Agentic Engineering & ToolingConference50min
Architecture Observability and Guardrails
Talk on preventing “AI slop” by enforcing code quality in AI-generated codebases. It covers agent design feedback loops and ways to preserve human review bandwidth, using C4 models, PlantUML, captured sequence diagrams, complexity visualizations, and efficient testing practices.
talk.summaryAiDisclaimer
Victor RenteaFreelance
talkDetail.whenAndWhere
Wednesday, October 7, 16:40-17:30
TBA 7
talks.roomOccupancytalks.noOccupancyInfo
How do you observe and enforce the code quality to prevent AI Slop? The majority of the teams attending my workshops report 100% of their code is AI-generated already for many months. Some even report they often have to fix PRs that business vibe-coded. This talk summarizes the design feedback loops they setup for their agents, as well as techniques to maximize the human mental bandwidth in the code review step. You’ll hear about C4 model, plantuml diagrams, captured sequence diagrams, complexity visualisation, and efficient testing practices.
Victor Rentea
With 2 decades of software engineering experience, Victor spent the last 10 years training thousands of developers and architects from 150+ companies. Since early 2026, he’s been working hard to help his clients adopt Agentic Engineering, coaching AI Champions, developers, testers, product owners, ops, and managers with practical, actionable advice to kick-start their agentic reconversion. Every year, Victor gives energetic, intense conference talks in which he distills his training sessions - so be sure not to miss these ideas, heavily brainstormed with millennia of total experience. More about him on https://victorrentea.ro, and https://agentic.how.