Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Pi
- Understanding Pi’s philosophy of minimalism and control
- Comparison with tools like Claude Code, Codex CLI, and Cursor
- Overview of the four built-in tools: read, write, edit, and bash
- When to choose Pi over more heavyweight agents
Installation and Setup
- Installing Pi via npm and other package managers
- Configuring API keys for 15+ supported providers
- Setting up working directories and context files
- Running Pi in local and Docker environments
Core Terminal Workflows
- Generating code from simple prompts
- Precise file reading and editing
- Safely executing bash commands within the agent
- Managing session state and performing context resets
Building Custom Skills
- Understanding the TypeScript skill API
- Writing custom read, write, and edit operations
- Hooking into bash execution for specialized workflows
- Isolated testing and debugging of skills
Prompt Templates and Themes
- Adapting system prompts for various languages and frameworks
- Creating reusable prompt templates to ensure team consistency
- Packaging themes as shareable modules
Extending Pi with npm Packages
- Bundling skills as pi packages
- Publishing to npm and Git repositories
- Installing community-contributed packages
- Managing dependency versions and compatibility
Provider Flexibility
- Switching between Anthropic, OpenAI, Google, and other backend providers
- Optimizing for cost, speed, and quality based on task requirements
- Running entirely local models for sensitive code handling
Practical Use Cases
- Automated testing and test generation workflows
- Refactoring legacy code using custom skill chains
- Documentation generation and maintenance
- CI integration with minimal agent overhead
Security and Control
- Understanding the 300-word system prompt boundary
- Manual approval requirements for write operations
- Sandboxing bash execution in untrusted environments
- Audit logging of all agent actions
Summary and Next Steps
- Recap of principles regarding minimalism, control, and extensibility
- Community resources and contribution guidelines
- Advanced topics for experienced Pi users
Requirements
- Experience with terminal-based development and bash commands
- Fundamental knowledge of TypeScript or JavaScript
- Familiarity with npm package management
Target Audience
- Developers seeking a lightweight, hackable coding agent
- Senior engineers desiring complete control over agent internals
- Teams adopting terminal-first development methodologies
14 Hours
