Mustapha Adekunle
Data Engineer and Advocate. 5X Google Cloud Certified. Google Developer Expert (GCP)
Lagos, Nigeria
Actions
Mustapha is a passionate data professional with expertise in Google Cloud Platform, spanning data and analytics engineering, database engineering, and community engagement. His background allows him to bridge the gap between business objectives and technical solutions, designing, building, and securing efficient data processing systems. As a Data Engineer and Advocate, Mustapha is dedicated to empowering others to leverage data effectively and securely through their writing, speaking engagements, and online content.
Area of Expertise
Topics
AI Agents: The Frontiers of LLMs – Architecting Scalable Autonomy
The industry has mastered the chatbot; the next frontier is autonomy. We are rapidly moving from Large Language Models that simply generate text to AI Agents that can reason, plan, and execute complex workflows on behalf of users. But how do you architect a system that is reliable, scalable, and safe?
This session provides a technical blueprint for engineering robust AI Agents. We will move beyond basic prompt engineering to dissect the cognitive architecture of an agent; the "Think, Plan, Act, Reflect" loop, and explore essential design patterns like ReAct and Human-in-the-Loop (HITL) that turn stochastic model outputs into deterministic actions.
Crucially, we will address the issues that come with multi-agent orchestration. You will learn how to implement standardized communication protocols, specifically the Model Context Protocol (MCP) for tool decoupling and the Agent2Agent (A2A) protocol for collaboration, to treat agents as interoperable microservices.
To ground these concepts in reality, we will tear down the architecture of "Instavibe," a hyper-personalized social listening application built on Google Cloud and Vertex AI. We will demonstrate how real-time social data streams are processed by a cooperative swarm of specialized agents (a Profiler, a Planner, and an Integrator) to solve complex user problems.
Audience Takeaways:
1. Architectural Patterns: How to implement the reasoning loops (ReAct/Reflect) required for autonomy.
2. Standardization: Practical application of MCP and A2A protocols to build scalable "societies" of agents.
3. Real-World Implementation: A deep dive into a production-grade architecture on Google Cloud (Cloud Run, Spanner, Vertex AI).
Agent Context Engineering for Production
LLMs are inherently stateless, making agentic reliability highly dependent on context engineering. Even a 5% drop in per-step accuracy can cause a 14-point drop in reliability over three chained agent calls. Getting context right is the difference between a demo and a production system.
This session covers how to optimize the context window with tools, skills, memories, and history using ADK. We will explore on-demand tool retrieval, progressive-disclosure skills, and context compaction for long-running agents. We will dive deep into Memory Bank to see how noisy session events become refined, durable memories, how to customize them via topic definitions and few-shot examples, and when to inject them.
Leave with a framework for context control, state persistence, action routing, and insights into the 2026 Gemini Enterprise roadmap.
Agent Context Engineering for Production
LLMs are inherently stateless; they can't access fresh information, read private data, or take multi-step action on their own. Every agentic technique that exists today is really just a different answer to the same question: how do you give a model exactly the right information, in the right structure, at the right time? Get this wrong, and the failure compounds; a 5% drop in per-step accuracy becomes a 14-point drop in reliability over just three chained agent calls. Get it right, and you've built the difference between a demo and a production system.
In this session, you'll learn how to treat the context window like a suitcase, packing in tools, skills, memories, and session history without letting it become the bottleneck and see how ADK handles this through on-demand tool retrieval, progressive-disclosure skills, and context compaction for long-running agents. We'll go deep on Memory Bank: how raw, noisy session events get extracted and consolidated into refined, durable memories; what gets remembered by default; how to customise it with topic definitions and few-shot examples; and when to inject
Attendees will leave with a practical framework for context control, state persistence, and action routing, plus resources to go deeper on multi-agent systems.
Vertex AI Embeddings API + Vector Search Grounding LLMs made easy
In this talk, I'll showcase how Google's Vertex AI Embeddings API can simplify grounding large language models (LLMs) using Vector Search. We'll explore how the API helps generate high-quality embeddings for unstructured data, making it easier to query, retrieve, and match relevant information in real time. By combining embeddings with vector search, we can enhance the performance and relevance of LLMs in a variety of AI applications. Attendees will gain practical insights into building smarter, more efficient AI models.
Navigating Burnout: Your Guide to thriving in the workspace.
Description:
- Feeling exhausted and overwhelmed by the demands of your professional life?
- Struggling to maintain a healthy work-life balance?
- Worried that burnout is impacting your well-being and career?
This talk explores the complex world of burnout and equips you with practical strategies to thrive in the workplace. Attendees will gain a deeper understanding of burnout, its signs, and how to prevent it.
The session will cover:
- The psychology behind burnout and why it's so prevalent in today's fast-paced world.
- Practical techniques to recognize burnout early and take proactive steps toward recovery.
- How to create a healthier work-life balance and prioritize self-care without compromising success.
- Strategies for managers to build supportive, resilient teams and foster a positive work environment.
Through real-life anecdotes and evidence-based insights, This talk will itemise how individuals and organizations can combat burnout, boost well-being, and achieve sustainable success.
This talk was inspired by Ashley Willis talk on "The thing about burnout" at Google Cloud Next 2022
Level Up Your Presentations with AI! Build Your Own AI Slide Reviewer |Gemini |Build with Google AI
Tired of staring endlessly at your slides, unsure if they're polished and impactful?
This talk introduces you to the Slides Reviewer project, your secret weapon for crafting stellar presentations! It utilizes the power of Generative AI and the lightweight efficiency of Google Gemini to analyze your Google Slides against a customizable set of guidelines.
In this talk, you'll learn:
* The magic of Slides Reviewer: Witness a live demo of this AI-powered tool meticulously reviewing your presentation for clarity, conciseness, and adherence to your chosen criteria.
* Extend to your needs: Learn how to tailor Slides Reviewer with your own specific guidelines to ensure your presentations flawlessly align with your workflow.
* Embrace the future: Gain a glimpse into the exciting potential of AI for streamlining and enhancing your presentations.
Whether you're a seasoned presenter or just getting started, Slides Reviewer is here to elevate your game. Tune in and unlock the power of AI for creating impactful presentations!
Maximizing Your University Journey for a Thriving Tech Career
This session offers a strategic roadmap for university students aiming to excel in the tech industry. In year one, students establish foundations through introductory courses and extracurricular activities. Year two focuses on specialization, internship preparation, and portfolio development. Year three emphasizes gaining practical experience, refining skills, and seeking mentorship. In year four, students engage in capstone projects, job search, and continued learning. Throughout, networking, personal projects, and career development are key. Attendees will learn to navigate each year effectively, from exploring interests to securing job offers, ensuring they make the most of their university experience and are well-prepared for a successful tech career.
Introducing Google Crowdsource
What is Crowdsource.
Crowdsource is a fun, easy way for you to use your own abilities to contribute to the building blocks of Artificial Intelligence (AI). This helps make the Google products that you love even better for your language, region and culture. Answers from you and millions of others around the world are used in Machine Learning based products, making them work well for the diversity of global population.
Why it matters?
Artificial Intelligence (AI) powers some of the most magical experiences in your favorite apps and products. It helps organize your photos, understand your voice commands, show you the most relevant reviews for products and businesses, and much more!
AI learns these skills by studying vast numbers of examples. The more examples it has for your language, region, or culture, the better it gets for you and everybody in your community.
Mustapha Adekunle
Data Engineer and Advocate. 5X Google Cloud Certified. Google Developer Expert (GCP)
Lagos, Nigeria
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