Extended lessons

57 lessons across 12 categories
0 of 57 complete

Command Line

  1. SSH and tmux
  2. File Permissions and Ownership
  3. Dotfiles and Shell Config
  4. jq

Model Behavior

  1. Small Models and Distillation
  2. Pretraining and Post-Training
  3. Reading a Model Card

How Claude Code Works

  1. Claude Code Surfaces
  2. Configuration Diagnostics
  3. Model and Effort Configuration
  4. Background and Cloud Sessions
  5. Claude Code in Chrome

Customization

  1. Output Styles and Statusline
  2. Agent Teams
  3. Dynamic Workflows
  4. Testing Skills
  5. Publishing a Plugin

MCP

  1. MCP Authorization
  2. Deploying a Remote Server
  3. The MCP Registry
  4. MCP Apps
  5. Desktop Extensions and MCPB

Building on the API

  1. Files, PDFs, and Vision
  2. Context Editing and the Memory Tool
  3. Hooks and Subagents in the Agent SDK
  4. Managed Agents
  5. Rate Limits and Operations

Context and Retrieval

  1. Vector Stores
  2. GraphRAG
  3. Late Chunking
  4. Pruning Tool Results
  5. Progressive Disclosure

Orchestration

  1. Deep Research Architecture
  2. Durable Execution
  3. Agent-to-Agent Protocols
  4. Parallel Agents That Write
  5. Judge Panels and Debate
  6. Designing an Agent's Tool Set
    AI Engineer ยท 23 minVideo + articles

Evals and Observability

  1. OpenTelemetry for Agents
  2. Production Monitoring
  3. Evaluating RAG
  4. Evals in CI
  5. Eval Awareness and Contamination
  6. Eval Tooling
    AI Engineer ยท 26 minVideo + articles

Security

  1. Agents in CI/CD
  2. Red-Teaming Agents
  3. Incidents and CVEs
  4. OWASP LLM and Agentic Top 10
  5. Data Leakage to Providers

Deployment and Governance

  1. The EU AI Act
  2. Acceptable Use Policy Design
  3. Vendor Risk Review
  4. Shadow AI

Adoption

  1. Adoption in Professional Services
  2. Why Enablement Programs Fail
  3. Skill Atrophy and Verification
  4. Forward-Deployed Engineering