurić
Open session

World Congress 2026 North America

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal

Related videos

Generate AI in the Browser with Chrome AI - Raymond Camden thumbnail
36:41
Perf + AI • 9 months ago

Generate AI in the Browser with Chrome AI - Raymond Camden

Raymond Camden

Google Gemma and Open Source AI Models - Clement Farabet thumbnail
47:25
about 1 year ago

Google Gemma and Open Source AI Models - Clement Farabet

Google Gemini: Open Source and Deep Thinking Models - Sam Witteveen thumbnail
50:12
Coffee With Developers • over 1 year ago

Google Gemini: Open Source and Deep Thinking Models - Sam Witteveen

Sam Witteveen

Exploring the Future of Web AI with Google thumbnail
33:51
Coffee With Developers • over 1 year ago

Exploring the Future of Web AI with Google

Thomas Steiner

AI in Your Browser: Exploring Chrome's Built-In LLM thumbnail
29:59
WWC Europe 2026 • about 1 month ago

AI in Your Browser: Exploring Chrome's Built-In LLM

Daniel Ostrovsky

Prompt API & WebNN: The AI Revolution Right in Your Browser thumbnail
30:36
WWC 2025 • 12 months ago

Prompt API & WebNN: The AI Revolution Right in Your Browser

Christian Liebel

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.