AUTHOR
Baruch Sadogursky
Baruch Sadogursky (@jbaruch) did Java before it had generics, DevOps before there was Docker, and DevRel before it had a name. He built DevRel at JFrog from a ten-person company through IPO, co-authored "Liquid Software" and "DevOps Tools for Java Developers," and is a Java Champion, Microsoft MVP, and CNCF Ambassador alumni.Today, he's obsessed with how AI agents actually write code. At Tessl, an AI agent enablement platform, Baruch focuses on context engineering, management, and sharing. On top of sharing context with AI agents, Baruch also shares knowledge with developers through blog posts, meetups, and conferences like DevNexus, QCon, Kubecon, and Devoxx, mostly about why vibecoding doesn't scale.
Articles
Article
I Spent a Week Fixing the Wrong Skill (And Other Lessons from Evaluating an AI PR Reviewer)
The article explores lessons learned from evaluating an AI PR reviewer, highlighting the importance of risk classification and addressing false positives in AI models.
Article
I Built an AI PR Reviewer That Catches Bugs by Not Looking for Bugs
An AI PR reviewer achieves 97.7% accuracy by creating evidence packs and risk classifications, aiding humans in decision-making without directly hunting for bugs.
Article
Our AI is the bright kid with no manners, part 2
The article explores how an AI's performance drastically drops when deprived of context, highlighting the importance of behavioral training for effective OSS contributions.
Article
Our AI is the bright kid with no manners, part 1
An AI agent excelled in writing code but struggled with open-source etiquette. After implementing social skills, its acceptance rate rose from 15% to 99%.
Article
I Invented a Three-Tier Stack for AI Agents (And I'm Not Apologizing)
The article discusses a three-tier stack for AI agents, emphasizing the importance of layered architecture to improve agentic applications' performance and adaptability.
Article
My Coding Agent Needed a Package Manager for Its Own Brain (And I Gave It One Using a Skills Registry)
Explore how a skills registry transformed a coding agent's decision-making, enabling it to read library documentation and make informed stack decisions.
Article
My Coding Agent Invented an API That Doesn’t Exist (And Blamed CORS When It Failed)
A coding agent mistakenly created a non-existent API and blamed CORS for failures. The article explores using Spec-kit and Tessl tiles to correct and control smart bulbs.
Article
My Coding Agent Lied to Me (And I Have the Screenshots)
The blog explores the challenges of using AI coding agents by comparing two approaches to building an airline loyalty app, highlighting issues with outdated data and misinformation.