Tagged: AI Agents
24 posts · All tags
-
Fabric Is Best as a Backend
October 5, 2026
Fabric as a Backend passes Steve Jobs' iPad test on the wiring: workspace identity, Git, and 700+ REST APIs Microsoft is building for agents.
Read More → -
Same Prompt, Two Reports: Give Desktop Bridge a Spec Before It Builds
October 2, 2026
Give Desktop Bridge the same prompt twice and you get two different reports. The three report skills and a real kickoff page are how you get the same one.
Read More → -
Agentic Distributed Wisdom: Why Your Team's AI Skills Can't Live in One Head
September 30, 2026
Your team's AI skills are agentic IP. Agentic distributed wisdom puts that judgment in one library every person and every agent on the team reads.
Read More → -
The Context Harness and the Execution Harness: Two Harnesses, One Loop
September 25, 2026
The context harness holds what your agent knows. The execution harness does the work. Why 80% of my agentic time goes into the first one.
Read More → -
A Data Agent Should Be a Sub-Agent
September 23, 2026
A Fabric data agent works best as a sub-agent with one job that Copilot, Foundry, or Copilot Studio calls. Here's how I write those instructions.
Read More → -
A skill.md Is Not Wisdom. So Make the Agent Grill You.
September 21, 2026
Your skill file carries instructions, never the judgment that says this is six hours not two. Matt Pocock's grill-me is how I get the judgment back in.
Read More → -
Build the Thing That Creates the Thing
September 16, 2026
Stop prompting for the same notebook edit. Build the executor: an agent, its skills, and the context it reads, in a harness that reaches Fabric and Power BI.
Read More → -
Don't Hire a Senior to QA the Agent
September 14, 2026
Hand agents to people who can't interrogate the output and you haven't scaled your team. You've built a review queue and staffed it with your architect.
Read More → -
You Don't Have an AI Strategy. You Have AI Theater.
September 9, 2026
The intake test I run on every new skill, MCP server, and harness before it touches client work.
Read More → -
Governance Pillars 3 and 4: Write the Contract Before You Hire the Watchdog
September 2, 2026
Accountability and culture are where governance gets hard. The data contract that gives an agent something real to enforce, plus a 30-day plan.
Read More → -
The Four Pillars of Data Governance (and the Agent That Reports to Each) - Part 1
August 31, 2026
Enablement and promotion are the first two governance pillars. What actually lives in each, what doesn't, and the agent job to hire under both.
Read More → -
Agents Raise the Floor and Lower the Ceiling
August 28, 2026
Hand a DAX agent to someone who never learned filter context and you make them productive while capping how far they can go. Prove the fundamentals first.
Read More → -
Hard Data, Soft Data: The Layer Your AI Agent Is Missing
August 26, 2026
Your semantic model is only half your data. Why soft data, the decision logs and business context behind your tables, decides if AI agents work.
Read More → -
AI Made Your Center of Excellence Bigger. Did It Get Better?
August 24, 2026
AI can flood your Power BI Center of Excellence with content overnight. Here's the maturity ladder for making it measurably better, not just bigger.
Read More → -
Fabric Task Flow Studio: From One Sentence to a Deployed Fabric Architecture
August 21, 2026
A tour of Fabric Task Flow Studio: describe a Fabric problem in plain language, approve once, and get a deployed architecture with the docs to prove it.
Read More → -
Design the Report From the Meeting You Already Had
August 19, 2026
Agents can design Power BI reports now. What makes them good is a locked brief from your stakeholder meeting, plus commands and the Desktop Bridge loop.
Read More → -
Don't Let Your Agent Touch Fabric Until It Reports Back
August 17, 2026
An agent's bad PySpark doesn't get a red squiggly line. It gets you data. The read-only survey I open every Fabric MCP session with, and the asserts that gate everything after.
Read More → -
You're AI Ready. Your Organization Isn't.
August 12, 2026
Nobody has defined what AI ready means for an organization. The roles and delivery gaps behind slow AI adoption, plus a 30-60-90 that starts with data quality.
Read More → -
From Notion Page to Power BI Model: Inside an MCP Execution Session
August 5, 2026
What a real Claude instructions page contains and how one line kicks off semantic model work over the Power BI Modeling MCP, kickoff to write-back.
Read More → -
Meet My Assistants: The Three Agents That Keep My Projects Honest
August 3, 2026
Part 3 of Stop Re-Prompting: the Notion assistants that organize context, drive requirements, and draft status updates for my Fabric projects.
Read More → -
Anatomy of a Project Hub: Where Your Agent's Context Actually Lives
July 29, 2026
A tour of the project hub that feeds my AI agents context, so every session starts informed instead of from zero.
Read More → -
Agent Skills Are the New Theme Files
July 23, 2026
What BI teams learned governing theme files and PBITs is the playbook for agent skills. One rule sorts what gets governed from what stays personal.
Read More → -
Stop Re-Prompting: Your Second Brain Should Write Your Agent's Instructions
July 20, 2026
Stop re-prompting your AI agent. Build a two-harness workflow where your second brain writes the agent's instructions and MCP executes in Power BI and Fabric.
Read More → -
Should an AI Agent Sit on Your Data Governance Committee?
July 16, 2026
AI agents won't lead your data governance program, but they can own its hardest job: transparency. Where to point them first, plus a 30-day plan.
Read More →