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 core philosophy of minimalism and control
- Comparing Pi with tools like Claude Code, Codex CLI, and Cursor
- Overview of the four built-in tools: read, write, edit, and bash
- Scenarios where choosing Pi is advantageous over heavier agents
Installation and Setup
- Installing Pi via npm and other package managers
- Configuring API keys for support of 15+ providers
- Setting up working directories and context files
- Running Pi in local environments as well as Docker containers
Core Terminal Workflows
- Generating code from simple text prompts
- Precisely reading and editing files
- Safely executing bash commands within the agent
- Managing session state and performing context resets
Building Custom Skills
- Understanding the TypeScript skill API structure
- Writing custom operations for read, write, and edit functions
- Integrating bash execution hooks for specialized workflows
- Isolated testing and debugging of skills
Prompt Templates and Themes
- Customizing 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 into pi packages
- Publishing packages to npm and Git repositories
- Installing community-contributed packages
- Managing dependency versions and ensuring compatibility
Provider Flexibility
- Switching between Anthropic, OpenAI, Google, and other backends
- Optimizing for cost, speed, and quality based on specific tasks
- Running local models entirely offline for sensitive code handling
Practical Use Cases
- Automated testing and test generation workflows
- Refactoring legacy code using custom skill chains
- Documentation generation and ongoing maintenance
- Seamless CI integration with minimal agent overhead
Security and Control
- Understanding the limitations of the 300-word system prompt boundary
- Requiring manual approval for all write operations
- Sandboxing bash execution in untrusted environments
- Maintaining audit logs of all agent actions
Summary and Next Steps
- Recap of key principles: minimalism, control, and extensibility
- Accessing community resources and understanding contribution guidelines
- Exploring advanced topics for experienced Pi users
Requirements
- Experience with terminal-based development and bash scripting
- Foundational knowledge of TypeScript or JavaScript
- Familiarity with npm package management
Target Audience
- Developers looking for a lightweight, customizable coding agent
- Senior engineers seeking full control over agent internals
- Teams embracing terminal-first development methodologies
14 Hours