Inzichten over het bouwen van beheerste, agentische AI.
Aantekeningen uit de studio: hoe we door AI geschreven code uitleveren met gates, audittrails en menselijk toezicht ingebouwd.
Claude Code · 23 min lezen
Stop Collecting Claude Skills and Plugins. Build a Pipeline.
What I install, in what order, what each layer catches, and what it costs, with the config files and the receipts from real pull requests.
LezenArtificial Intelligence · 8 min lezen
They Fired People for AI. Now They're Hiring Them Back.
Two in three employers that cut roles for AI are already rehiring. The data behind the reversal, and what the companies that kept their people did differently.
LezenProgramming · 13 min lezen
My AI Code Reviewer Beats Your Human One
After twenty years of cleaning up what human-reviewed code became, I stopped debating and built the harness.
LezenAi Agents · 15 min lezen
How I Trust AI Agents to Ship Enterprise-Grade Code Without Reviewing Every Line
The setup that earned that trust: nine phases, guardrail hooks, three AI reviewers, a seven-check gate wall, and the one button an agent can never press.
LezenClaude · 4 min lezen
I paid for Claude twice in one day. Check if you do too.
I pay for a Claude Max subscription. Yesterday I also had to top up my Anthropic API credits twice, 40 dollars in total, just to keep working. Both of those things should not be true at the same time.
LezenArtificial Intelligence · 13 min lezen
Gates, not guidelines: building a product with AI agents that cannot cut corners
The pitch is that you wire up one agent and go ten times faster. That is not what happens. Here is the setup, tool by tool, that actually let AI agents write every line of my product’s code without quietly breaking a database full of customer data.
LezenWilt u deze discipline op uw eigen systemen?
Wij maken van bedrijfsprocessen onderhoudbare, mens-geregisseerde AI-systemen, met governance vanaf dag één ingebouwd.