Automating deep learning experiments with agentic AI
A practical way to stop babysitting deep learning runs: containerize your training script, add a health-check sidecar, and let an agent handle restarts and hyperparameter tweaks.
Tag: AI Assistants
WordPress AI Assistant is now built into WordPress.com
WordPress.com built its new AI Assistant directly into the block editor and Media Library. It edits blocks and generates images with Google’s Gemini models, though full layout control needs a Block Theme.
Vibe coding security risks I keep finding in client code
AI agents optimize for code that runs, not code that is safe. Two failures I keep finding in agent-written WordPress code, hardcoded API keys and REST routes with no permission callback, plus the review habits that catch them.
Agentic AI for repositories: automating READMEs and CI
Writing the README and wiring up CI is the part everyone puts off. OSA is a multi-agent tool that reads the repository, drafts the docs and docstrings, and generates the workflow files. Here is how it works and how to run it.
Claude Code internal tooling that actually saves time
Claude Code pays off when you build it tools instead of asking it for snippets. A CLAUDE.MD map, real WP-CLI commands, and a small plugin audit script turned a four-hour debugging session into a check that runs in seconds.
AI agent prompt fidelity: verified data vs guesswork
AI agents rarely tell you which parts of an answer came from your data and which came from the model’s memory. Here is how to score that split in bits, and how a loose tool schema leaves the agent guessing.
Agentic RAG on SQL without changing your schema
Dumping a relational database into a vector store gives you a slow, expensive system that has forgotten its own schema. This covers hybrid retrieval instead: ReAct tool routing, why FAISS post-filtering returns nothing, and a PHP dispatcher for WordPress.
Agentic AI supply chain: why dashboards can’t find the delay
Dashboards tell you a delivery was late. They do not say which team caused it. This post covers the MCP setup I use so Claude can read ERP, WMS and TMS timestamps and work out where the delay started.
AI coding agents and the code smells they leave behind
Notes from cleaning up after AI coding agents: the code compiles fine and still rots. Divergent change and speculative generality are the two smells I keep finding, with a refactored ML pipeline showing the fix.
OpenClaw as a personal AI assistant, isolated in Docker
OpenClaw keeps Claude Code running as a long-lived agent instead of a chat window. My setup puts it in a Docker container, links a Claude Code token, and uses explicit skills for jobs like GitHub PR reviews and email triage.