agentic engineering
4 mentions across all digests
Agentic engineering is the practice of developing production-quality software by directing AI coding agents (such as Claude Code, Codex, or Gemini CLI) that run tools in a loop, where the human role shifts to specifying problems well, verifying results, and updating agent instructions — distinct from 'vibe coding' in that it emphasizes rigor and review.
What is agentic engineering?
Agentic engineering redefines the developer's role from code author to problem specifier and instruction refiner, establishing a rigorous, production-quality discipline distinct from prototype-quality "vibe coding."
Cirrus Labs to join OpenAI
Bootstrapped developer tools maker Cirrus Labs joins OpenAI's Agent Infrastructure team, bringing Apple Silicon virtualization and CI/CD expertise to accelerate agent development.
Your code is worthless
Garry Tan's celebrated 37,000 LOC/day from AI-generated code is productivity theater that silently accumulates technical debt and security risk — repeating Bill Atkinson's 1982 lesson that code deletion, not generation, creates value.
Highlights from my conversation about agentic engineering on Lenny's Podcast
Claude Opus 4.5 and GPT-4.1 crossed a November 2025 inflection point where code generation shifted from 'mostly works' to 'almost always works,' marking a critical capability threshold for agentic engineering and positioning software engineers as early indicators of broader information worker automation.