I Almost Bought an AI Code Reviewer. Then I Did the Math.
Eight months of running automated AI code review on my own projects. Then I brought it to Nayax — and didn't buy a single dedicated tool to do it. (5 min read)
Jonathan Barazany - AI Agents & Engineering Leadership
Chief AI at Nayax sharing insights on AI agents, data engineering, and technical leadership in enterprise software development.
Latest posts
I Had Claude Mine 30 Days of My Own Messages. What It Found Was Uncomfortably Accurate.
For months I kept correcting Claude the same ways. Instead of correcting it again, I asked it to go read everything I'd ever said — and tell me who I am. (5 min read)
The 5-Hour Quota, Boris's Tweet, and What the Source Code Actually Reveals
Everyone's complaining about the Claude Code quota. Boris said improvements are coming. My first reaction: what can he possibly do? Then the source code dropped. (7 min read)
Claude Code's Compaction Engine: What the Source Code Actually Reveals
A few months ago I described context engineering from the outside. Then Claude Code's repository surfaced - and I asked Claude to analyze its own source code. Here's what's actually running beneath every long session. (5 min read)
We Were About to Buy an Automation Platform. We Already Had One.
We spent weeks in governance spirals over n8n and Workato. The answer was already deployed — it just needed one more feature to click into place. (5 min read)
What Karpathy's Autoresearch Unlocked for Me
I was stuck at 0.58 AUC for three weeks. Then an AI agent ran 165 experiments while I slept — and broke through a ceiling I couldn't crack on my own. (5 min read)
How We Measured 65% AI-Written Code (And Why Lines Don't Matter)
After our Claude Code pilot hit 65% AI-written code, the most common question was: how did you actually measure that? The answer is simpler than most expect - and it starts with abandoning the wrong metric. (4 min read)
What 65% AI-Written Code Taught Us About 'Good Enough'
A pilot group of 30-40 engineers set a 40% AI-written code target. Six weeks later, the real number was closer to 80%. What we learned about adoption, power users, and the shift to 'good enough.' (5 min read)
Connecting Snowflake to Claude: The Guide That Should Have Existed
It took a month to connect Snowflake to Claude. Not because the setup is impossible — but because the right documentation doesn't exist. Here's the guide I wish I had. (5 min read)
Good Enough and Really Fast: A Haiku 4.5 Case Study
A development team moves so fast that Product can't keep up. How a shift to Haiku 4.5 changed their economics and workflow, and what it reveals about the future of coding agents. (4 min read)
Cursor 2.0: When Your Code Editor Becomes a Work OS
Cursor 2.0 reimagines code editors as orchestration platforms. Exploring multi-agent workflows, parallelization trade-offs, and how AI tools are fundamentally changing how we think about work. (4 min read)
Haiku 4.5: The Model Nobody Expected to Care About
A small, fast, affordable model that matches Sonnet 4-level capabilities. The gap between what we think we need and what actually gets the job done is closing faster than most people realize. (3 min read)
Z.ai and the GLM-4.6 Model: Good Progress, But Not Sonnet-Level Yet
GLM-4.6 is gaining attention as a capable, affordable alternative to Claude, but after nine months with Sonnet models, it's solid progress without redefining the frontier. (2 min read)
Context Engineering: What Keeps AI Agents From Losing Their Minds
Behind every long-running AI agent, there's quiet, invisible engineering that keeps the model from forgetting who it is and what it's doing. (6 min read)
Anthropic vs OpenAI: The AI Model Rally That Changed Everything
A week of rapid-fire AI releases changed the game. GPT-5 challenged Claude's dominance, Anthropic countered with 1M context windows, and Claude 4.5 followed. Here's what this means for developers. (3 min read)
How MCP Prompts Automated 600-Line Kusto Query Debugging
From manual pain to automated precision: how I used MCP tools to turn the nightmare of debugging complex Kusto queries into structured, data-driven performance reports. (4 min read)
AI Agents Debug Spark Faster
How I turned a painful Spark debugging cycle into a tight feedback loop using Databricks CLI, DuckDB, and local iteration. From cluster slog to terminal efficiency. (4 min read)
Why I Set Kubernetes CPU Requests Equal to Limits (And You Should Too)
A production mystery that changed everything I thought I knew about Kubernetes resource management. When our 8-core workload couldn't get 8 cores, I discovered the real problem with traditional request/limit configurations. (6 min read)