# AI Architects

> AI Architects helps business owners translate AI capability into operational leverage. We run a mentorship program, a 30-day Claude Code challenge, and publish field notes from real implementations.

## Core pages
- [Home](https://theaiarchitects.com/): Overview of AI Architects, what we do, who it's for.
- [About](https://theaiarchitects.com/about): Background on Tom Crawshaw and the team.
- [Mentorship](https://theaiarchitects.com/mentorship): 1:1 + cohort program for business owners implementing AI in their operations.
- [30-Day Challenge](https://theaiarchitects.com/challenge): Build-in-public Claude Code challenge — daily prompts, weekly calls.
- [Blueprint](https://theaiarchitects.com/blueprint): Self-serve framework for mapping where AI fits in a business.
- [Case studies](https://theaiarchitects.com/case-studies): Documented client outcomes.
- [Blog](https://theaiarchitects.com/blog): Articles, frameworks, and field notes.

## Case studies
- [Kyle Rucker](https://theaiarchitects.com/case-studies/kyle-rucker): Replaced manual ops, projecting six figures year-one savings
- [Cal Hewitt](https://theaiarchitects.com/case-studies/cal-hewitt): Built agentic work-order dispatch, became company's head of AI
- [Chris Cole](https://theaiarchitects.com/case-studies/chris-cole): Cut a 2-day document workflow to under 2 minutes
- [Keven Elison](https://theaiarchitects.com/case-studies/keven): Rebuilt a 7-year content workflow into a system that runs in minutes
- [Tim King](https://theaiarchitects.com/case-studies/tim): Launched solo AI agency, 7 demos and first client in 30 days
- [Andrew Bybee](https://theaiarchitects.com/case-studies/andrew-bybee): Built his first software in 2 weeks with zero coding experience
- [Doug Loud](https://theaiarchitects.com/case-studies/doug-loud): Built a one-click web dashboard that hides Claude, n8n and Qdrant from non-technical users
- [Chris Hawes](https://theaiarchitects.com/case-studies/chris-hawes): Built and pitched a RAG storytelling product, signed first client
- [Lisa Avvocato](https://theaiarchitects.com/case-studies/lisa): Shipped ad, blog and SEO workflows from a non-technical start
- [Steven](https://theaiarchitects.com/case-studies/steven): Shipped first paid lead-gen build in 3 weeks from zero

## Articles
- [Claude Code Plan Mode Checklist Before Production Edits](https://theaiarchitects.com/blog/claude-code-plan-mode-checklist): A practical checklist for using Claude Code Plan Mode before you let an agent edit production code, automations, or business-critical workflows.
- [Claude Chrome Extension Permissions: What It Can See](https://theaiarchitects.com/blog/claude-chrome-extension-permissions): A plain-English guide to Claude Chrome extension permissions, what browser agents can access, and the workflow rules non-technical teams should use before trusting it.
- [Claude Code API Credits: The Real Free Trial Path](https://theaiarchitects.com/blog/claude-code-free-trial-api-credits): How to use Anthropic API credits to test Claude Code without committing to a subscription, what the test proves, and where it gives a false signal.
- [Claude Code Pricing Calculator: Pick Pro, Max, or API](https://theaiarchitects.com/blog/claude-code-pricing-calculator): A practical decision guide for choosing Claude Code Pro, Max, or API credits based on how often you build, how large your projects are, and whether you need predictable spend.
- [GitHub MCP for Claude Code: Setup Checklist](https://theaiarchitects.com/blog/github-mcp-claude-code-setup-checklist): A practical setup checklist for connecting GitHub MCP to Claude Code, including permissions, repo boundaries, review rules, and the first safe workflow.
- [Is Claude Down? Check This Before You Debug Claude Code](https://theaiarchitects.com/blog/is-claude-down-before-you-debug): A simple outage checklist for Claude, Claude Code, the API, your network, and local project setup so you do not waste an hour debugging the wrong thing.
- [Claude Code Tutorial: The Only One You Need](https://theaiarchitects.com/blog/claude-code-tutorial): The Claude Code tutorial that skips the fantasy builds and shows the real mistakes, the real learning timeline, and the setup that makes it actually work.
- [Claude Code Use Cases That Are Actually Insane](https://theaiarchitects.com/blog/claude-code-use-case-examples): Five Claude Code use case examples from a live demo: content repurposing, live dashboards, pre-call briefs, website builds, and invoice handling.
- [Claude Code for SEO: How I Ranked #1 on Google](https://theaiarchitects.com/blog/claude-code-seo): How I use Claude Code and the DataForSEO MCP to build a keyword-researched content cluster that ranks on Google, the exact 6-prompt SEO workflow.
- [How to Learn AI in 2026: My Unfiltered Advice](https://theaiarchitects.com/blog/how-to-learn-ai-2026): Stop consuming tutorials and start building. Here's my honest advice on how to learn AI in 2026, based on 10 years of building automation systems.
- [Hermes Agent: A Beginner's Guide](https://theaiarchitects.com/blog/hermes-agent): Hermes Agent is an open-source self-hosted AI agent that learns your habits, builds reusable skills, and runs 24/7 on a VPS, here's how to get started.
- [Claude Code Tips: 10 Hacks From 1,000 Hours In](https://theaiarchitects.com/blog/claude-code-tips): 10 Claude Code tips from 1,000 hours of real use: auto mode, plan mode, Superpowers plugin, CLAUDE.md, token optimizer, and more.
- [Claude Code Status Line: Show Context, Cost and Git](https://theaiarchitects.com/blog/claude-code-statusline): The Claude Code status line is a custom bar showing context usage, cost, and git status. Here's how to set it up with /statusline or a script.
- [How to Update Claude Code (and When You Don't Need To)](https://theaiarchitects.com/blog/claude-code-update): How to update Claude Code: when it auto-updates, when you run claude update yourself, and how to fix a stuck version. The honest version, by install method.
- [Claude Code Settings: The settings.json Guide](https://theaiarchitects.com/blog/claude-code-settings): Claude Code settings live in settings.json across four levels. Here's the hierarchy, the precedence order, and the keys that actually matter.
- [Claude Code Checkpoints: How to Rewind a Bad Edit](https://theaiarchitects.com/blog/claude-code-checkpoints): Claude Code checkpoints auto-save your code before each edit so you can rewind. Here's how /rewind works, what it tracks, and the one thing it doesn't.
- [Claude vs ChatGPT Chrome Extension: Which Wins?](https://theaiarchitects.com/blog/claude-vs-chatgpt-chrome-extension): I've run both browser extensions in real workflows. Claude wins on browser control and multi-step automation. ChatGPT wins on simplicity. Here's the full breakdown.
- [Claude Chrome Extension Not Working? Fixes](https://theaiarchitects.com/blog/claude-chrome-extension-not-working): If your Claude Chrome extension is not working, the most common cause is a plan mismatch or missing site access, not a broken install. Here are the fixes for every failure mode.
- [Best MCP servers for Claude Code (my stack)](https://theaiarchitects.com/blog/best-mcp-servers-for-claude-code): The best MCP servers for Claude Code connect it to the tools you already work in. Here are the ones I run every day, plus how to add them.
- [Claude Code vs Codex: When I Use Each (Honest Take)](https://theaiarchitects.com/blog/claude-code-vs-codex): Claude Code vs Codex from someone who runs both. The real differences, when I reach for Codex, and why Claude Code stays my default driver.
- [Supabase MCP for Claude Code: Setup and What It Does](https://theaiarchitects.com/blog/supabase-mcp-claude-code): The Supabase MCP server lets Claude Code query your database, run migrations, and read logs. Here's how I add it and what I actually use it for.
- [Claude Code in Cursor: How I Run It (and Skip Cursor AI)](https://theaiarchitects.com/blog/claude-code-in-cursor): How to run Claude Code in Cursor: the integrated-terminal CLI setup, the extension panel, IDE diff viewing, and why I use Cursor as just an editor.
- [Git Workflow for Claude Code: Solo and Team Guide](https://theaiarchitects.com/blog/git-workflow-claude-code): I ran feature branches on a one-person project for months. Here's the git system that actually works for solo Claude Code operators and teams.
- [Claude in the Browser: The Build-and-Verify Loop](https://theaiarchitects.com/blog/claude-browser): Using Claude in the browser means Claude can read, click, and verify in Chrome while you build in the terminal. Here's how the developer loop actually works.
- [Claude Code Use Cases: What I Actually Build With It](https://theaiarchitects.com/blog/claude-code-use-cases): Claude Code use cases go far past writing code. Here are the real ones I ship with it: content pipelines, lead-gen sites, agents and back-office automation.
- [Claude Code Notifications: Get Alerted When It's Done](https://theaiarchitects.com/blog/claude-code-notifications): Claude Code notifications alert you when a task finishes or needs permission. Enable the terminal bell, desktop alerts, or a custom sound hook.
- [GitHub MCP for Claude Code (my setup)](https://theaiarchitects.com/blog/github-mcp-claude-code): The GitHub MCP server lets Claude Code work your repos: pull requests, reviews, issues, code search, and CI. Here's how to set it up and what it's for.
- [Playwright MCP for Claude Code (setup + verdict)](https://theaiarchitects.com/blog/playwright-mcp-claude-code): Playwright MCP lets Claude Code drive a real browser: click, fill, screenshot, and test. Here's how to install it and when it actually earns its slot.
- [Claude Agent Mode: Background Sessions You Monitor From One Screen](https://theaiarchitects.com/blog/claude-agent-mode): Claude agent mode (agent view) lets you dispatch multiple background Claude sessions and monitor them all from one screen with the claude agents command. Here is how it works.
- [Vibe Coding Tools: What They Are and Which to Use in 2026](https://theaiarchitects.com/blog/vibe-coding-tools): Vibe coding tools let you build apps and scripts by describing what you want in plain English. Here is the landscape in 2026, what each tool is actually for, and how to choose.
- [The Best Vibe Coding Tools in 2026: Tested and Ranked](https://theaiarchitects.com/blog/best-vibe-coding-tools): The best vibe coding tool depends on what you are building. Claude Code for production systems, Cursor for IDE workflow, v0 for UI, Bolt for no-setup prototyping. Here is the honest ranking.
- [Claude Code Multi-Agent: Orchestration Patterns That Work in 2026](https://theaiarchitects.com/blog/claude-code-multi-agent): Multi-agent orchestration in Claude Code means splitting work across coordinated Claude sessions. Here are the three patterns that work and the one decision that determines which to use.
- [Claude Vibe Coding: What It Is, When It Works, When It Doesn't](https://theaiarchitects.com/blog/claude-vibe-coding): Vibe coding with Claude means describing what you want and letting AI write the code. Here is the honest version of when that works, when it fails, and why Claude Code is the serious builder's pick.
- [Claude Cowork Plugins: Connectors, Skills, and What Ships Free](https://theaiarchitects.com/blog/claude-cowork-plugins): Claude Cowork plugins bundle connectors and skills together. Anthropic ships three free plugin packs. Here is what each one includes and how to extend Cowork beyond the built-ins.
- [Claude Cowork on Windows: Install and First Task (2026)](https://theaiarchitects.com/blog/claude-cowork-windows): Claude Cowork works on Windows through the Claude desktop app. Here is the exact install path, what you need, and how to run your first task in under 10 minutes.
- [Is the Claude Chrome Extension Safe?](https://theaiarchitects.com/blog/is-claude-chrome-extension-safe): The Claude Chrome extension is safe for everyday business tasks, with real limits you need to know. Here's what Claude can see, what it can't, and when to keep it off.
- [How to Install the Claude Chrome Extension](https://theaiarchitects.com/blog/how-to-install-claude-chrome-extension): Install the Claude Chrome extension in four steps: open the Web Store, click Add to Chrome, sign in with your paid plan, and grant site access.
- [Blender MCP: Control Blender With Claude (Setup + Real Examples)](https://theaiarchitects.com/blog/blender-mcp): Blender MCP connects Blender 3D to Claude via the Model Context Protocol. You describe what you want in plain English and Claude creates, modifies, and scripts objects in Blender directly.
- [Context7 MCP: Up-to-Date Docs Inside Claude Code (2026)](https://theaiarchitects.com/blog/context7-mcp): Context7 is an MCP server that pulls current library documentation into Claude Code at query time, stopping the hallucinated APIs and outdated code examples.
- [Claude Opus 4.8: The Model That Stopped Guessing](https://theaiarchitects.com/blog/claude-opus-4-8): Claude Opus 4.8 is Anthropic's new flagship model, and the real upgrade isn't speed. It's honesty: around 4x less likely to let its own code flaws slip.
- [Claude Code Agents Explained: Subagents, Agent View, and Teams](https://theaiarchitects.com/blog/claude-code-agents): Claude Code has four ways to run agents in parallel. Subagents, agent view, agent teams, and worktrees each do something different. Here is how to choose.
- [What Is Claude Cowork? The AI That Does Your Work For You](https://theaiarchitects.com/blog/claude-cowork): Claude Cowork is Anthropic's desktop AI that does the work for you. What it is, how it works, what people build with it, and where it falls short.
- [Claude Agent Teams: How to Run Multiple AI Agents at Once](https://theaiarchitects.com/blog/claude-agent-teams): Claude agent teams let multiple Claude Code agents talk to each other and share a task list. How they work, setup, and whether they beat subagents.
- [Claude Cowork vs Claude Code: Which One Should You Use?](https://theaiarchitects.com/blog/claude-cowork-vs-claude-code): Claude Cowork vs Claude Code, explained simply. Cowork is your assistant, Code is your engineer. How they differ and which to use for what.
- [10 Real Claude Cowork Use Cases That Save You Hours](https://theaiarchitects.com/blog/claude-cowork-use-cases): 10 real Claude Cowork use cases pulled from actual demos, with the numbers. Receipts, file cleanup, inbox triage, reports, and scheduled work.
- [How to Use Claude Cowork (Step-by-Step for Operators)](https://theaiarchitects.com/blog/how-to-use-claude-cowork): How to use Claude Cowork the right way. Folder setup, guardrails, connectors, outcome-first prompts, skills, and scheduled tasks, in 7 steps.
- [AI Statistics 2026: Adoption, Agents, and ROI](https://theaiarchitects.com/blog/ai-statistics-2026): The AI statistics that matter in 2026: adoption rates, AI agent deployment, ROI, barriers, and jobs, pulled from McKinsey, Stanford HAI, and Gartner.
- [How to Install Claude Code on Windows in 2026 (PowerShell, WSL, and the Path Gotcha)](https://theaiarchitects.com/blog/claude-code-windows-install): How to install Claude Code on Windows step-by-step. The two install methods (PowerShell vs WSL), the path issue that breaks half of new setups, and how to verify.
- [Claude Code on the Web: Coding From Your Phone in 2026](https://theaiarchitects.com/blog/claude-code-web): Claude Code on the web, mobile, desktop, and terminal. Multi-surface async coding, Routines, Channels, and the iOS app workflow that changed mine.
- [Claude Code Rate Limits and How to Stop Hitting Them (2026)](https://theaiarchitects.com/blog/claude-code-rate-limits): Claude Code rate limits, how to check your usage, the 5-hour and weekly caps explained, plus 9 ways to cut token usage by 80% without changing what you ship.
- [npm install @anthropic-ai/claude-code: What Actually Happens (and 4 Errors to Watch For)](https://theaiarchitects.com/blog/npm-install-claude-code): What npm install @anthropic-ai/claude-code actually does, what gets installed where, the 4 errors most devs hit on first run, and the verify command that proves it worked.
- [Claude Code Free Trial: The Honest Path to a Real Test in 2026](https://theaiarchitects.com/blog/claude-code-free-trial): Is there a Claude Code free trial in 2026? Yes and no. Here's what's actually free, what isn't, and the cheapest path to a real test before you commit to a plan.
- [The --dangerously-skip-permissions Flag: When to Use It](https://theaiarchitects.com/blog/claude-code-dangerously-skip-permissions): Claude Code's --dangerously-skip-permissions flag bypasses every permission prompt. Here's when it's actually safe, when it will cost you, and the smarter alternatives.
- [Claude Agent SDK: Build Your First Production Agent](https://theaiarchitects.com/blog/claude-agent-sdk): The Claude Agent SDK lets you build production AI agents in Python or TypeScript. Inbox triage tutorial, MCP servers, cron deploy, rate-limit gotchas.
- [24 Claude Code Skills, Subagents and Hooks Worth Stealing in 2026](https://theaiarchitects.com/blog/best-claude-code-skills): The 24 skills, subagents, and hooks I actually run in my Claude Code setup, with one-line problem statements and the .claude/ files behind each one.
- [Claude Code vs Copilot vs Codex: Three Tools, Three Jobs](https://theaiarchitects.com/blog/claude-code-vs-copilot): I ran the same five tasks through Claude Code, GitHub Copilot, and Codex CLI. Here's where each one wins and why pairing them beats picking one.
- [Claude Plugins Explained: Install, Create, and Distribute](https://theaiarchitects.com/blog/claude-plugins): Claude plugins bundle skills, agents, hooks, and MCP servers into one installable package. How to install, create, and compare plugins to .claude/ config.
- [Claude for Excel: The Honest Guide to AI in Spreadsheets](https://theaiarchitects.com/blog/claude-for-excel): Claude for Excel is an AI add-in that lets you ask questions about any cell, fix formula errors, test scenarios, and build models from scratch inside your workbook. Here is how it actually works.
- [Claude Code GitHub Integration: Actions, MCP, Auto-Review in 2026](https://theaiarchitects.com/blog/claude-code-github): How to wire Claude Code into GitHub. Three integration paths (Actions, MCP, /review), copy-paste workflow file, and the auto PR review setup.
- [Claude Chrome Extension: Setup, 8 Use Cases, Privacy](https://theaiarchitects.com/blog/claude-chrome-extension): The Claude Chrome extension gives Claude real browser control. Here's the setup, the 8 use cases that matter, and the privacy trade-off in plain language.
- [Claude Code Slash Commands: What They Do and How They Work in 2026](https://theaiarchitects.com/blog/claude-code-commands): Claude Code slash commands turn repeat prompts into one keystroke. Here's how they work, the 9 I run, and the quiet merge into skills.
- [Markdown vs HTML for Claude Code: When to Use Which (and Why Anthropic Just Switched)](https://theaiarchitects.com/blog/markdown-vs-html-claude-code): On May 9, Thariq from the Claude Code team published a piece arguing HTML beats markdown for plans, audits, reports, and reviews. 10.9M views in 48 hours. Here is the head-to-head: where HTML wins, where markdown still wins, the gotchas, and 5 prompts to test it on real work.
- [The Ralph Wiggum Loop and /goal in Claude Code (2026)](https://theaiarchitects.com/blog/claude-code-ralph-loop): The Ralph Wiggum loop is the AI coding pattern where the agent keeps building until a verifiable condition is met. Claude Code's /goal command is the official version. Here's how to use it.
- [Claude vs Gemini for Real Work in 2026](https://theaiarchitects.com/blog/claude-vs-gemini): Claude vs Gemini tested on 6 real workloads: code review, email, spreadsheets, research, agent building, and long-doc QA. Honest results and a clear verdict.
- [Claude 4 models (Opus, Sonnet, Haiku): which for which job](https://theaiarchitects.com/blog/claude-4-models): Opus 4.7, Sonnet 4.6, Haiku 4.5: three models, three jobs. The pricing crossover points, version numbering explained, and the default setup I use in Claude Code daily.
- [Karpathy's CLAUDE.md: 4 Rules That Fix Claude Code](https://theaiarchitects.com/blog/karpathy-claude-md-rules): Andrej Karpathy's CLAUDE.md is a 4-rule behavioral file that stops Claude Code from over-engineering. Here's what each rule does, plus 8 more rules from six weeks of testing that cut mistake rates from 41% to 3%.
- [How to Install Claude Code on Mac, Windows, Linux + WSL](https://theaiarchitects.com/blog/how-to-install-claude-code): Step-by-step Claude Code install guide for Mac, Windows, Linux, and WSL. Exact commands, prerequisites, troubleshooting, update and uninstall paths.
- [Claude Code Just Got 10x More Powerful: 10 New Features](https://theaiarchitects.com/blog/claude-code-10x-more-powerful): 10 new Claude Code features that change how I build day-to-day: insights reports, effort levels, remote control, batch, simplify, hooks, agent teams.
- [How to Use Claude Code: The 60-Minute Beginner Guide](https://theaiarchitects.com/blog/how-to-use-claude-code): How to use Claude Code in 60 minutes: install it, write CLAUDE.md, build a slash command, add a skill, run subagents in parallel, deploy to Vercel.
- [Is n8n Dead in 2026? My Honest Verdict After 8 Years](https://theaiarchitects.com/blog/is-n8n-dead-in-2026): Is n8n dead in 2026? My honest take after 8 years in automation. Why n8n still beats Claude Code for production work, plus a real student case study.
- [OpenClaw: 95% Cheaper Than Claude Code (Real Setup)](https://theaiarchitects.com/blog/openclaw-95-percent-cheaper-than-claude): OpenClaw setup that cuts your Claude Code bill by 95%. Open Router, model routing, heartbeat tuning, QMD, and the exact config I use.
- [Claude Code Subagents vs Skills: When to Use Each](https://theaiarchitects.com/blog/claude-code-subagents-vs-skills): Claude Code subagents vs skills, compared side by side. Decision tree, 5 production subagents I run daily, plus YAML frontmatter to copy in 2026.
- [Claude Code vs Cursor: An Honest Comparison](https://theaiarchitects.com/blog/claude-code-vs-cursor): Claude Code vs Cursor, compared after building 12 real projects in both tools. Honest pros, cons, pricing, and a clear verdict on which to pick in 2026.
- [Claude Code Plan Mode: When and How to Use It in 2026](https://theaiarchitects.com/blog/claude-code-plan-mode): Claude Code plan mode explained: the Shift+Tab shortcut, /plan open command, four scenarios where it wins, and how to save a plan to a file.
- [Paperclip AI Review: How to Use It, Set It Up + Pricing](https://theaiarchitects.com/blog/paperclip-ai-review): Hands-on Paperclip AI review and setup tutorial. What it does, how to install it, pricing, alternatives, and whether it's worth the hype.
- [How to Succeed in AI Without Grinding 24/7](https://theaiarchitects.com/blog/succeed-in-ai-without-grinding): You don't need to grind 17-hour days to succeed in AI. The people winning are not the ones working the most hours. They are the ones using leverage.
- [Is Claude Code Free? What You Pay in 2026](https://theaiarchitects.com/blog/is-claude-code-free): Claude Code is not free. You need a Pro, Max, Team or API account. Here's what each tier costs in 2026 and the cheapest way to actually use it.
- [Claude Code Skills Explained: SKILL.md, Triggers, Sharing](https://theaiarchitects.com/blog/claude-code-skills): Claude Code skills explained: how SKILL.md works, how to trigger them, share them, plus 3 of my real production skills with verbatim frontmatter.
- [Claude Code Memory: CLAUDE.md, Auto Memory, and Path Rules](https://theaiarchitects.com/blog/claude-code-memory): How Claude Code remembers things between sessions. The four CLAUDE.md scopes, Auto Memory (v2.1.59+), and path-specific rules.
- [Claude Code Pricing Explained (2026 Pro vs Max vs API)](https://theaiarchitects.com/blog/claude-code-pricing): Claude Code pricing in plain English. Pro $20, Max 5x $100, Max 20x $200, plus API. What you actually get on each tier and which one I run daily.
- [Claude Code MCP: Setup, Scopes & The 4 Servers I Use](https://theaiarchitects.com/blog/claude-code-mcp): Claude Code MCP setup guide: install Playwright, GitHub, Postgres, and custom servers. Scope tradeoffs, .mcp.json config, OAuth, and remove commands.
- [Claude Code Hooks: 9 Production Hooks That Actually Work](https://theaiarchitects.com/blog/claude-code-hooks): Claude Code hooks tutorial: 9 production PreToolUse, PostToolUse, Stop and SessionStart hooks with real JSON config and runnable shell scripts.

## Optional
- [Full content](https://theaiarchitects.com/llms-full.txt): Concatenated markdown of all articles and case studies for single-shot ingestion.
- [Sitemap](https://theaiarchitects.com/sitemap.xml)