Loading...
Loading...
Frameworks hide the real engineering behind coding agents. Build your own Claude-code-style agent from scratch: tool loops, safe sandboxing, file editing, and context management, so you understand exactly what breaks in production and how to fix it.
Message a mentor about fit, prerequisites, or where to start. Replies come on WhatsApp, usually within a day.
Engineers are learning here from
Claude Code is the most capable AI coding agent available today. In this workshop, you reverse-engineer its architecture and build your own from scratch: the agent loop, tool design, context compaction, task management, multi-agent teams, and git worktree isolation. Each phase adds one real capability. By the end you have a production-grade agentic system.
Reverse-engineer how Claude Code works. Then build your own production AI coding agent from scratch.
What you'll ship
What you'll learn
Curriculum
The agent loop
Build the core loop that powers every AI coding agent. Start with 17 lines, then add bash execution, error handling, and dual-mode operation.
Tool design
Move beyond bash-only. Design read, write, and edit tools with path sandboxing. Learn why the model IS the agent.
Planning and constraints
Plans get buried in conversation history. Add a TodoManager with constraints that keep the agent focused.
Subagents and skills
Isolate context with subagents. Externalize knowledge with skills. Optimize costs with cache-preserving injection.
Memory management
Build three-layer context compaction and file-based task graphs that survive compression.
Parallelism
Background execution with daemon threads, notification draining, and persistent teammates.
Team coordination
JSONL message buses, shutdown and approval protocols, WORK/IDLE lifecycle, and identity preservation.
Worktree isolation
The final module. Git worktrees for directory-level isolation. Tasks as control plane, worktrees as execution plane.
Who it's for
You use agent frameworks but could not build one from scratch. That gap is becoming a liability.
You want to understand how tools like Claude Code, Cursor, and Copilot actually work under the hood.
Your team ships AI features but nobody understands the agent architecture. You need someone who can debug and extend it.
FAQ
No. You build your own from scratch. The workshop teaches the patterns, not the product.
Any provider that supports function calling. LiteLLM handles OpenAI, Anthropic, Google AI Studio (free tier), and more.
Yes. This workshop assumes you understand tool calling and agent loops. Building AI Agents covers those foundations.
About 14 hours. Most people finish in 3-4 sessions over a week. Each module is self-contained.
Pricing
One subscription unlocks every paid course and workshop replay. Pick yearly or monthly.
Unlock with Pro
You save 47% with regional pricing
Billed annually. Cancel anytime.
Still deciding? Ask Param a question
Reverse-engineer how Claude Code works. Then build your own production AI coding agent from scratch.
Learn to Build your own Coding Agent (Claude Code)
From $16/mo with Pro