Turning Codex Review Into a Service
The hard part of AI code review is not asking a model to read a diff. It is turning trigger, execution, comments, approval, history, cost, and failure recovery into a controlled engineering workflow.
Tag: #Codex
11 posts
The Hottest Topic in Tech Has Moved from Models to Agents
The real heat in tech is no longer just another model release. AI coding agents are entering real development workflows: taking tasks, editing repositories, running tests, opening pull requests, and forcing old questions about context, safety, and review back onto the table.
From Missing the Subway to a Small Probability Model
A small mathematical modeling case based on a subway timing problem: headway, dwell time, running speed, distance, repeated events, and where calculus enters if we model passenger distance explicitly.
Codex App Server: Bringing Coding Agents Into Your Own Workbench
A practical look at the protocol boundary of Codex App Server, the product and engineering scenarios it fits, and how it compares with Claude Code and Cursor in automation, cloud agents, and custom integrations.
Gemma 4 12B in Practice: Local Code Generation, OpenClaw, and QVeris Tool Calls
A practical test of Gemma 4 12B through Ollama: generating Canvas code, connecting it to OpenClaw, calling QVeris tools, and judging where a 12B local model is useful and where it still needs guardrails.
The Longer You Use Codex, The More You Need To Save Tokens
A token and cost breakdown from one real long Codex session: why context is expensive, which conversations cost the most, how prompt caching helps, and practical ways to split sessions, compress logs, use files, and preserve stable rules.
Codex Practice Notes: Modes, Spark, Skills, Slash Commands, And exec
A practical Q&A about Codex collaboration modes, GPT-5.3-Codex-Spark, statusline configuration, skills, slash commands, codex exec, and the Codex SDK.
How I Use AI for Real Engineering Work: PRs, Docs, Remote Ops, and Releases
A sanitized field note on using Codex, Claude Code, Cursor, gh, and lark-cli for real engineering tasks: what work is worth delegating to AI, what boundaries must stay firm, and how to make AI-assisted work verifiable and shippable.
Image Generation Inside A Coding Tool Is Surprisingly Useful
Cursor Composer 2 can trigger image generation in real workflows, and Cursor's changelog points to Google Nano Banana Pro. This article records the workflow, cost intuition, and a same-aspect comparison with Codex-generated images.
Codex, Cursor, And The Codex Extension Inside Cursor
A practical guide to combining Codex and Cursor: product boundaries, Codex IDE, Codex CLI, the Codex extension inside Cursor, Skills, Cursor Rules, session context, and a workable coexistence workflow.
After The SpaceX And Cursor Deal: What Might Change?
A personal look at the reported SpaceX and Anysphere Cursor agreement, how Cursor differs from Claude Code and Codex, and what model ownership, capital, billing, and product direction may mean for developers.