A Field Guide for Safely Introducing AI into Unix Production Workflows. Not a productivity tutorial — an operational safety manual for engineers who already live in the terminal.
Most AI tutorials focus on productivity. Almost none focus on safety. Oyster Stew exists to prevent expensive mistakes.
If you already live in the terminal — three TTYs open, writing shell commands and scripts, managing build systems or administering servers — this guide shows you how to integrate AI, both local and remote, into your shell workflows. This is not a guide for becoming a prompt engineer. It is an operational safety field guide for experienced Unix users integrating AI into real environments.
AI is entering production environments faster than operational discipline is evolving. Oyster Stew closes that gap.
AI is not an execution engine. It is a thinking aid, a conversational co-process that lives beside your shell — interweaving grep, awk, make, and gcc without replacing any of them. The distinction between probabilistic suggestion and deterministic execution is the central discipline this guide teaches.
Seven chapters and a printable safety checklist. Each example follows a consistent pattern: real problem, exact command, AI prompt, raw output, what worked, what failed, and a safer version.
ai.sh in ~20 lines. The deliverable is the script itself.rm suggestions, overconfident Makefile edits, and fake man page options. The most valuable chapter in the guide.The guide builds around a small number of foundational ideas that apply across every workflow. Understanding these first makes everything else fall into place.
Unix tools given the same input always produce the same output. AI is a distribution over possible responses. You don't replace one with the other — you layer them.
Not an app, not a chatbot — a conversational process sitting beside your shell. Think of it as a fast junior engineer with encyclopedic recall and zero accountability.
Never execute directly. Pipe AI output into less or a file for inspection. This single pattern prevents more accidents than any other practice in the guide.
Pipe the actual man page into AI instead of asking it from memory. Hallucination drops dramatically when the model works from real source material.
Guardrails don't belong inside the model — they belong around it. Deny rm by default, require confirmation for writes, restrict scope. Shell enforces; AI suggests.
Classic Unix filters transform syntax. AI filters meaning. Piping a man page through ai.sh is qualitatively new — probabilistic compilation, not text transformation.
ai.sh wrappers for both. The remainder of the guide applies equally regardless of which backend you use.Every chapter uses real problems with real commands — not toy examples. Each section follows the same pattern: real problem, exact command, AI prompt, raw output, what worked, what failed, and a safer version.
rm suggestions, overconfident Makefile edits — you stop fearing AI, stop worshipping it, and start using it correctly.
Available as a PDF. A tokenised download link will be emailed to you immediately after registration.
Complete the form below to receive your tokenised download link by email. A copy of the link will also be shown immediately on this page.
Announcements, beta releases, and updates for Oyster Stew, AIShell-Gate, and related work from AIShell Labs. Low volume. No spam.