🏢AI Workspace
Build a unified workspace where AI agents work across your team's repositories.
What you'll learn
- Build a meta-workspace for multiple repositories
- Design an agent and skills system for your team
- Implement pipelines for automated development
- Connect Linear, Slack, Kubernetes and other tools via MCP
- Set up cross-repo architecture with parallel development
Who this is for
Tech leads, engineering managers and senior developers who want to bring AI into their team's entire development process.
Prerequisites
Syllabus
The Meta-Workspace Pattern
Your team has 5-20+ repos but AI tools only see one at a time. The meta-workspace pattern solves this by aggregating everything into a single context.
Designing Your Agent System
Architects plan, developers implement, runners execute, reviewers check. Learn how to design a system of specialized AI agents for your team.
Skills and Development Pipelines
Skills are orchestrated multi-agent workflows. Learn how to build repeatable pipelines that take a feature from plan to reviewed code.
Cross-Repo Architecture
Real features touch multiple repos. Learn how the Solution Architect agent orchestrates parallel development across your entire stack.
Project Tracking with AI
Track features across repos with file-based project management. Session resumption, activity logs, and integration with Linear and Jira.
Infrastructure as Code with AI
Terraform pipelines, Kubernetes manifest generation, GitHub Actions workflows — all orchestrated by specialized infrastructure agents.
Connecting Your Toolchain via MCP
Model Context Protocol turns your Linear, Slack, Kubernetes, and Terraform into tools that AI agents can use directly. Here is how to set it up.
Scaling and Team Onboarding
From solo setup to team-wide adoption. Setup scripts, workspace rules, auto-generated IDE configs, and measuring the impact of your AI workspace.