Browse All Machine Learning Content (188)

Microsoft Developer explains why an AI agent’s output quality depends on the context you can retrieve at runtime, and shows how Foundry IQ-style capabilities connect agents to enterprise data, ground responses, and enable actions across business workflows.

Samu Niemelä shares practical takeaways from FabCon 2026 on how Microsoft Fabric is maturing, from Fabric IQ grounding Copilot and agents in governed business semantics to new on-demand compute and stronger monitoring and governance features for running Fabric at scale.

NehaNellepalli outlines an architecture for building a reusable analytics layer around Odoo without modifying the ERP, using Azure Data Factory ingestion into ADLS Gen2, Databricks/Spark transformations, and Synapse/SQL modeling for governed Power BI reporting with row-level security.

This week's ML roundup centers on a practical shift toward governed, inspectable AI systems where semantics, permissions, and operational telemetry live close to the data. Microsoft Fabric doubled down on being the context and governance layer for Copilot and custom agents (via Fabric IQ, ontologies, OneLake controls, and scale tooling), while Azure SQL brought DiskANN-based vector indexing to GA to simplify retrieval next to transactional data. On the model side, Azure AI Foundry Model Router put measurable economics (quality, cost, latency) into routing decisions, and Azure Databricks highlighted unified pipelines, SQL-first AI decision patterns, and cost visibility. We also saw science-focused agent work (Microsoft Discovery and Research Quine) that treats reproducibility, tool traceability, and validation checkpoints as non-negotiable design requirements.

John Savill recaps major Microsoft AI announcements from September 2026, focusing on Azure AI Foundry updates (models, routing, agent features, and controls), Copilot platform changes, and developer-facing items like GitHub Copilot and VS Code agent workflows, plus data/AI additions such as Azure SQL vector capabilities.

Microsoft Developer explains how to evaluate Azure AI Foundry Model Router against a baseline model (for example GPT-5) to understand cost, latency, and quality trade-offs, using the open-source Model Router Auto Evaluation toolkit and its HTML dashboard output.

Microsoft Developer hosts a Data Exposed episode with the Azure SQL product management and engineering team, explaining how Azure SQL Database Hyperscale implements vector indexing (DiskANN) to support fast approximate vector search, filtering, and DML at scale, including billion-row scenarios and GA availability.

rickliev outlines Microsoft’s message for TM Forum Innovate Americas 2026: scaling agentic AI in telecom depends on trusted, governed data plus shared operational context. The post connects “agent-ready” data concepts (meaning, provenance, permissions) with Microsoft Fabric capabilities like OneLake, Fabric IQ, and Real-Time Intelligence.

Wiliam_Rosa breaks down Lakeflow in Azure Databricks, explaining how it unifies ingestion, transformation, and orchestration, and why Unity Catalog-based governance and lineage can reduce the “glue work” of multi-tool data engineering stacks.

Christine Caggiano explains how a multidisciplinary team used the Microsoft Discovery app to design an inspectable, reproducible bioinformatics workflow for phage therapy—connecting curated literature, genomic analysis, and external tools via MCP-based adapters, with validation steps and safety checks built into each stage.

sbaynes describes how the Microsoft Discovery app can help scientists and data teams design an inspectable, reproducible bioinformatics workflow for phage therapy research, from profiling antibiotic resistance and bacterial defenses to searching environmental metagenomic data and ranking candidate phages with traceable evidence and validation steps.

varghesejoji introduces a local “Assessment & Optimization Workbench” that pulls together Azure billing and Databricks workspace evidence so teams can review Databricks cost drivers, utilization, job health, and selected posture checks. It walks through the UI workflow (configure, validate, run, visualize, export) and how to build and run it locally.

Wiliam Rosa explains how to use Azure Databricks ai_query to run a “decision model” (closed-set classification with probabilities) directly from SQL against Unity Catalog-governed tables, avoiding chat-style outputs and extra orchestration. The post covers required warehouse/runtime constraints, structured return types, hosting options, and governance caveats in Unity Gateway.

sbaynes introduces Quine, a Microsoft Research system that combines a multimodal “world model” of biology with an interactive harness that connects models, scientific tools, literature, and wet-lab workflows to speed up biological discovery and hypothesis testing.

bogdanc summarizes the Fabric Analytics announcements from FabCon Europe 2026, covering Fabric IQ’s GA in Copilot experiences, new Power BI app-building capabilities, GPU-accelerated query execution for Fabric Data Warehouse, and expanded governance controls (labels, DLP, and Copilot restrictions) across the Fabric stack.

Arun Ulag summarizes the FabCon and SQLCon Barcelona 2026 announcements across Microsoft Fabric and Azure SQL, focusing on how Fabric IQ, OneLake, and new agent experiences aim to provide governed business context for Copilot, analytics, and data/AI applications, plus new observability and database management capabilities.

yitzhak outlines how Microsoft Fabric is positioning Real-Time Intelligence and Fabric IQ as the “live” data and semantic foundation for trusted AI in enterprises, then walks through new preview features like Observability Insights, Operations Agent/Investigator, Eventstreams improvements, ontology tooling, and governance capabilities.

shireesht summarizes FabCon EU and SQLCon 2026 announcements across Microsoft Fabric and Microsoft SQL, including Fabric Apps for building governed data-backed apps, Database Hub for centralized estate management, and preview “database agents” plus Azure SQL updates like DiskANN vector indexing for RAG scenarios.

diptiborkar announces new Planning capabilities in Microsoft Fabric IQ, focused on building budgets and forecasts directly on governed Fabric data and Power BI semantic models. The post covers tighter Fabric IQ integration, a new native planning engine, event-driven automation, embedding planning into org apps, and governance/billing controls.

Faisal Mohamood and Bogdan Crivat outline a guided modernization path from Azure Data Factory and Azure Synapse Analytics to Microsoft Fabric, covering the new “view in Fabric” upgrade experience, migration assessment and incremental upgrades, and migration assistants for Spark and dedicated SQL pools into Fabric Data Engineering and Fabric Data Warehouse.

Dipti Borkar summarizes the FabCon and SQLCon Barcelona 2026 announcements for Microsoft OneLake, covering new ways to share governed context (IQ sharing), connect external platforms via shortcuts and mirroring, use Table APIs for Iceberg/Delta access, and strengthen governance with catalog, policies, and OneLake security.

sapatney announces major updates to Fabric Apps and the Rayfin framework, adding first-class backend capabilities (functions, storage, and databases), new Fabric data connectors (including semantic models with DAX), built-in app metrics, and a clearer enterprise access model based on Entra authentication and delegated identity.

Faisal Mohamood summarizes the FabCon/SQLCon Barcelona 2026 announcements for Fabric Data Factory, covering new mirroring sources, multicloud data distribution improvements, faster and more reusable transformations (Power Query, Dataflow Gen2, notebooks, dbt), richer monitoring, and MCP-based AI assistance across authoring and operations.

kimani announces a set of Microsoft Fabric platform updates aimed at running Fabric estates at scale, covering new observability and monitoring experiences, repeatable delivery features (deployment plans, bulk definition APIs, Git enhancements), OneLake catalog discovery (including Copilot CLI), capacity controls and billing options, and expanded governance and security controls.

murray-kp rounds up the September 2026 Microsoft Fabric release, covering major updates across governance, CI/CD and Git integration, OneLake catalog and APIs, data engineering and Spark runtime improvements, warehouse features, real-time intelligence (Eventstream/Eventhouse/Activator), and Fabric IQ/MCP capabilities for agent-driven workflows.

This week in ML, the focus shifted toward running agent workflows closer to the data tier, with SQL-driven agentic RAG and chat completion patterns that bring prompts, tool calls, and logging under existing database security and auditing. We also saw practical guidance on agent isolation and durable memory using Azure AI Foundry with Azure Blob Storage, plus production-oriented debugging considerations when agents run as long-lived services. On the applied side, Microsoft Discovery highlighted a human-in-the-loop, multi-agent approach to wastewater metagenomics that keeps reproducibility and reviewability central. Rounding out the week, platform updates covered the operational plumbing that hybrid analytics and agent-backed pipelines depend on, including gateway improvements and expanded observability for Oracle AI Database@Azure.

Microsoft Developer shares a weekly developer-news roundup covering .NET memory dumps for diagnosing failures, the pitfalls of migrating time-related data between PostgreSQL and SQL Server, and how AI agents can use stronger isolation plus durable memory with Microsoft Foundry and Azure Blob Storage.

goupadhy announces the September 2026 on-premises data gateway release (v3000.334), highlighting a new Soft Delete recovery window, security dependency updates (including Log4j 2.26.1 and a fix for CVE-2026-18401), and compatibility alignment with the September 2026 Power BI Desktop query runtime.

RajyaLaxmiYellajosyula explains how Oracle GoldenGate is now managed as a native Azure experience within Oracle AI Database@Azure, including Azure portal/API lifecycle operations, Azure control-plane governance (RBAC, tags, Activity Log), and generally available observability via Azure Monitor metrics and Azure Log Analytics events.

Bob Ward explains how Microsoft SQL (SQL Server, Azure SQL, and SQL DB in Fabric) can be used for chat completion and agentic RAG scenarios, including making REST calls to models, building prompts in SQL, and adding security controls like immutable logging, content moderation, and prompt-injection protection.

Simon Frost explains how the Microsoft Discovery app and Premonition Insights on Azure can speed up exploratory analysis of wastewater metagenomics, while keeping human scientific judgment in control. The post walks through an end-to-end workflow: literature grounding, taxonomic filtering, weather-data enrichment, phylogenetic verification, and interactive dashboards.

Simon Frost explains how he used the Microsoft Discovery app to speed up exploratory analysis of a large wastewater metagenomics dataset, while keeping human scientific judgment in the loop. The post walks through agent-assisted data wrangling, API enrichment, phylogenetics, and visualization to produce auditable, reproducible findings.

This week's ML roundup focuses on how data agents are getting closer to production standards, from Fabric IQ and MCP-grounded Copilot Studio experiences to Databricks Genie evaluations that run as a continuous quality loop. On the platform side, Fabric shipped updates that reduce migration risk (BigQuery mirroring GA and an ODBC inventory tool for the ADBC cutover) and improve day-2 operations with bounded, read-only natural-language diagnostics for Fabric Data Warehouse. We also look at Azure's MLPerf Inference v6.1 results for DeepSeek-R1 on NVIDIA GB200 and GB300 systems, plus smaller governance and integration updates across Databricks and Fabric.

Wiliam_Rosa explains why Azure Databricks Genie Agents need the same ongoing evaluation discipline as production ML models, and walks through Genie Agent Benchmarks, including SQL-based “Chat mode” scoring, LLM-judged “Agent mode”, and a practical workflow for monitoring and improving agent accuracy over time.

Sayanika walks through building a conversational analytics agent that queries data in OneLake using Microsoft Fabric semantic models and Fabric IQ Ontology, with a Copilot Studio setup that normalizes messy location inputs (e.g., abbreviations and misspellings) before running ontology-backed queries.

goupadhy announces a preview soft-delete lifecycle for standard-mode on-premises data gateways in Microsoft Fabric, letting tenant and gateway admins restore deleted gateway clusters and members within a 30-day retention window instead of having to recreate them after accidental deletion.

Michaela Isaacs announces general availability of Mirroring for Google BigQuery in Microsoft Fabric, positioning it as a supported way to bring BigQuery data into Fabric for broader analytics work without building or maintaining ingestion pipelines.

Microsoft Developer introduces Rayfin, an open-source SDK and CLI for defining and deploying application backends to Microsoft Fabric as first-class Fabric items, highlighting how Fabric identity, governance, and compliance carry through to the deployed app and why Fabric’s SQL database option matters.

Sayanika outlines an architecture pattern for a retail “growth intelligence” agent that uses Azure AI Foundry (Foundry IQ) to orchestrate reasoning across Microsoft Fabric (Fabric IQ + ontology), Dynamics 365 Finance & Operations via an ERP MCP server, SharePoint policy documents, and web intelligence, backed by Azure AI Search.

Wiliam Rosa explains Azure Databricks’ new (beta) configurable retention for supported system tables, including the 30–3,650 day range, the default behavior when enabled, and how to set the st_retention value via the Databricks Account Settings API for governance and long-term auditing needs.