Boris-Wilfried Nyasse
GDE
Montréal, Canada
Actions
I am a technology leader with over a decade of experience in the software development industry, and I'm proud to be a member of the Google Developer Expert program. Throughout my career, I've had the privilege of collaborating with leading technology companies, including extensive experience working with Google Cloud technologies.
Beyond my managerial achievements, I'm passionate about technology education and leadership. I'm an enthusiastic speaker at tech conferences, sharing insights and expertise. I also offer training and mentorship to aspiring developers, empowering them to excel in the ever-evolving tech landscape.
I've specialized in enabling transitions to innovative tech solutions, often built upon Google's cutting-edge offerings.
Area of Expertise
Topics
Beyond Word Games: Crafting Production-Ready AI Agents for Interactive Gaming
AI agents are revolutionizing interactive entertainment by creating dynamic, adaptive, and truly immersive experiences. But how do you transform a simple word game into an intelligent, multi-modal companion that can see, understand, and respond like a human player?
This session explores the cutting-edge intersection of 𝘃𝗶𝘀𝗶𝗼𝗻 𝗮𝗻𝗱 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗔𝗜, demonstrating how we evolved a traditional Scrabble game into a production-ready AI gaming companion powered by Google's latest Gemini 2.5 Pro model. You'll witness firsthand how multi-modal AI can process visual board states, generate natural language explanations, and deliver personalized gaming experiences that adapt to player behavior in real-time.
𝗪𝗵𝗮𝘁 𝘆𝗼𝘂'𝗹𝗹 𝗹𝗲𝗮𝗿𝗻:
• 𝗕𝘂𝗶𝗹𝗱 𝗶𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝘁 𝗺𝘂𝗹𝘁𝗶-𝗺𝗼𝗱𝗮𝗹 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁s that seamlessly combine computer vision, natural language processing, and voice synthesis to create engaging game companions
• 𝗜𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 𝘃𝗶𝘀𝘂𝗮𝗹 𝗽𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴 using Gemini 2.5 Pro's advanced vision capabilities to analyze game boards, detect patterns, and suggest optimal moves
• 𝗗𝗲𝘀𝗶𝗴𝗻 𝗮𝗱𝗮𝗽𝘁𝗶𝘃𝗲 𝗴𝗮𝗺𝗶𝗻𝗴 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲𝘀 with Flutter and Firebase that scale from prototype to production while maintaining sub-second response times
• 𝗖𝗿𝗲𝗮𝘁𝗲 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗲𝗱 𝗔𝗜 𝗲𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲𝘀 that learn from player interactions and evolve their communication style and difficulty level dynamically
• 𝗗𝗲𝗽𝗹𝗼𝘆 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗔𝗜 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 using Google Cloud Services (Vertex AI, Text-to-Speech) with robust error handling and performance optimization
𝗟𝗶𝘃𝗲 𝗗𝗲𝗺𝗼𝗻𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻𝘀:
Watch as our AI agent analyzes a Scrabble board in real-time, explains strategic thinking in natural language, and provides voice-guided coaching—all while maintaining the engaging, competitive spirit that makes gaming fun.
𝗧𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝗗𝗲𝗲𝗽-𝗗𝗶𝘃𝗲:
From computer vision preprocessing to multi-modal prompt engineering, you'll see the complete pipeline that transforms visual input into intelligent, contextual responses. We'll explore the architectural decisions, performance optimizations, and production challenges that bridge the gap between experimental AI and reliable gaming experiences.
𝗞𝗲𝘆 𝗧𝗲𝗰𝗵𝗻𝗼𝗹𝗼𝗴𝗶𝗲𝘀:
• Gemini 2.5 Pro (Multi-modal capabilities)
• Flutter & Firebase (Real-time gaming infrastructure)
• Google Cloud Services (Vertex AI, Text-to-Speech)
• Computer Vision APIs
• Advanced prompt engineering techniques
Walk away with practical patterns for building AI agents that don't just process data—they create meaningful, interactive experiences that users love.
🎯 𝗔𝘂𝗱𝗶𝗲𝗻𝗰𝗲 𝗟𝗲𝘃𝗲𝗹: Intermediate to Advanced
Perfect for developers ready to move beyond basic AI integrations
📋 𝗣𝗿𝗲𝗿𝗲𝗾𝘂𝗶𝘀𝗶𝘁𝗲𝘀:
• Experience with mobile/web development (Flutter knowledge helpful but not required)
• Basic understanding of AI/ML concepts and API integrations
• Familiarity with cloud services and real-time architectures
🛠 𝗧𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝗦𝘁𝗮𝗰𝗸:
• 𝗔𝗜 𝗣𝗹𝗮𝘁𝗳𝗼𝗿𝗺: Gemini 2.5 Pro (Multi-modal capabilities)
• 𝗙𝗿𝗼𝗻𝘁𝗲𝗻𝗱: Flutter with real-time state management
• 𝗕𝗮𝗰𝗸𝗲𝗻𝗱: Firebase (Firestore, Cloud Functions)
• 𝗖𝗹𝗼𝘂𝗱 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝘀: Google Cloud Platform (Vertex AI, Text-to-Speech, Vision API)
• Architecture: Event-driven microservices, WebSocket connections
🚀 𝗞𝗲𝘆 𝗧𝗮𝗸𝗲𝗮𝘄𝗮𝘆𝘀:
• Production-ready AI agent patterns specifically designed for interactive applications
• Multi-modal integration strategies that combine vision, language, and speech seamlessly
• Real-time gaming architectures that scale while maintaining sub-second response times
• Advanced prompt engineering techniques for consistent, contextual AI responses
• Performance optimization methods for mobile AI applications with limited resources
📽 𝗙𝗼𝗿𝗺𝗮𝘁: Technical deep-dive with live coding demonstrations, architectural diagrams, and real-time AI interactions
💡 What Makes This Session Unique: You'll see a complete, working AI gaming system in action—not just theory, but battle-tested code running in production.
Building the Chain of Trust: A Google ADK Blueprint for Grounded Legal AI Agents
𝗟𝗲𝗴𝗮𝗹 𝗔𝗜 demands zero tolerance for 𝗵𝗮𝗹𝗹𝘂𝗰𝗶𝗻𝗮𝘁𝗶𝗼𝗻𝘀. When an attorney asks an AI assistant about case precedents, "creative" answers aren't innovative—they're malpractice waiting to happen. How do you transform a 𝗚𝗲𝗺𝗶𝗻𝗶 𝗺𝗼𝗱𝗲𝗹 from an eloquent improviser into a rigorous legal expert? How do you build an AI system that doesn't just cite sources, but proves every claim with verifiable documentation?
This session reveals the architecture of a "𝗖𝗵𝗮𝗶𝗻 𝗼𝗳 𝗧𝗿𝘂𝘀𝘁"—a production-tested pipeline for building AI agents that earn credibility through verification. Drawing from a real-world legal AI project, we'll trace the complete journey of a fact-checked response, from document ingestion to the final Flutter interface.
You will learn how to:
• 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗮 𝗴𝗿𝗼𝘂𝗻𝗱𝗲𝗱 𝗮𝗴𝗲𝗻𝘁 𝘄𝗶𝘁𝗵 𝗚𝗼𝗼𝗴𝗹𝗲 𝗔𝗗𝗞, constraining a Gemini model to reason exclusively over your private legal corpus using Vertex AI Search, eliminating hallucinations at the source
• 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁 𝗮 𝗵𝘆𝗯𝗿𝗶𝗱 𝗔𝗜 𝗯𝗮𝗰𝗸𝗲𝗻𝗱 that orchestrates lightweight Cloud Functions for rapid document classification alongside a powerful Cloud Run agent for complex multi-step legal analysis
• 𝗕𝘂𝗶𝗹𝗱 𝗮 𝗰𝗿𝗶𝘁𝗶𝗰𝗮𝗹 𝗣𝘆𝘁𝗵𝗼𝗻 𝘃𝗮𝗹𝗶𝗱𝗮𝘁𝗶𝗼𝗻 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲 that acts as an automated fact-checker, mapping AI outputs to canonical sources in Firestore and providing an audit trail for every claim
• 𝗗𝗲𝘀𝗶𝗴𝗻 𝗮 𝘁𝗿𝘂𝘀𝘁-𝗳𝗶𝗿𝘀𝘁 𝗙𝗹𝘂𝘁𝘁𝗲𝗿 𝗨𝗜 that uses reactive services to asynchronously enrich responses with source verification, ensuring users see proof alongside every answer
• 𝗢𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗲 𝗯𝘂𝗹𝗹𝗲𝘁𝗽𝗿𝗼𝗼𝗳 𝗱𝗮𝘁𝗮 𝗳𝗹𝗼𝘄𝘀 across Firestore and Cloud Storage that maintain data integrity throughout the entire pipeline
This isn't academic theory—it's a battle-tested playbook from the legal trenches. Walk away with the architectural blueprint and practical knowledge to build AI applications that don't just answer questions, but earn institutional trust through verifiable proof.
𝗟𝗲𝗴𝗮𝗹 𝗔𝗜 can't afford to 𝗵𝗮𝗹𝗹𝘂𝗰𝗶𝗻𝗮𝘁𝗲. When legal professionals depend on AI for document research, "creative" answers become liability risks. How do you build AI agents that prove every claim with verifiable sources?
This session presents a production-tested "𝗖𝗵𝗮𝗶𝗻 𝗼𝗳 𝗧𝗿𝘂𝘀𝘁"—an architectural blueprint that transforms 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗔𝗗𝗞 𝗮𝗻𝗱 𝗩𝗲𝗿𝘁𝗲𝘅 𝗔𝗜 𝗦𝗲𝗮𝗿𝗰𝗵 into a rigorous legal assistant. We'll explore how to ground Gemini models on private legal corpora, architect hybrid backends that balance speed with complexity, and implement Python validation layers that fact-check every AI response against canonical sources.
From document ingestion through 𝗙𝗹𝘂𝘁𝘁𝗲𝗿 𝗨𝗜, you'll see how a reactive architecture ensures users receive not just answers, but proof. We'll dive into real code, production patterns, and the hard-won lessons from building AI systems where accuracy isn't optional—it's legal.
Leave with a proven playbook for building AI applications that earn trust through transparency and verification.
𝗞𝗲𝘆 𝗧𝗮𝗸𝗲𝗮𝘄𝗮𝘆𝘀:
• 𝗣𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 𝗳𝗼𝗿 𝗴𝗿𝗼𝘂𝗻𝗱𝗲𝗱 𝗔𝗜 agents using Google ADK
• 𝗛𝘆𝗯𝗿𝗶𝗱 𝗯𝗮𝗰𝗸𝗲𝗻𝗱 𝗽𝗮𝘁𝘁𝗲𝗿𝗻𝘀 𝗳𝗼𝗿 𝗔𝗜 𝘄𝗼𝗿𝗸𝗹𝗼𝗮𝗱𝘀 (Cloud Functions vs Cloud Run)
• 𝗩𝗮𝗹𝗶𝗱𝗮𝘁𝗶𝗼𝗻 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀 that eliminate hallucinations through source verification
• 𝗧𝗿𝘂𝘀𝘁-𝗳𝗶𝗿𝘀𝘁 𝗨𝗜 𝗽𝗮𝘁𝘁𝗲𝗿𝗻𝘀 that display proof alongside AI responses
• Real-world lessons from high-stakes 𝗔𝗜 𝗱𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁 𝗶𝗻 𝗹𝗲𝗴𝗮𝗹 𝗱𝗼𝗺𝗮𝗶𝗻
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