WooCommerce bug fixing: the support team cleared 150 bugs
Woo ran a Bug Blitz: support engineers with Claude Code and Copilot shipped over 170 fixes across 20 products, every line reviewed by quality engineers. Why it worked and what to copy.
Tag: Agentic Commerce
How to give your AI coding assistant a memory
LLMs forget your stack the moment you close the tab. Here is what actually sticks: a project rules file in the repo, global rules for your own preferences, and MCP when the assistant needs data from outside the codebase.
AI agent architecture: why LLM wrappers are dying off
One LLM cannot draft emails, read documents and optimize a sales pipeline well. A look at splitting the work across reasoning, orchestration and execution layers, with TD learning doing the sequential decisions.
Context engineering for AI agents: why bigger windows fail
Bigger context windows do not fix agent reasoning. Notes on context rot, compaction and folding, the harness that wraps the model, and why agents should pass distilled artifacts instead of raw traces.
WordPress 7.0 AI infrastructure and the end of glue code
WordPress 7.0 ships three pieces of AI plumbing: the Abilities API for registering what a site can do, the AI Client for provider-agnostic model calls, and the MCP Adapter that exposes both to assistants like Claude.
Agentic AI transparency without the black box or the log dump
Two bad defaults for agent UIs: hide everything behind a spinner, or stream every raw log. What I map instead, and how I decide which agent decisions a user actually needs to see.
Bits-over-Random metric: why more context hurts AI agents
The Bits-over-Random Metric compares your retrieval against random chance, which is how you catch the context pollution a high Success@K hides. Notes on staged tool routing and where the collapse regime starts.
Claude Code efficiency starts before the agent writes code
My agent failed the same caching refactor three times before I fixed how I was briefing it. Planning mode, browser access through Playwright MCP, and claude.md files are what turned that into one-shot work.
Autonomous AI agents as a force multiplier, scars included
My agents decided their own heartbeat config was redundant and deleted it, twice. The tiered OpenClaw setup that came out of it: orchestrators for judgment, throwaway personas for tasks, and five Markdown files that hold an agent’s identity.
AI agent reliability: why 85% per step means 20%
An agent that is 85% accurate per step is about 20% accurate over ten steps. Lusser’s Law explains why, the Replit database deletion shows what it costs, and a gatekeeper pattern in PHP puts human review in front of the irreversible actions.