ÜberConf 2026 is taking place in Denver, USA, featuring a workshop on AI without the slop presented by a CodeScene representative. The conference offers opportunities for attendees to visit the CodeSc…
A developer shared reflections after six months of using agentic engineering for software development, finding the shift surprisingly easy and noting that good coding practices remain relevant. Human …
A developer found that giving an AI coding agent a tool to check code health before commits achieved 100% compliance, compared to only 70-85% with a written rule. The tool, an MCP server entry point c…
An experiment comparing token usage between MCP and CLI approaches for LLM tool calling found no significant difference, with MCP using 5 fewer input tokens on the initial request and negligible per-c…
A developer researching code quality tools found that methods most tools rely on, such as complexity metrics and code smells, have weaker empirical evidence than expected. The research aims to identif…
CodeScene released a PR Refactoring Agent that autonomously analyzes pull request code health and fixes issues, creating new commits. The tool packages everything into a single executable with a ready…
Codebases with poor code health cause AI agents to consume 35-50% more tokens when performing the same tasks, according to research across C++, Java, and Python by CodeScene. The study found that unhe…