People in the Loop

Diary of an AI Practitioner

A working diary from inside real AI rollouts. What we build, what it costs, and what we would do differently. No client names.

Human in the Loop, On the Loop, or Out of the Loop: Which One Each of Your Workflows Needs

Human in the loop means a person approves every output. On the loop means it runs and a person watches. Out of the loop means it runs unattended. Most businesses use one setting for everything. Here is how to decide per workflow.

The Real Microsoft Copilot Adoption Numbers, 2026

Not a vague sense that adoption is stalling. The actual 2026 numbers, so you know if your team's experience is normal, and what it's really costing you.

Netlify Just Rebuilt Itself Around Agents. Here's What That Actually Means.

Netlify shipped a major update built around AI agents: Functions redesigned for Agent Experience, an open benchmark called AXIS, and Claude Opus 4.8 live in its AI Gateway. Here's what it means if you're building with Claude.

How I Actually Think: Voice Notes, Brain Dumps, and Coming Back to Refine

My process is audio first, not outline first, and forcing myself into the standard advice would have broken the way I actually work.

You Can't Micromanage Claude, or You'll Never Succeed

Most people fail with Claude because they treat it like a vending machine for tiny tasks instead of giving it a real goal and letting it work.

You're Doing Claude Wrong (No One Else Is Going to Tell You)

The same mistake keeps showing up in room after room: something pretty that solves today's problem and nothing built to hold up past it.

You're Not Orchestrating AI Agents, You're the Executive

The real unlock in agent orchestration isn't directing every agent's every move, it's delegating the orchestration itself and reviewing outcomes like an executive.

Claude Team vs Enterprise, for a 15-person team

Most teams under 20 to 30 people don't need Enterprise. The real difference isn't the price, it's what happens to your data and who controls it. Here's how to actually decide.

Human-in-the-Loop (HITL): Building the Workforce of the Future

Human-in-the-loop means AI systems always include checkpoints where people validate, adjust, or decide. Here's why that matters for governance, trust, and the jobs of the future.

AI Governance: Building Trust in Healthcare, Finance, and Beyond

AI governance is a framework of policies, oversight, and practices that ensure AI is ethical, compliant, and trustworthy. Learn how to build trust in regulated industries.

AI Transformation Strategy: From Experimentation to Enterprise Scale

Moving from pilots and experiments to enterprise-wide AI adoption with measurable outcomes. Strategy, governance, HITL, and change management.

Answer Engine Optimization (AEO): Winning Visibility in the Age of AI

AEO is about structuring your content so AI tools like Google AI, Alexa, and Copilot can find, understand, and cite you as the trusted answer.

— 12 entries —