Programme outline
Learning objectives
By the end of this course, participants will be able to:
- Explain the OpenClaw agent loop and describe how its components interact at the system level.
- Install, configure, and run OpenClaw using both cloud-based and local Large Language Model (LLM) providers.
- Connect OpenClaw to messaging platforms and manage agents remotely.
- Configure the heartbeat scheduler to enable autonomous and continuous agent operation.
- Develop custom skills that integrate with external Application Programming Interfaces (APIs) and services.
- Design multi-step automation pipelines and agent-driven workflows.
- Apply security best practices, including prompt injection defence, skill sandboxing, and secure configuration defaults.
- Assess when OpenClaw is an appropriate solution compared with other agent frameworks.
Day 1
- Introduction to Artificial Intelligence (AI) Agents
- OpenClaw Architecture Overview
- Installing and Configuring OpenClaw
- Large Language Model (LLM) Integration and Context Management
Day 2
- External Interface Integration for Agent Input
- Building Custom Skills for OpenClaw Agents
- Heartbeat System and Autonomous Workflows
- Security, Safety, and Responsible Deployment of AI Agents
- Assessment
Assessment
- In-class laboratory assignment