Opening lesson…

AEAgentic Engineer

LeaderboardWhat's NewSign in

Agentic Engineer — A Definitive Book and Ecosystem for the Agent Era
Claude Code and OpenCode: A Crash Course
Agentic Engineering Fundamentals: A 45-Minute Crash Course
Give Your AI Agent a Nervous System: A 90-Minute Crash Course
AI Identity: Human Sign-In and Agent Access
- Founding an AI-Native Startup
The AI-Native Transformation: From Adoption to Advantage
The Agent Is the Operating Layer
AI Prompting in 2026: A Crash Course
AI Workers
Build AI Agents with the OpenAI Agents SDK: A 90-Minute Crash Course
- I: Foundations
- II: Office of the CFO
- V; Product & Value Chain
Courses & Certifications
Cheatsheets
Choosing Agentic Architectures: A Decision-Driven Crash Course
Code You Never Write: A Crash Course
Connector-Native Apps: A Remote MCP Server Whose Customer Is an AI
Cowork and OpenWork: A 90-Minute Crash Course
Deploy Your Agent Harness to the Cloud: A Multi-Track Crash Course
Building a Digital FTE: A 4-Hour Crash Course
A Self-Expanding Workforce with Paperclip: A 90-Minute Crash Course
Eval-Driven Development for AI Employees: A Multi-Track Crash Course
The AI-Native Finance Catalog
Foundations: Start in the Browser
From One-Off to Worker: The Handoff to Manufacturing
General Agents
Getting Started: Crash Courses
Glossary
Hermes with General Agents: A 90-Minute Crash Course
How to Think in the AI Era: Crash Course
Human-Agent Teams: The Operating Model for Your Workforce
Build Your Identic AI Chief of Staff: A 4-Hour Crash Course
Is This an Agent Problem? A Crash Course
Loop Engineering: A Crash Course
Markdown In, HTML Out: A Crash Course
The Marketing Catalog
Mode 1 — Problem-Solving
Mode 2 — Manufacturing
OpenClaw with General Agents: A 90-Minute Crash Course
Payment-Enabled Agents: ACP, AP2, x402, and MPP in Production
Personal Agent Harnesses
Plugins for Coding Agents: Extend Claude Code and OpenCode
Give Your AI Searchable Context: RAG on Postgres with pgvector — A Crash Course
Preface: The Right Side of the Line
Problem Solving with General Agents: A 90-Minute Crash Course
- Phase 9 — Capstone
- Phase 8 — Production Systems
Python in the AI Era: A Crash Course
The Roles This Book Trains
The Sales Catalog
Project Labs
Skills & Connectors: Teach AI Once, Connect It to Your Apps
Spec-Driven Development: A Crash Course
- Agentic Engineer Thesis: Plain-English Version
What AI Actually Is: A Crash Course
What's New
Which AI Employees To Use in 2026?
Why AI Is Non-Negotiable
The AI Worker Catalog
Building a Workforce with Paperclip: A 90-Minute Crash Course

Opening lesson…

Designing Eval Datasets — Agentic Engineer

DocsDesigning Eval Datasets

1 min read

Designing Eval Datasets

Designing Eval Datasets

Log in to access this lesson.

Log in to continue Browse open lessons