7 min read
Claude Code's Monitor Tool vs Polling: What Actually Happened
I gave Opus 5.5 a build to watch and a dev server to start, with and without the Monitor tool. It used Monitor inconsistently, and headless runs hid the answer.
Microsoft MVP
Data Platform & Fabric
Michael John Peña
Data & AI Director
Technologist specializing in Microsoft Fabric, Azure data platforms, and cloud architecture. Microsoft MVP and certified trainer helping organizations unlock the power of their data.
10+
Years Experience
MVP
Microsoft MVP
MCT
Certified Trainer
scroll
Expertise
What I Do
Specialized in the Microsoft data ecosystem. From Fabric lakehouses to real-time analytics, I help teams build modern data platforms.
Microsoft Fabric
End-to-end analytics platform expertise including Lakehouses, Data Factory, Real-Time Intelligence, and OneLake architecture.
Azure Data Platform
Designing and implementing enterprise data solutions on Azure including Synapse, Databricks, Data Factory, and Cosmos DB.
AI & Analytics
Integrating AI/ML capabilities with Azure OpenAI, building analytics solutions with Power BI, and implementing MLOps best practices.
Credentials
Microsoft Certifications
Microsoft MVP
- Microsoft Most Valuable Professional (MVP)
Microsoft Certified Trainer
- Microsoft Certified Trainer (MCT)
Expert
- Azure Solutions Architect Expert
- Azure DevOps Engineer Expert
Associate
- Fabric Analytics Engineer
- Fabric Data Engineer
- Azure Data Engineer Associate
- Azure AI Engineer Associate
- Azure Administrator Associate
- Power BI Data Analyst Associate
Tech Stack
Tools I Work With
Microsoft Fabric Platform
Azure Synapse Analytics Analytics
Azure Databricks Data
Azure OpenAI AI
Microsoft Foundry Platform
Claude Anthropic AI
Power BI Analytics
Python Language
Apache Spark Processing
.NET Framework
C# Language
Azure Cosmos DB Database
Azure Kubernetes Infra
Latest Articles
From the Blog
Thoughts on data engineering, Azure, and technology
7 min read
What xhigh Effort Bought Me on Short Tasks: Tokens, Not Answers
ultrathink now runs at xhigh effort in Claude Code. I ran six exact-answer tasks 96 times from low to max: every level got them right; higher just cost more.
6 min read
Auditing 30 of My Posts with claude -p --json-schema
I had Haiku 5.5 audit 30 of my posts twice: once with --json-schema, once asking nicely for JSON. The shape held. The judgement moved, and that's the lesson.
6 min read
I Planted Five Bugs to Test Claude Code's Review Levels
I hid five bugs in a real change and ran /code-review at low, medium, high and xhigh. Medium found all five for 15 cents. Here's what each level adds.
6 min read
Turning a Blog Post into a Deck with Claude Slides
Slides is out of beta. I had Claude Code turn one of my posts into a nine-slide deck, then checked every claim against the source. Here's what held up.
7 min read
I Put a Guard on az in a Claude Code Mod, Then Tried to Get Past It
A Claude Code mod to hold destructive Azure CLI commands passed 12 unit tests and stopped nothing live. Here's why, the fix, and the gap no regex closes.
Get in Touch
Let's Build Something Together
Looking for Fabric expertise or Azure data architecture guidance? I'm available for consulting, training, and speaking engagements.