Blog

Field notes from the frontier.

Short essays on AI product management, program leadership, and the craft of building digital products that people actually trust.

July 24, 20265 min read

The acceptance criteria didn't disappear. They became evals.

Gartner says over 40% of agentic AI projects will be canceled by 2027. Most of them will fail for the same boring reason: nobody wrote a testable definition of done.

AIProductEvals

July 24, 20265 min read

RolesRadar: how I built an AI job search agent on n8n

RolesRadar is an AI job search automation I built on n8n. It reads my resume, scans live listings daily, and ranks the best-fit product and AI roles for me.

AI Automationn8nProductJob Search

July 10, 20266 min read

From prompts to products: turning GenAI experiments into shipped features

Notes on moving beyond demos, choosing evaluation metrics that matter, and building the operational muscle to ship AI features safely.

AIProductGenAI

June 18, 20265 min read

Program management for AI teams: cadence, clarity, and controlled chaos

How I run programs where research, engineering, and product move at different speeds without losing the plot.

Program ManagementAIOperations

May 2, 20264 min read

Designing for trust in AI products

Confidence, provenance, and the small UX choices that make users trust — or quietly abandon — an AI feature.

DesignAIUX