Claude Code for non-technical tasks, from slides to CRM
Claude Code is not only for refactoring PHP. Three things I run through it that never touch a codebase: LaTeX decks kept in Git, cross-app search over Slack and Notion, and prospect research.
Tag: AI Assistants
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.
How ElevenLabs voice AI is replacing warehouse screens
Voice picking used to mean vendor-locked hardware. ElevenLabs voice AI does the same job off an ordinary smartphone, and this covers the WordPress side of it: a cached text-to-speech wrapper, plus the latency and noise problems that sink most builds.
How I build AI memory systems that know when to forget
Vector search on its own leaves an agent repeating things that stopped being true months ago. Here is the memory lifecycle I build instead: decay scores, contradiction detection, confidence values, compression, and a background worker that does the cleanup.
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.
Build an MVP with Claude Code without the tech debt
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.
Enterprise RAG systems: how to ground AI in your data
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.
Model collapse and the case for deep web data
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.
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.