DEV Community: Wolfgang Katz

500+ AI Prompts, 50+ Automation Recipes, and 4 More Products — Dropped Tonight

Wolfgang Katz — Thu, 02 Apr 2026 09:24:07 +0000

500+ AI Prompts, 50+ Automation Recipes, and 4 More Digital Products — All Dropped Tonight

I spent the last 2 weeks running a 24/7 AI agent from a Mac Mini. Along the way, I documented everything — every prompt that worked, every automation I built, every personality config I tested.

Tonight I turned all of that into 6 digital products:

1. The AI Prompt Playbook ($19.99)

500+ copy-paste prompts organized by category:

Business & Email (75 prompts)
Sales & Marketing (75 prompts)
Social Media (75 prompts)
Content & SEO (75 prompts)
Coding & Tech (50 prompts)
Strategy & Analysis (50 prompts)
Productivity & Personal (50 prompts)
Advanced Prompt Stacking (50 prompts)

Each prompt includes variables to customize, expected output, and pro tips.

2. The AI Automation Cookbook ($29.99)

50+ ready-made automation recipes for email, social media, business ops, content, research, e-commerce, and advanced multi-step workflows. Each recipe has step-by-step instructions with specific tools (n8n, Zapier, Make, ChatGPT, Claude).

3. The SOUL Pack Studio ($24.99)

50 complete AI agent personality templates — from Executive Assistant to Code Reviewer to Real Estate Agent. Each includes a full SOUL.md, AGENTS.md rules, HEARTBEAT.md config, and setup tips.

4. The Agent Monetization Guide ($39.99)

How to actually make money with AI agents. Freelancing, consulting, digital products, agency model, and 6 specific niches with pricing frameworks and templates.

5. The AI Voice & Video Toolkit ($19.99)

How to create content with AI — TTS setup guide, 30 video scripts, faceless content workflows, podcast templates, and tool comparisons.

6. The Weekly Project Blueprint ($29.99)

A 5-day framework for building and launching a new project every week. 12 complete project blueprints with templates, checklists, and marketing calendars.

All 6 are also included in the Full Stack Bundle at bootstrapyouragent.com.

Built them all in one night using AI sub-agents running in parallel. The irony of using AI to build products about AI is not lost on me.

Questions? Drop them below.

500 AI Prompts That Actually Work (10 Free Samples Inside)

Wolfgang Katz — Thu, 02 Apr 2026 08:22:49 +0000

500 AI Prompts That Actually Work — Organized by Use Case

I got tired of generic AI prompt lists. You know the ones — 'Write me a blog post about X' or 'Summarize this text.' Useless.

So I compiled 500+ prompts that I actually use to run my business. Prompts with variables you fill in, expected outputs, and pro tips for getting better results.

Here are 10 free samples from the collection:

Business & Email

Cold Outreach That Gets Replies:

Write a cold outreach email to [COMPANY] about [YOUR SERVICE]. 
Their company does [WHAT THEY DO]. Reference their recent [ACHIEVEMENT/NEWS]. 
Keep it under 100 words. No fluff. End with a specific, 
low-commitment ask (not 'jump on a call').

What you get: A personalized email that shows you did your homework.

Client Follow-Up After No Response:

Write a follow-up email to [NAME] at [COMPANY]. My first email was about [TOPIC]. 
It's been [TIME] since I sent it. Add one new piece of value 
(a relevant article, stat, or insight about their industry). 
Keep it shorter than the original. No guilt-tripping.

Sales & Marketing

Landing Page Headline Generator:

Generate 10 landing page headlines for [PRODUCT]. 
Target audience: [WHO]. Main benefit: [BENEFIT]. 
Main pain point: [PAIN]. Use these frameworks:
- How to [benefit] without [pain]
- [Number] ways to [benefit]
- The [adjective] way to [benefit]
- Stop [pain]. Start [benefit].
Include a subheadline for each.

Product Description That Sells:

Write a product description for [PRODUCT NAME]. 
Price: [PRICE]. Target buyer: [WHO]. 
Key features: [LIST 3-5 FEATURES].
Format: Hook sentence, 3 bullet points (feature -> benefit), 
social proof line, clear CTA.
Keep it under 150 words. Make it scannable.

Content & SEO

Blog Post Outline That Ranks:

Create a detailed blog post outline for the keyword '[TARGET KEYWORD]'. 
Include: H1 title (with keyword), 5-7 H2 sections, 
2-3 H3 subsections under each H2, 
a 'People Also Ask' section with 4 questions and answers.
Target word count: [NUMBER]. Include internal link suggestions for [YOUR SITE].

Coding & Tech

Debug Any Error:

I'm getting this error: [PASTE ERROR]
Language: [LANGUAGE]
Framework: [FRAMEWORK]
What I was trying to do: [CONTEXT]
What I've already tried: [LIST]
Explain what's causing it, give me the fix, 
and tell me how to prevent it in the future.

Strategy

Competitor Analysis in 60 Seconds:

Analyze [COMPETITOR NAME] as a competitor to my business [YOUR BUSINESS]. 
Compare: pricing, target audience, unique selling proposition, 
weaknesses I can exploit, and what they do better than me.
Format as a table with columns: Category | Them | Us | Opportunity.

These are 7 out of 500+. The full collection covers:

Business & Email (75 prompts)
Sales & Marketing (75 prompts)
Social Media (75 prompts)
Content & SEO (75 prompts)
Coding & Tech (50 prompts)
Strategy & Analysis (50 prompts)
Productivity (50 prompts)
Advanced Prompt Stacking (50 prompts)

Every prompt includes [VARIABLES] to customize, what to expect back, and a pro tip.

Full collection: The AI Prompt Playbook

I Built a 24/7 AI Agent That Runs My Business From a Mac Mini — Here's Exactly How

Wolfgang Katz — Thu, 02 Apr 2026 03:57:08 +0000

I Built a 24/7 AI Agent That Runs My Business From a Mac Mini — Here's Exactly How

Two weeks ago, I set up an AI agent on a Mac Mini sitting in my closet. It now runs 24/7, handling tasks that used to eat up hours of my day.

This isn't a chatbot. It's an operator — a persistent system with memory, tools, and autonomy that works while I sleep.

Here's exactly what it does, how I built it, and what I learned.

What My Agent Handles

Email triage — Monitors Gmail, flags urgent messages, drafts responses
Calendar management — Tracks upcoming events, sends me reminders
Website monitoring — Uptime checks on 5 sites every 4 hours
Competitor analysis — Weekly automated scans of competitor pricing and products
WooCommerce monitoring — Order tracking and inventory alerts
Social media scheduling — Posts to Bluesky on a daily cron
Cron jobs — Recurring tasks that run without me touching anything

The Stack

Hardware: Mac Mini M4, sleep disabled, always on. Sits in a closet connected to power and ethernet.

Software:

OpenClaw — The agent framework (Node.js, runs as a LaunchAgent)
Anthropic Claude Opus — Primary AI model
OpenAI GPT-5.2 + GPT-4.1 — Failover models (auto-rotates if Anthropic goes down)
n8n — Workflow automation for complex multi-step processes
Telegram — Bot interface so I can chat with my agent from my phone

5 Hard-Won Lessons

1. Model Failover Is Non-Negotiable

On day 3, Anthropic's API went down at midnight. My agent sat there retrying the same dead endpoint for 30 minutes. Dead silence. No responses.

The fix: Set up a failover chain across multiple providers:

Primary: Claude Opus (Anthropic)
Fallback 1: Claude Sonnet (Anthropic — lighter model, same provider)
Fallback 2: GPT-5.2 (OpenAI — different provider entirely)
Fallback 3: GPT-4.1 (OpenAI — last resort)

If one provider goes down, the system auto-rotates to the next model in seconds. Two providers minimum. Four models deep.

2. OAuth > API Keys (If You Already Pay for a Subscription)

I was burning through API credits until I realized — I already pay for Claude Max and ChatGPT Plus. Both support OAuth/subscription auth, which lets your agent use those subscriptions instead of per-token API billing.

Same models. Already paid for. Monthly cost dropped to basically $0.

3. Sub-Agents Beat One Mega-Agent

Don't try to make one agent do everything. My main agent delegates:

Coding tasks → Claude Code (sub-agent)
Research → Lighter model (saves cost)
Complex decisions → Opus (the heavy thinker)

Each sub-agent is specialized and disposable. The main agent orchestrates.

4. Heartbeats Keep It Alive

Instead of waiting for me to ask "check my email," my agent proactively monitors on a schedule:

Email checks every hour
Site uptime every 4 hours
Calendar review every morning
Competitor scan weekly

Heartbeat = periodic pulse check. If nothing needs attention, it stays quiet. If something's urgent, it pings me on Telegram.

5. Memory Files > Conversation History

AI agents forget everything between sessions. Every restart, every crash — blank slate.

The fix: File-based memory.

memory/2026-04-01.md — Daily notes (raw log of what happened)
MEMORY.md — Curated long-term memory (decisions, preferences, lessons)

On startup, the agent reads its memory files and picks up where it left off. It knows what happened yesterday, what's pending, and what matters.

The Cost

Item	Cost
Mac Mini	Already owned
Claude Max subscription	$100/mo (already paying)
ChatGPT Plus	$20/mo (already paying)
OpenClaw	Free / open source
Additional API costs	~$0 (using subscription auth)

Total additional cost: $0/month

Getting Started

If this interests you, I wrote a complete playbook that covers the full setup — from installation to configuring models, memory, heartbeats, sub-agents, and everything I learned in the first two weeks.

👉 Bootstrap Your Agent

It covers:

Installation and configuration
Model selection and failover setup
Memory system design
Heartbeat and cron automation
Sub-agent architecture
Real-world use cases

Questions?

Happy to answer anything about the setup. Drop a comment below or find me on Bluesky.