9 min read
Foundry Hosted Agents Are GA: When to Stop Running Your Own Containers
Hosted agents in Foundry Agent Service are GA. How they compare with Agent Framework on Container Apps or AKS on identity, networking, cold starts and tracing.
Observability
47 articles
8 min read
Harness Agent or Plain Agent? What Agent Framework Now Decides for You
The Agent Framework Harness bundles planning, memory, compaction, approvals and telemetry. When to accept its opinions and when a plain Agent is better.
7 min read
Write-Audit-Publish in Fabric: Stop Bad Data Before It Ships
Why many data quality root-cause fixes come down to where the check runs, and how to build a write-audit-publish boundary on a Fabric lakehouse.
8 min read
Splitting an AI Journey's Latency Budget Across Its Steps
A journey-level latency budget only works when each step gets a cap, a timeout and a fallback; here is how to split one across a RAG request.
9 min read
Blameless Reviews for Data Incidents: Ask Which Control Failed
How to run blameless reviews for data quality incidents: record who detected it, which control was missing, and turn each review into a tracked change.
7 min read
Failure Budgets for Data Products: SLOs for Fresh, Correct Tables
Measure data product reliability in good hours, catch bad data at the publish boundary, and let a failure budget decide when pipeline changes stop.
7 min read
Pruning Data Quality Checks: Keep, Demote, or Delete
How to cut an inherited data quality rule set down to the checks that change decisions, using failure history, ownership and an explicit retirement path.
7 min read
Noise or a Real Change? Three KQL Checks Before Anyone Gets Paged
Use KQL baselines, week-over-week comparison and diffpatterns in an Eventhouse to tell a meaningful operational change from ordinary noise, and to explain it.
8 min read
Fabric Pipeline Failure Paths: Catch the Error, Then Fail the Run
How dependency conditions decide a Fabric pipeline's final status, why try-catch hides failures, and how to log, alert and still fail the run honestly.
8 min read
Two Tickets per Data Incident: Contain First, Fix the Cause Second
Why every data quality incident should produce two pieces of work, a containment action and a root-cause fix, and how to run both on a Fabric lakehouse.
9 min read
Foundry After the March GA: What's Governed and What's Still Preview
Foundry Agent Service went GA in mid-March 2026, but monitoring and tracing are still preview. What's governed now, and the controls I'd add first.
7 min read
Five Data Quality Signals for the Data-to-AI Handoff
Why I'd track five quality signals per feature table at the data engineering to AI handoff, and how to compute them in a Fabric notebook without a new tool.
8 min read
KQL for SQL People: The Query Language Azure Already Runs On
Why KQL is a baseline Azure skill, how its pipe model differs from SQL, and the operators, join defaults and has-vs-contains traps that matter most.
8 min read
Monitoring AI in Production: Layers, Owners and a Review Rhythm
Run AI monitoring as an operating rhythm: four layers with owners, what pages versus what waits, and tagging every change so regressions are traceable.
8 min read
LLM Observability: The Few Signals That Actually Matter
Which LLM signals deserve a dashboard or a page: tokens by feature, latency split by phase, throttling, and sampled quality, using OpenTelemetry on Azure.
1 min read
Implementing Observability for AI Applications with OpenTelemetry
Observability is essential for AI applications. Without it, you're flying blind on costs, performance, and quality. Implement these patterns early and…
1 min read
Monitoring AI Applications: Observability Patterns for LLM Systems
LLM systems have unique characteristics: non-deterministic outputs, variable latency, complex cost models, and quality metrics that require semantic…
1 min read
Monitoring AI Applications with Azure Monitor and Application Insights
Configure alerts for latency spikes, error rate increases, and token usage anomalies to catch issues before they impact users.
1 min read
Observability for LLM Applications: Tracing, Metrics, and Debugging
Log prompts and responses for failed interactions to a secure store for debugging. Implement sampling for successful calls to control storage costs while…
1 min read
AI Monitoring Dashboards: Visualizing AI System Health
Comprehensive monitoring dashboards enable proactive AI operations management.
1 min read
AI Observability: Monitoring LLM Applications in Production
Comprehensive observability enables continuous improvement of AI applications.
1 min read
Building Custom LLM Observability: DIY Solutions
Building custom observability gives you full control over your data and features. Start simple and add complexity as your needs grow.
1 min read
Phoenix Observability: Local-First LLM Tracing
Phoenix provides powerful local-first observability that keeps your data private while offering the visualization and analysis capabilities needed for…
1 min read
Weights and Biases for LLM Applications: Complete Guide
Weights & Biases provides a comprehensive platform for LLM observability, evaluation, and collaboration. Its strength lies in combining experiment tracking…
1 min read
LangSmith Alternatives: Choosing the Right LLM Observability Platform
The best tool depends on your specific needs. Start with the simplest option that meets your requirements, and upgrade as your needs grow.
1 min read
OpenTelemetry for AI: Standard Observability for LLM Applications
OpenTelemetry provides a standardized way to instrument AI applications, ensuring your observability data is portable across different backends and tools.
1 min read
Tracing Frameworks for AI: Distributed Tracing in LLM Applications
Effective tracing reveals the inner workings of AI applications, helping you understand performance bottlenecks, cost drivers, and error sources across your…
1 min read
Agent Observability: Monitoring AI Systems in Production
Observability transforms AI agents from black boxes into understandable systems. Combine metrics, logs, and traces to gain complete visibility into agent…
1 min read
Audit Logging for AI Agents: Complete Activity Tracking
Comprehensive audit logging is essential for AI agents in production. It enables debugging, ensures compliance, and provides the visibility needed to build…
1 min read
Tracing and Debugging AI Applications
Debugging AI applications is different from traditional software. Today I'm exploring tracing and debugging techniques for production AI systems.
1 min read
Monitoring AI Systems in Production
AI systems require specialized monitoring beyond traditional application metrics. This guide covers comprehensive observability for production AI.
1 min read
Tracing and Debugging LLM Applications
Advanced techniques for tracing and debugging complex LLM applications in production.
1 min read
Fabric Monitoring: Observability for Your Data Platform
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…
1 min read
Observability and Monitoring: Practices That Worked in 2022
Observability in 2022 moved beyond simple monitoring to true understanding of system behavior. OpenTelemetry became the standard for instrumentation. SLOs…
1 min read
Azure Monitor Agent: The Future of Azure Monitoring
Azure Monitor Agent provides a unified, secure, and flexible foundation for all monitoring needs.
1 min read
Azure Managed Grafana Preview: Enterprise Observability
Azure Managed Grafana provides enterprise observability with seamless Azure integration and reduced operational overhead.
1 min read
OpenTelemetry with Azure: Vendor-Neutral Observability
OpenTelemetry provides a future-proof approach to observability. By using vendor-neutral instrumentation with Azure Monitor as the backend, you get the…
1 min read
Azure Monitor Application Insights: Deep Observability for Applications
Application Insights provides the deep observability needed for modern applications. Combined with Azure Monitor's broader capabilities, it enables…
1 min read
Configuring Azure Diagnostic Settings for Comprehensive Logging
Azure resources produce several types of diagnostic data: Platform Metrics : Numerical performance data Resource Logs : Detailed operational logs (formerly…
1 min read
Deep Dive into Azure Monitor Metrics
Azure Monitor collects two types of metrics: Platform Metrics : Automatically collected from Azure resources Custom Metrics : Application specific metrics…
1 min read
Prometheus with Azure Monitor: Unified Observability
Azure Monitor for Prometheus addresses these while maintaining compatibility.
1 min read
Azure Managed Grafana: Visualization for Cloud Observability
Grafana on Azure became substantially easier when Azure Managed Grafana reached general availability. Before that, teams ran Grafana on AKS or a VM, managed…
1 min read
Deep Dive into Application Insights
Application Insights is the monitoring tool that pays you back in proportion to how much you invest in it. Out of the box you get…
1 min read
Mastering Log Analytics Queries with KQL
KQL is the query language I've spent the most hours in this year that most developers have never heard of. If you use Log Analytics, Sentinel, Application…
1 min read
Proactive Monitoring with Azure Monitor Alerts
Azure Monitor supports several alert types: Metric alerts Based on metric values crossing thresholds Log alerts Based on Log Analytics query results…
7 min read
Azure Monitor Workbooks as an Incident Triage Tool, Not a Wallboard
Design an Azure Monitor workbook for incident triage on workspace-based Application Insights, with sampling-safe KQL, drill-down and ARM deployment.
1 min read
Azure Log Analytics: Central Logging Platform
Log Analytics is the database I've spent the most hours in this year that nobody calls a database. It's where every Azure diagnostic, AppInsights trace…