Egor Burlakov
••3 min readWho Is to Blame? Working with Coding Agents
Three thousand commits with coding agents. When things went wrong, the agent had almost always done exactly what I asked.
Read article
Three thousand commits with coding agents. When things went wrong, the agent had almost always done exactly what I asked.
The stack recommender now ranks on how well a product fits your requirements rather than how popular it is, and prices a stack on the edition you would actually buy. Plus alternatives that really compete, comparisons that answer a real question, and a reordered profile page.
One model plans, another writes the code. The surprise was the two writing the code messaging each other and sorting out a task without me
After scoring 500+ data tools on a 100-point framework, clear patterns emerge. Here are the ten that separate great tools from forgettable ones.
Local LLMs are practical for content generation, legal document processing, and internal knowledge bases. I benchmarked five Qwen models on my MacBook Pro. Qwen 3 14B scored 91/100 avg vs 62 for Qwen 2.5 14B -- same size, dramatically better. Newer models performed worse.
A practical 2026 guide to starting an AI-assisted software project — tools, agent orchestration, Git rules, baselining, documentation, and lessons learned.
Data pipelines pass all tests but silently lose millions in revenue. Discover Automated Data Tests (ADT)—lightweight checks that catch join drops, sum errors, and aggregation glitches across billions of rows. Python and SQL solutions coming next.
How specs make AI coding reliable—and redefine the manager's role
Tech front lines to AI era: real stories on leading teams, testing tools, and data engineering wins—short, human-crafted lessons for your daily grind.