8 min read
AI Product Lessons: Users Want Augmentation, Not Automation
What building AI features for six products taught me: users want their existing tasks done faster, visible uncertainty and easy overrides, not chat.
Blog
Thoughts on data engineering, cloud architecture, and technology. 2205 articles and counting.
Showing 24 of 2205 posts — page 7 of 92
5 min read
The Five-Minute Father: Phone Down When My Kids Talk
Andriel showed me a Pokémon drawing and I answered without looking up. The one rule I set afterwards: when my kids talk, the phone goes down.
9 min read
Synapse to Fabric Migration: 5 Things I Wish I'd Known
Our Synapse to Fabric migration took twice as long as planned. Five lessons on scope, notebook refactoring, Direct Lake, capacity monitoring and training.
7 min read
Boring Code on Purpose: Writing Software I Can Maintain at 2 AM
Why I now prefer explicit, predictable code over clever one-liners, the four questions I ask before merging, and when terse code is the better choice.
8 min read
Testing AI Systems: Which Tests Run Where, and Why
A layered test strategy for LLM apps: stubbed unit tests per commit, pass-rate gates on PRs, nightly evaluator runs and red teaming before release.
8 min read
From F64 to F32: Three Fabric Sizing Mistakes and the Fixes
Why we moved Microsoft Fabric from F64 to F32: the three sizing mistakes, the monitoring and alerts we added, and when going smaller is the wrong call.
8 min read
What Makes Technical Writing Actually Useful
Most technical posts fail readers with a job to do; here is a five-part template, the gotchas worth including, and when not to use it.
8 min read
Cost Per Query: Measure the Unit Cost Before You Cut It
Treat cost per query as the unit metric for an LLM app: decompose it from the usage object, then cut it in order with model choice, caching, context and batch.
4 min read
Autism Meltdowns: What Doesn't Help, What Does, and Prevention
What our family has learned about our son's autism meltdowns: what makes them worse, what helps, how we prevent some, and why it isn't bad parenting.
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.
8 min read
The Myth of Continuous Learning: Depth Beats Keeping Up
Trying to learn every new framework and model leads to fatigue, not growth. Why depth, deliberate rest and relevance beat keeping up.
9 min read
Databricks or Fabric in 2026: Choosing Your Primary Platform
A practical decision guide for picking Azure Databricks or Microsoft Fabric as your primary data platform in 2026, and when running both is worth the cost.
8 min read
Semantic Kernel Agents in Production: What's Stable, What Isn't
Running Semantic Kernel agents in production in early 2026: which APIs are GA, which are preview, how to guard tool calls, and where Agent Framework fits.
7 min read
The Weekend I Stopped Answering Slack
How I went from working every weekend to zero weekend work: the setup, the team pushback, what changed after eight weeks, and the exceptions I still allow.
9 min read
Six Vector Stores for RAG and Where Each One Hurts
Azure AI Search, DocumentDB, Cosmos DB for NoSQL, pgvector, Pinecone and Redis each fail differently in RAG. Where each one hurts in January 2026.
8 min read
Why I Still Blog in 2026: Owning the Place I Think Out Loud
Why I still keep a blog when everyone posts on LinkedIn and X: ownership, clearer thinking, and a searchable record of my work.
7 min read
Eight Prompt Engineering Myths to Drop in 2026
Eight prompt engineering myths worth dropping in 2026, from verbose prompts to reflexive chain-of-thought and temperature rules, and what to measure instead.
8 min read
What My Son's Autism Taught Me About Predictable Systems
Andriel needs routine, not just likes it. Living with that has changed how I design functions, error messages, API deprecations and change for my teams.
9 min read
Seven RAG Failure Modes and the Pattern That Fixes Each
Diagnose why a RAG system fails before adding patterns: hybrid search, semantic reranking, grounding gates and citations on Azure AI Search, mapped to failures.
7 min read
The Tech Parent's Dilemma: Home All Day, Present for None of It
My seven-year-old asked why I'm always on my computer. How remote tech work erased my boundaries, and the rules I'm putting back in place.
9 min read
Microsoft Fabric Reality Check: What Holds Up and What Hurts
An honest look at running Microsoft Fabric on an F64: what OneLake and Direct Lake deliver, how throttling really works, and what the bill looks like.
8 min read
Azure OpenAI Hidden Costs: What Your Token Estimate Misses
Re-sent history, hidden reasoning tokens, billed failures, idle fine-tuned deployments and re-embedding: where Azure OpenAI bills drift from the estimate.
6 min read
Explaining ChatGPT to My Sons: Very Good Guessing, Not Thinking
How I explained ChatGPT to my sons, aged seven and 10: autocomplete, educated guessing, and why sounding confident is not the same as being right.
9 min read
AI Agents in 2026: Where They Earn Their Keep and Where They Don't
A practitioner's reality check on AI agents going into 2026: the use cases that work, where they break, and how to pick a framework without the hype.