Tool Use Patterns for AI Agents: Effective Function Design
The most consequential design decision in a function-calling agent isn't the model you choose — it's how you write the tool definitions. The model selects…
Thoughts on data engineering, cloud architecture, and technology. 2205 articles and counting.
Showing 24 of 2205 posts — page 47 of 92
The most consequential design decision in a function-calling agent isn't the model you choose — it's how you write the tool definitions. The model selects…
Function calling, released last week with the 0613 model versions, gives AI agents a proper foundation — and I've been rebuilding some agent prototypes to…
Function calling patterns enable sophisticated AI agents. Tomorrow, I will cover building AI agents in more depth.
RLS provides essential data security for multi-tenant and sensitive data scenarios. Tomorrow, I will cover Azure OpenAI function calling patterns.
Item permissions provide the flexibility to share specific artifacts securely. Tomorrow, I will cover Row-Level Security in Fabric.
Proper role management is essential for secure and efficient collaboration. Tomorrow, I will cover Item Permissions in more detail.
Security is an ongoing responsibility. Tomorrow, I will cover Workspace Roles in more detail.
Fabric's capacity unit (CU) model is genuinely different from the per-resource billing in Synapse Analytics, and understanding it properly is the difference…
One of my first questions when evaluating any data platform for enterprise use is "how do I see what's actually running?" — and in the early Fabric…
Deployment Pipelines provide controlled, auditable content promotion across environments. Tomorrow, I will cover Fabric Monitoring.
Git integration in Fabric is something I've been waiting for since the first preview. Power BI's lack of proper version control has been a persistent…
Mirroring simplifies real-time data replication to Fabric. Tomorrow, I will cover Git integration in Fabric.
Dataflows Gen2 provide an accessible way to build data transformations. Tomorrow, I will cover Mirroring in Fabric.
Fabric Pipelines enable robust data orchestration with full control flow capabilities. Tomorrow, I will cover Dataflows Gen2.
Notebooks are the primary development environment in Fabric. Tomorrow, I will cover Fabric Pipelines for orchestration.
Semantic models provide the business logic layer that enables self-service analytics. Tomorrow, I will cover Fabric Notebooks.
Direct Lake is the quiet superpower of Microsoft Fabric, and I think it's underexplained in most of the post-Build coverage. The classic Power BI trade-off…
Of everything announced at Build 2023, OneLake shortcuts might be the feature I find most architecturally elegant. A shortcut is not a copy, not a linked…
Delta Lake isn't a bolt-on feature in Microsoft Fabric — it's the foundational table format for everything. Every table you write through a Spark notebook…
A week after Build 2023, I'm still unpacking what Microsoft Fabric actually means for how we design data platforms. The Lakehouse is the centrepiece — but…
Build 2023 had two dominant themes: 1. AI Everywhere : Generative AI integrated into every product and platform 2. Platform Unification : Simplifying…
Dapr simplifies building distributed applications by providing standardized building blocks. Tomorrow, I will conclude the May series with a summary.
Jobs in Container Apps provide flexible batch processing capabilities. Tomorrow, I will cover Dapr 1.11 updates.
Container Apps provides a powerful, serverless container platform. Tomorrow, I will cover Jobs in Container Apps in more detail.