Written by Florin — full-stack & AI engineer.
Latest articles
Designing Trust Boundaries for MCP Servers That Call Your Backend
The Mistake I Keep Seeing With MCP Model Context Protocol gives AI agents a standard way to connect to tools. It does not automatically…
When AI Agents Hallucinate IDs
A Production Bug That Changed One of My Rules for Tool Calls A customer asked a booking assistant a normal question: Do you have…
Review Debt: The Cognitive Cost of AI-Assisted Coding
A few months back, I shipped four features in two days. By Friday of that week, I couldn't explain two of them without opening the code. By…
AI Engineering · 3 posts
Designing Trust Boundaries for MCP Servers That Call Your Backend
The Mistake I Keep Seeing With MCP Model Context Protocol gives AI agents a standard way to connect to tools. It does not automatically…
When AI Agents Hallucinate IDs
A Production Bug That Changed One of My Rules for Tool Calls A customer asked a booking assistant a normal question: Do you have…
Review Debt: The Cognitive Cost of AI-Assisted Coding
A few months back, I shipped four features in two days. By Friday of that week, I couldn't explain two of them without opening the code. By…
Algorithms · 3 posts
Valid Parentheses
Problem Given a string containing just the characters '(', ')', '{', '}', '[', and ']', determine if the input string is valid. Description…
Climbing Stairs
Problem You are climbing a staircase with n steps. At each step, you can climb either 1 or 2 steps. Determine the number of distinct ways to…
Anagram
Problem Given two strings, a and b, write a function to determine if a is an anagram of b Description The function receives two strings and…
LangChain · 6 posts
Schema-Driven Validation for Stable LLM Evaluations
In my first eval runs, a single malformed row could flip a whole report. Now schemas sit in front of the dataset and the model outputs, so…
Why Averages Lie: Using Tags to Expose Hidden LLM Regressions
In the overall score, our bundle recommender seemed stable. One region-specific slice, though, was failing badly, and tags are what made it…
Tracing LLM Pipelines: From Bug Report to Root Cause
The fastest way I've found to debug an LLM app is to open its trace first. A good trace shows where the chain broke and which inputs…
Node.js · 1 posts
System Design · 2 posts
Scaling to 1 Million Requests Per Second
A system design interviewer asks: "How would you handle 1 million requests per second?" I've been on both sides of that question. And…
Reliable Order Processing: From Retries and Cron to Async Workflows
When our license-ordering system places an order with Microsoft, the order stays pending for a while before it becomes an active…