Building AI Agents in Google Cloud: Beyond Chatbots

As AI evolves toward agent-based solutions, the role of AI Agents is becoming increasingly crucial in creating seamless, interactive, and adaptable systems. This talk dives into what AI Agents are, why they’re essential in today’s digital landscape, and how the shift toward agents is shaping the future of AI. We’ll explore the diverse pathways for building intelligent agents in Google Cloud, from the built-in tools like Dialogflow, Vertex AI Agent Builder to open-source frameworks such as LangGraph.

Through a practical case study, I’ll demonstrate how we build a retail natural language to SQL agent using LangGraph, showcasing the journey from development to serverless deployment on Google Cloud. Attendees will gain insights into the foundational concepts of AI Agents, practical approaches to agent building, and how to leverage Google Cloud’s resources to power agent-based applications.

This session is suitable for cloud architects and developers interested in advancing their understanding of AI agents and serverless solutions on Google Cloud. Prior experience with Google Cloud services like BigQuery, Vertex AI, or Cloud Run is beneficial but not required. Session duration is ideally 30-45 minutes to cover technical depth and live demos.
Previous presentations include Google Cloud Nordics Summit, DevFest 2023, Google Cloud Next 2024, and Öredev (Not on same topic).

Retail Beyond Borders, One Data Platform: BigQuery & Analytics Hub in Action Across Countries

This session dives deep into a real-world retail success story, showcasing how a leading retail brand in Nordics unified its data landscape across multiple Nordic and Baltic countries. Facing the challenge of fragmented data silos and complex cross-border data sharing, the company leveraged the power of Google Cloud's BigQuery and Analytics Hub to build a centralized, scalable, and cost-effective data platform.
We'll explore how they:

Conquered data fragmentation: Consolidated disparate data sources from various countries into a single source of truth in BigQuery, enabling comprehensive analysis and reporting.

Streamlined data sharing: Utilized Analytics Hub to securely share and access data across different departments and external partners, fostering collaboration and data democratization.

Optimized ownership and cost: Implemented Analytics Hub's granular data sharing capabilities to clearly define data ownership and allocate costs effectively, ensuring transparency and accountability.

Modern data transformation: Leveraged Dataform, a powerful alternative to DBT, for efficient and collaborative data modeling and pipeline orchestration.

Automated deployments: Built a robust DevOps and CI/CD pipeline using Workload Identity Federation, GitHub, and Terraform Cloud, enabling rapid and reliable deployments.

This session is suitable for cloud architects, data engineers, and developers interested in advancing their understanding of AI agents and serverless solutions on Google Cloud. Prior experience with Google Cloud services like BigQuery, Vertex AI is beneficial but not required.
Session duration is ideally 30–45 minutes to cover technical depth and live demos.
Previous presentations include Google Cloud Nordics Summit, DevFest 2023, Google Cloud Next 2024, and Öredev.

Accelerate AI with Serverless: Deploying Scalable AI Applications on Google Cloud Run

This talk dives into the power of serverless technologies on Google Cloud, with a focus on using Cloud Run to efficiently build and deploy AI applications. As a fully managed, auto-scaling container service, Cloud Run eliminates the need for infrastructure management and adapts to the dynamic, often unpredictable demands of AI workloads. Attendees will learn how Cloud Run’s serverless architecture is particularly suited to AI, offering a cost-effective, pay-per-use model that scales based on demand.

Through engaging demos, this session showcases the versatility and ease of using Cloud Run for AI:

Gemini-powered Chat Application
Asynchronous AI with Cloud Run Jobs for batch processing
Function Calling with LLMs

Attendees will leave with insights into the benefits of Cloud Run for scalable AI deployment, tips for leveraging Google Cloud’s client libraries and buildpacks, and practical steps for integrating Cloud Run into their AI projects.

From Idea to Impact: How Serverless is Serving Retail at Scale

As a Cloud Solution Architect, I’ve helped retail customers reimagine their infrastructure, shifting from rigid, cost-heavy architectures to fully serverless models powered by Cloud Run (compute) and BigQuery (data analytics). The impact? Faster go-to-market, seamless scalability, and real-time data-driven decisions without the operational burden.

In this talk, I’ll share how we built a serverless retail intelligence platform, enabling:
• Lightning-fast product analytics with BigQuery, helping stores track sales trends instantly.
• AI-powered demand forecasting running on serverless functions, reducing stockouts and improving shelf availability.
• Edge-to-cloud data pipelines using Cloud Run and Pub/Sub, seamlessly ingesting IoT and transaction data from thousands of retail stores.

But beyond the tech, the real story is about business agility—how serverless helped retailers shift from monolithic struggles to nimble, data-driven decisions, serving customers with exactly what they need, when they need it.

Join me as we explore why serverless isn’t just about cost savings—it’s about transformation, innovation, and making the impossible happen, at scale.

Structured Data from Images: Deploy a Gemini-Powered OCR App on Cloud Run

Want to turn images into valuable data? This workshop guides you through building a multimodal OCR processor using Gemini. You'll learn to:

Extract text and structured data from images with Gemini.
Develop an interactive frontend with Streamlit/Mesop.
Define structured output with Pydantic.
Deploy your app on Cloud Run and store data in BigQuery. Gain practical skills in building and deploying AI-powered data applications.

This workshop empowers you to build a practical, AI-driven OCR application using Gemini. Learn to extract text and structured data from images, create an interactive frontend, define structured outputs, and deploy your application on Cloud Run while storing data in BigQuery. Gain hands-on experience in developing and deploying multimodal AI solutions for real-world data extraction.