What using Claude Code actually looks like
Using Claude Code is a loop: ask, change, check, decide. Here is what a normal session looks like, the six commands I use most, and how to recover when it goes wrong.
Ivan Misic - Blog
Product leadership, digital transformation, and lessons from 20 years of building things that sometimes work.
Latest posts
Capturing email and calendar without a mailbox API
Microsoft Graph and IMAP were off the table, so I used Power Automate, OneDrive sync, and one 15-minute scheduled task to pull email and calendar into a local inbox.
Most of my AI pipeline isn't AI
By volume, most of my AI pipeline is plain Python. The model is a small, expensive part I call as little as possible. The script-first split, and why it wins.
Claude Code skills: building a workflow that runs itself
The whole control layer of my work system is a folder of markdown files. How a real workflow is built from Claude Code skills, rules, and parallel sub-agents.
The Claude Code plugins I built and run
I put the Claude Code tools I reuse across projects into one public toolshed: generators, workflow commands, anti-slop checks, search visibility, rule packs, and prompts.
My AI was smart. It just couldn't see my job.
My work context was scattered across email, meetings, documents, and notes. So I wired it into a private Obsidian vault Claude Code can read.
Your next team is three people and a pile of agents.
I expect AI-assisted teams to become smaller and organize around complete workflows. The model works only when the pod owns the outcome and runs what it builds.
Four calendar days, one person, one full redesign
Full site redesign, end to end: design system, admin stack, the lot. Four calendar days, one person, two evenings plus a weekend of real work. The interesting bit isn t the speed. It s what the new ship velocity asks of teams.
A safe way to edit database content with AI coding tools
AI coding tools edit files. Your content lives in a database. This is the pull, diff, push workflow that connects the two without hand-writing SQL against production.
Klarna's AI U-turn isn't a failure story
Klarna reported faster support and stable satisfaction, while its CEO later admitted that cost focus reduced quality. Product leaders need to read both.
The permission tax: why growing teams ship less, not more
It took a month to build and four months to get permission. Growing teams don t move faster. They just spend more time asking for approval.
One app, many markets: the central vs. local paradox
Build centrally and local markets hate you. Build locally and you drown in fragmentation. The model that actually works for multi-market digital products.
AI made building easy. Knowing what to build just got expensive.
AI can make execution cheaper, but it also exposes weak decisions faster. The valuable skill is defining work clearly enough to test whether it matters.
The app consolidation playbook
Large app portfolios grow through local decisions, acquisitions, and separate teams. Consolidation works when one owner can remove duplication while keeping the local differences customers need.
AI isn't coming for your team. It's coming for their busywork.
AI s immediate value is removing repetitive work from experienced people. Leaders should start with one workflow, not a headcount target.
Don't replace your billing system (build around it instead)
Core-system replacement programs can delay digital products for years. I would build a stable API around the current system so the digital product can move.
The laundry list trap: why much of your roadmap doesn't matter
We analyzed engagement across an entire app feature set. Over 40% of the candidate scope generated less than 2% of measured engagement. I use that evidence to decide what deserves a place on the roadmap.
Your app isn't a service channel (it should be your business)
I watched European telco apps move from self-service into sales and retention. These three phases explain what changed and where the programs became stuck.
How I built this site with Claude Code
Three weeks, end to end: PHP backend, vanilla JS, a CSS design system I built by hand, the lot. Claude did most of the typing. The speed is the obvious story. The one worth telling is which decisions I d still own and which I d hand back.
Claude Code and the context window on bigger projects
My website is close to a thousand files. I keep Claude Code useful by giving each session one task, naming the files involved, and keeping the project instructions current.