Grímur Sæmundsson
Data and AI, Crayon Iceland
Reykjavík, Iceland
Actions
Grímur is an experienced professional in Business Intelligence with about 30 years of experience in Iceland and Norway. He has been working with Power BI since its release, teaching the tool to a significant number of people in Iceland - close to 1% of the country's population.
Currently, Grímur works as the Data and AI Lead at Crayon in Iceland. His background is diverse, with his first university degree being in philosophy and his last job being a fisherman before he moved into the tech field.
Area of Expertise
Topics
Leave the progress reports to the agents
To demonstrate the power of AI agents, we will showcase a compact solution that automatically generates project progress reports in Azure AI Foundry based on data retrieved from Microsoft Fabric .
The solution comprises Fabric data agents and a specialized composition agent working in tandem. We will examine the system architecture and explore each component in detail.
Attendees will gain an appreciation for the power of AI agents and learn how to create their own. The goal is to inspire new ideas about applying these concepts to design custom solutions that leverage AI and agents for data retrieval, interpretation, and presentation.
Fabric and Azure AI Foundry playing nicely together
In this presentation, we will dive into a solution developed for supervisors at a municipality when they are about to conduct an employee assessment. We combine the power of Fabric and OpenAI to streamline and enhance the assessment process.
It is common for supervisors to spend a lot of time gathering quantitative information before the assessment and then analyzing and interpreting the data. We will explore a solution that uses the data processing power of Fabric and the analytical and interpretative capabilities of large language models to conduct a fair and accurate assessment and provide comprehensive and insightful feedback.
We will employ techniques like RAG (Retrieval Augmented Generation) to store guidelines for the supervisors, and we will use Notebooks and Python in Fabric with tools such as Semantic Link to retrieve data from semantic models (Power BI) and PySpark to retrieve data from Lakehouse. We will send the data to an LLM with an appropriate prompt to generate a document that guides us through the assessment.
Real-Time Data Processing in Fabric: Tracking a Cycle Ride
We delve into the power of Microsoft Fabric for real-time data processing. Using data generated from a sports watch during a real cycle ride, we will simulate the ride and set up a live dashboard that dynamically visualizes the journey while leveraging KQL, Eventhouse, and Eventstream for analysis and insights.
You’ll discover how to leverage Microsoft Fabric to:
Process real-time GPS data streams and visualize the rider’s location on an interactive map.
Use KQL’s geographical functions to calculate distances to key points of interest, such as the nearest booze shop.
Dynamically identify postcodes and other geographical metadata based on the current location.
Gain insights into integrating spatial analytics into your real-time applications in Fabric.
This hands-on session will demonstrate the complete workflow, from ingesting streaming data into Fabric, applying transformations and spatial functions, to creating real-time dashboards.
European Microsoft Fabric Community Conference 2025 Sessionize Event
Data Saturday Oslo 2025 Sessionize Event
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