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.
Claude Code will scaffold a WordPress plugin faster than you can spec one, which is the problem. The workflow I use: a CLAUDE.md spec first, the terminal agent second, and a manual review of everything before it ships.
An LLM pointed at a folder of documents will confidently quote a 2019 policy at a customer in 2026. What decides whether a RAG pipeline holds up is the chunking, the retrieval and the evaluation, not the model you picked.
Models trained on the output of earlier models lose the tails of the distribution and drift into nonsense. The clean data sits behind logins, and the PROPS framework is one way to train on it without anyone handing it over.
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.
The Core AI team has a draft guide for anyone presenting on Abilities, the AI Client or the MCP Adapter at a WordCamp or meetup. Comments on it close on 21 April 2026.
AI tools guess at your store because they cannot see it. MCP gives them real context: your files, your data, your WP-CLI. We talk it through at WooCommerce office hours on April 15, 2026, on Slack.
Pinecone and Chroma are a lot of machinery for a few hundred Markdown notes. The Google Memory Agent Pattern keeps structured memories in SQLite, consolidates them in the background, and loads them straight into a large context window.
Most people run one Claude Code agent and then wait for it. Git worktrees let you keep several going in separate folders on the same repo. How I lay that out in Warp or Tmux, plus the shared local database problem nobody warns you about.
MCP lets an AI pull data out of Google Drive, read old repos and load BigQuery instead of just suggesting Python. Includes the 150GB log file one unattended loop produced, and why domain knowledge still decides the answer.