Skip to main content
New: the Agentic AI Academy, 5 courses on running AI agents in production.Start free →
beginner

OpenClaw: Your First AI Agent

Deploy OpenClaw locally or on a small VPS, add real tools, create one reusable automation, and apply essential security guardrails. You'll leave with a working 'Ops Assistant' that generates a Daily Brief, creates an Action Queue, and does it all safely.

7 lessons58m

What you'll learn

  • Install and run OpenClaw (local Docker or VPS)
  • Configure identity/memory and a sane default agent profile
  • Connect 2 real tools (web/search + one work integration like email/Slack)
  • Build one end-to-end automation (Daily Brief + Action Queue)
  • Apply essential security: secrets, allowlists, prompt-injection safety check
  • Create a simple ops routine: logs, updates, backup/restore

What it looks like in the lab

sandbox — bash
$ openclaw init my-agent
✓ Created agent workspace
$ openclaw run
Agent connected to gateway...
Listening for messages on #general
$ openclaw skill add weather
✓ Installed skill: weather (v1.2.0)

Real terminal output from the hands-on lab environment

Who this is for

  • • Developers moving into DevOps or infrastructure roles
  • • System administrators learning modern tooling
  • • CS students building practical skills

Prerequisites

  • • Basic terminal comfort (copy/paste commands)
  • • A machine with Docker or a small Linux VM
  • • Optional: API keys for your chosen tools (we provide a no-keys fallback path)

Course content

7 lessons, 58m of video

1

4 min

What we're building (Daily Brief + Action Queue). Mental model: agent loop, memory, tools, skills, guardrails. Minimum viable autonomy — safe-by-default.

2
Fast Deploy: Docker Local or Ubuntu VM on Azure

10 min

Option A: Docker run (fastest). Option B: small Ubuntu VM (same config, different ports). Smoke test: agent replies + health check.

3
AI Models Troubleshooting

5 min

Configuring LLM providers, testing model connectivity, and common troubleshooting steps for API keys and rate limits.

4
Identity + Memory That Doesn't Rot

8 min

Define role, tone, boundaries (what I can/can't do). Create 2 memory files: about_me.md (user/org context) and operating_rules.md (safety + permissions). Quick test prompt to validate memory usage.

5
Connect Tools

10 min

Tool 1: Web/search (or a stubbed offline search fallback). Tool 2: One of email draft, Slack/Telegram post, or local command tool with strict allowlist. Principle: least privilege + separate credentials.

6
Build the Automation: Daily Brief + Action Queue

15 min

Define the workflow contract. Build the Daily Brief (status + top priorities). Create the Action Queue (next steps). Optionally post to chat or draft an email. Run it safely with guardrails + minimal permissions.

7
Operate It: Logs, Backups, Updates & Safe Iteration

8 min

Day-2 operations: viewing logs, backing up agent data, updating OpenClaw, and safely iterating on workflows and memory.

Get started

Start Free Lesson

First lesson is always free — no signup required

This course includes

7 hands-on lessons
Beginner level
58m total

Every lesson, with Pro

All 7 lessons of this course and every other course.

$25 a month billed yearly, or $29 month to month

Until 30 November: $210 for the first year, or $14.50 for the first month, with code LAUNCH.

See plans →

Your instructor

Luca Berton

Founder and CEO, Open Empower. About the author

More in AI Agents

All courses in this track

Claude Code Masterclass: Ship Real Code with AI

Stop treating AI like a magic autocomplete and start using it like a sharp junior engineer who sits next to you — one you direct, review, and hold accountable. In 10 hands-on modules you'll master the Plan → Implement → Test → Review → Commit loop and use it to ship real, tested code with Claude Code: Best-of-N, honest test suites, safe git workflows, multimodal prompts, refactoring & docs, reusable skills, the GitHub MCP server, lifecycle hooks, and a production-readiness checklist. You stay the engineer of record — Claude proposes, you decide what ships.

Intermediate · 10 lessons · 5 h

Preview free lesson

MLflow on Kubernetes: ML at Scale

Build scalable MLOps with MLflow, KServe, Docker, and Kubernetes. Automate deployments, monitor models, and workflows. Learn to deploy ML models to Kubernetes at scale, implement CI/CD pipelines, track experiments, perform hyperparameter tuning, and build production-ready ML services.

Intermediate · 15 lessons · 1 h 28 min

Preview free lesson

Claude Code Bootcamp: Build Real-World Software with AI

The complete Claude Code Bootcamp by Luca Berton — thirteen hands-on modules that teach you to ship real, tested software with Claude Code. You stay the engineer of record: Claude proposes, you review and merge. Master the Plan → Implement → Test → Review → Commit loop, then apply it across GCOE prompting, CLAUDE.md brain files, Best-of-N, testing & self-review, safe Git workflows, multimodal screenshot-to-UI, constrained refactoring & docs, reusable Skills, the GitHub MCP server, lifecycle Hooks, and a five-axis production-readiness review. Includes a ten-skill reusable library and a 20-question knowledge quiz.

Intermediate · 15 lessons · 8 h

Preview free lesson