32 articles - page 2 of 3
Self-improving applications with Claude Code and Codex: the loop from user feedback to GitHub issue to reviewed PR, paying per closed issue, not per token.
Auto-narrated changelog videos in one hour: a coding agent scripts from git history, Screen Studio records the demo, and Descript narrates and edits it.
Put an AI agent on a cron job with OpenCode: a runner script, a schedule, first chores and guardrails, so recurring dev work arrives as PRs to review.
A guide to setting up an isolated spare Mac that Claude Code can control remotely over SSH, Remote Control from your phone, and Tailscale.
Loop engineering patterns: plan/act/verify cycles, convergence criteria, retries, budget-bounded loops, and loop-until-dry, so agents stop when they should.
GLM 5.2 UK VAT return benchmark: how the model handled 59 transactions with near-human bookkeeper accuracy, where it erred, and why HN focused on liability.
Codex Record & Replay companion guide: record a recurring computer task once in OpenAI Codex and replay it as a reusable automation skill, plus where it fits.
Loop engineering means building long-running loops, goals and automations instead of re-prompting an LLM. The core idea from the video and where to go deeper.
Codex-Maxxing done right is bounded autonomy: AGENTS.md, small worktrees, explicit stop conditions and review checkpoints for long-running Codex workflows.
Loop engineering in Claude Code and Codex - when to use a goal, loop or routine, the real commands, production patterns and two failure modes that burn money.
Claude Code Routines vs Managed Agents scheduled deployments: how triggers, pricing and limits differ, and where your recurring agent work should run.
codex exec is OpenAI's non-interactive mode to run Codex agents from scripts, CI and GitHub Actions. How to set it up safely with real flags and working YAML.
Showing 13-24 of 31 articles
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 840 topics
Browse All Topics