// tag
#ai
Every post tagged ai, newest first.
EU AI Act in Force: A Checklist for the AI Features You Ship
Enforcement began on 2 August 2026 and the high-risk rules moved to 2 December 2027. The five-module checklist I run before an AI feature ships.
Ten Million Events, One Verdict: Building the AI UX Research Platform
Four signal sources, three agents, one session timeline. The verdict arrives before the evidence does.
Vertical Agents Beat Wrappers: Proof From a Clinic and a Plumber
A chat widget answers questions and stops there. A clinic network and a plumber in Porto paid for an agent that touches their calendar, their rate card, and their logs.
Logistics Site from Zero: PHP, Admin, and a Bot That Reads Papers
One PHP build, no CMS, a private admin where the owner edits routes, price, and news, plus a Telegram bot that answers drivers from the same data.
From Craft to Velocity: My LinkedIn Pivot to AI Design Engineer
Fifteen years of Figma to Python taught me craft. Vibe Coding taught me velocity. I changed my profile when my delivery time did.
AI Team Culture Over Models: How Full-Stack Crews Ship
I ran the same model with two crews. The one that logged failures together shipped in six weeks. The other still tunes prompts.
AI Agent Development: From Prototype to Production
I take AI agents from demo to production: RAG pipelines, evals, cost and latency budgets. This guide covers each stage with the checks I run before shipping.
Staff Your AI Initiative: Three Roles That Ship
Models are interchangeable. The team is not. The AI engineer, the prompt engineer, and the responsible-AI lead: what each owns and how they work as one unit.
Why Your AI Agent Needs a Compliance Layer
I ship AI agents that log every tool call, pin data retention, and pass audits. Here is the layer I add first.
Build an AI Agent That Handles Your Leads in 48 Hours
I built a no-code agent with Make.com, Claude MCP, and Airtable that qualifies leads and books meetings. I walk through the two-day setup, the $29/month cost, and the follow-up sequence.
Glass-Box AI: Showing Model Confidence So People Trust It
Confidence Rails, Undo Trails and Intent Forks make AI uncertainty visible. People trust what they can check and reverse.
Ship Faster Than the Tech Changes
I keep learning as a habit, admit gaps early, and keep AI literacy high. That turns change into an edge.