Categories
Most of my articles are about the Astrophotos that I take during my free time. I also write about software architecture and modern application developmentStay Tuned
Want to become a Next.js pro?
The best articles, links and news related to web development delivered once a week to your inbox.Latest Articles
A few handcrafted articles about my thoughts and experiments.
Page 1/12

The AI Platform Team Is an Enablement Layer
How AI platform teams can provide reusable harnesses, evaluation systems, source governance, capability controls, and operational patterns without owning every product decision.- Published on

When Agents Should Refuse to Continue
A practical guide to refusal as an operational state for AI agents when evidence, authority, safety, budget, or task coherence breaks down.- Published on

AI Product Metrics Should Measure Control
Why AI product health should track evidence quality, correction rate, authority use, stop behavior, recovery, and user trust alongside speed and automation.- Published on

Human Handoffs Are Part of the System
How AI workflows should treat human review, escalation, approval, correction, and ownership as designed transitions rather than interruptions.- Published on

Agentic Search Needs Source Governance
Why AI agents that search, retrieve, and synthesize information need explicit rules for authority, freshness, conflict handling, exclusion, and citation.- Published on

The Prompt Is Not the Policy
Why AI policy must live in enforceable rules, source governance, tools, approvals, and evaluators rather than being reduced to instruction text.- Published on

Design AI Workflows Around Failure Modes
Why reliable AI products should begin with expected failure classes, containment paths, and recovery states instead of only optimizing the happy path.- Published on

Evidence Manifests for Agent Work
How agents can make completion auditable by recording required sources, artifacts, checks, decisions, exclusions, and unresolved uncertainty in one durable manifest.- Published on

Shadow Mode for AI Releases
Why AI features should run beside existing workflows before taking authority, and how shadow mode exposes behavior, cost, evidence, and failure classes safely.- Published on