When teams "agentify" an existing process, they hand the agent a workflow designed around human constraints. The agent inherits every stop-and-wait point, every workaround, every approval layer it doesn't need. The fix isn't to optimize the agent. It's to redesign the process.
I started thinking the hard problem was document parsing. Then format design. Then sync logic. The real challenge was building at the interface between two domains that don't talk to each other.
Processing a Word document through raw OOXML costs 359,706 prompt tokens. Clean markdown costs 106. Five design decisions that make that gap useful without losing formatting.
Every AI tool that works with documents treats formatting as disposable. For organizations running hundreds of documents through AI editing pipelines, it's a structural cost nobody is tracking.
Your Capability Map says a workflow is Agent Ready. Now what does the agent optimize for? OKRs were designed for humans. Agent Actionable Objectives are the translation layer that's been missing.
Most AI deployments fail not because the technology doesn't work, but because nobody decided which workflows agents should actually own. The Organizational Capability Map is a framework for making that call.
Klarna's AI agent saved $60M then backfired. The problem wasn't the AI. It was the gap between what agents optimize for and what organizations actually need.
Microsoft announced agents talking to agents at Ignite 2025. What they didn't address: the distributed systems complexity that creates. If you've built microservices architectures, this will feel familiar. If you haven't, you're about to learn some hard lessons.
Microsoft's Agent 365 demos compress 12-18 months of work into 10-minute presentations. The technology is real. The implementation gap is too. Here's what data readiness, integration complexity, and organizational change actually look like for enterprises planning AI agent deployments.
Enterprises are about to repeat every mistake they made during cloud adoption, but with AI agents. Here's what I learned from ten years of Azure migrations about why Shadow IT happens and what Microsoft's Agent 365 actually solves.
I used Claude Code to build a tool that creates Claude Skills. Open-source CLI tools for validating and packaging skills at scale. Built by AI, for AI, used by engineering teams. Includes practical examples for SDLC automation.
Teams hit every metric—green dashboards, perfect scores. But customers were frustrated and critical incidents kept happening. Here's why: people spent more time proving they had impact than actually having it. Measurement systems don't just fail, they twist the work they measure.
Program Management
Most TPM dashboards track the wrong things. Build success rates and sprint velocity tell you nothing about what matters. Every metric should answer one of three questions: Can we ship safely? Are teams fast enough? Will customers succeed? Stop measuring everything. Start measuring what matters.
Leadership
Southwest Airlines lost $825 million in ten days because of a crew scheduling system from the 1990s. Pilots had warned management for years. This wasn't a technical failure—it was a leadership failure. Technical debt isn't a technical problem. It's a business problem disguised as an IT issue.
Architecture
A manufacturer's web store took 12 seconds per order because of synchronous SAP calls. Customers abandoned carts. We fixed this with the strangler pattern - not by making SAP faster, but by stopping the wait for SAP. Real code examples included.
Leadership
A company spent $20M on software that didn't work. They picked tools first, then tried to solve problems. After 20 years at Microsoft, I learned to ask three questions before any tech decision. Start with problems, not solutions.
Architecture
The shift from engineer to architect isn't about learning new tools. It's expanding your scope from local fixes to global impact. Engineers make code work. Architects think about what happens when that code scales, fails, or succeeds beyond expectations.
Kubernetes
Teams pick Kubernetes before they understand their problem. This creates unnecessary complexity. I've seen simple apps that would work perfectly on Azure App Service struggle with container orchestration nightmares. Requirements should drive platform choice, not trends.
Cloud Migration
One bad call killed 2.5M connected cars. 75% of cloud migrations fail because teams assume apps work the same in cloud. They don't. Here are the 10 costliest mistakes and how to dodge them.
LLMs
Learn proven strategies for integrating LLMs with enterprise data systems. Practical insights on architecture patterns, data pipelines, and security from hands-on experience.
LLMs
Teams Copilot struggles with long meetings, 30-day history limits, and inconsistent formatting. Learn how to build a custom Azure solution using durable functions and OpenAI that processes any meeting length with unlimited history and team-specific templates.