Automation Playbook: Getting Started
Your quick-start guide to picking a use case, installing skills, and running your first automation in under 15 minutes.
What You Will Get
This playbook is a collection of ready-made recipes for AI automations you can run on RunTheAgent. Each use case is a complete walkthrough: what problem it solves, how to set it up step by step, and tips to get the most out of it. You do not need to read every article. Pick the one that matches your situation and follow along.
Every recipe assumes you have an OpenClaw agent deployed on RunTheAgent and a messaging app connected. The setup for each use case takes between 5 and 15 minutes. Most of the work is telling your agent what to do in plain English and installing one or two skills. No coding, no complex configuration.
The playbook covers four categories: Content & Marketing for publishing workflows, Sales & Outreach for lead generation, Productivity & Ops for daily routines, and Research & Intelligence for market monitoring. Start with whichever category sounds most useful to you right now.
What You Need
Three things to have ready before you follow any recipe.
RunTheAgent Account with Deployed OpenClaw
Sign up at runtheagent.com and deploy an OpenClaw agent. This takes about two minutes. Your agent is the engine that runs every automation in this playbook.
AI Provider API Key
You need an API key from an AI provider like OpenAI, Anthropic, or Google. Paste it into your agent settings so OpenClaw can call the model when processing tasks.
Messaging App Connected
Connect at least one messaging channel — Telegram, Slack, or WhatsApp. This is how you talk to your agent and how it delivers results back to you.
How Skills Work
Skills give your agent new abilities. Here is how to install them.
Find the Skill You Need
Each recipe lists the skills it requires, like tavily-search for web lookups or blogwatcher for RSS monitoring. You install them by messaging your agent directly.
Message Your Agent to Install
Send a message like: "Install the tavily-search skill." Your agent will confirm once the skill is active. Some skills need an API key — the agent will tell you if so.
Verify the Skill Is Working
Ask your agent to run a quick test. For example, after installing tavily-search, say: "Search for the latest news about electric vehicles." If you get results, the skill is live.
Add More Skills as Needed
You can install multiple skills on the same agent. They stack — an agent with tavily-search, summarize, and blogwatcher can research, condense, and monitor all in one workflow.
Setting Up Scheduled Tasks
Cron jobs let your agent run automations on a schedule without you lifting a finger.
Decide on Frequency
Most automations run daily (morning briefings, news digests) or weekly (patent scans, market reports). Pick the cadence that matches how often you need fresh data.
Create the Cron Job
In your RunTheAgent dashboard, go to your agent's settings and add a scheduled task. Set the time, frequency, and the prompt your agent should execute — for example: "Generate my morning briefing and send it to Telegram."
Test It Once Manually
Before relying on the schedule, run the prompt yourself by messaging the agent. Make sure the output looks right and lands in the correct channel.
Adjust Timing After a Few Runs
After a few scheduled runs, check whether the delivery time works for you. Move it earlier if you want results before your morning coffee, or later if you need west-coast market data.
Choose Your First Automation
Content & Marketing
You publish regularly and want to automate content creation, repurposing, or social media posting. Start with the daily social media content machine or blog post drafting workflows.
Sales & Outreach
You do outbound sales or partnership outreach and want personalized messages at scale. Start with the cold outreach drafter or LinkedIn engagement responder.
Productivity & Ops
You want a smarter daily routine with briefings, task summaries, and meeting prep handled automatically. Start with the daily morning briefing.
Research & Intelligence
You need market data, competitive intel, or patent monitoring without hiring a research team. Start with the market research report generator.
Frequently Asked Questions
Related Pages
Ready to get started?
Deploy your own OpenClaw instance in under 60 seconds. No VPS, no Docker, no SSH. Just your personal AI assistant, ready to work.
Starting at $24.50/mo. Everything included. 3-day money-back guarantee.
