After 14 years I moved most of my work out of the IDE and into the terminal: Claude Code in Warp, a Git worktree per agent so they stop colliding, and stored slash commands so I am not retyping the same prompt.
AI can write a WooCommerce feature in seconds, and it usually writes it as one 150-line God function with a hard-coded API key. This is what that debt costs and how to refactor it into something maintainable.
Chatting with an LLM in a browser tab is a bottleneck. This is the Claude Code setup I use instead: slash commands for the prompts I repeat, an AGENTS.md file for project memory, and plan mode before any code gets written.
Longer context windows cost server memory, not just compute. Infini-attention replaces the growing KV cache with a fixed-size compressive memory matrix updated by a Delta Rule, which cut memory use by 114x in Google’s tests.
Running several coding agents at once only works if you plan the work first and keep them off each other’s files. Here is the four-step workflow I use with Claude Code and Warp, plus the migration mess that taught me the isolation rule.
Prompting stops scaling as soon as a task has real edge cases. Here is what the Stanford ACE research found about its generator, reflector and curator loop, where the gains show up, where they do not, and how to keep the same kind of playbook in WordPress.
How I built a Mandarin tutor on n8n: audio in through a webhook, transcription with pinyin, Gemini for the pronunciation feedback, and ElevenLabs for the voice. It runs under 1 euro a month.
Most LLM agents ship with no visibility between the input and the answer. How the NeMo Agent Toolkit traces every tool call and scores trajectory rather than answer accuracy alone, using Arize Phoenix and W&B Weave.
I stopped retyping the same AI prompts and moved them into a commands folder. How slash commands work in Cursor and Claude Code, the two I use most on WordPress projects, and why that folder belongs in Git.
Manual prompt tweaking does not survive contact with vision models. A walkthrough of HRPO in the Opik-optimizer SDK on driving data: how the loop is wired, why you need a hold-out set, and the run that took accuracy from 15% to 39%.