AvailableNot started
AI Agent Builder
From Claude fundamentals through context engineering, memory and knowledge, workflow design, MCP trusted tools, and planning/reasoning, to multi-agent collaboration and a reliable agent harness: the complete agent-builder path.
12 courses · Estimated effort: 117 hours
Who this is for
- Developers and advanced learners who want to progress from using AI to building AI agents
- Technical staff responsible for designing repeatable, trustworthy automation
Outcomes
- Design an agent’s memory, knowledge, and skills architecture
- Let AI safely connect to tools and trusted data via MCP
- Design multi-agent collaboration and a reliability-focused agent harness
Competencies developed
- AI Literacy
- Prompt & Context Design
- Verification & Evidence
- Responsible AI & Data Safety
- AI Application & Use-Case Design
- AI Task Judgment
- Instruction Design
- Context & Source Awareness
- Output Verification
- Human-AI-Human Workflow
- Responsible Use
- Prompt vs. Context Diagnosis
- Context Taxonomy
- Context Quality Assessment (RAFS)
- Context Strategy Selection
- Context Failure Diagnosis
- Context Canvas Design
- Agentic AI
- Context vs. Memory Distinction
- Memory Lifecycle Design
- RAG & Retrieval Decisions
- Chunking & Metadata Design
- Knowledge Architecture & Agent Skills
- Context Optimization & Failure Diagnosis
- Workflow Design
- Prompt, Workflow & Agent Diagnosis
- Task Decomposition & Execution Steps
- Workflow Pattern Selection
- Decision Spectrum Classification
- Basic Agent Loop
- Verification Method Selection
- Human-in-the-Loop Design
- Agentic AI Workflow Canvas Design
- MCP Architecture & Roles
- Tool Discovery & Tool Calls
- Grounding & Provenance
- Human Verification & Failing Visibly
- Data Classification, Risk & Confirmation
- Workflow vs. Adaptive Agent Diagnosis
- Goal Decomposition & Planning Fundamentals
- ReAct: Reasoning + Acting
- Search, Trees & MCTS for Agent Decisions
- Evaluation & Verification
- Self-Reflection
- Adaptive Planning & Re-planning
- Agent Planning & Reasoning Canvas Design
- Single-Agent vs. Multi-Agent Decision
- Agent Role & Responsibility Design
- Task Allocation, Delegation & Handoff
- Agent Communication & Message Contracts
- Shared Context, Memory & Coordination
- Orchestration Pattern Selection
- Conflict Resolution, Human Oversight & Evaluation
- Multi-Agent Architecture Design
- Harness vs. Agent Logic
- State, Loops & State Machines
- Checkpointing & Durable Execution
- Verification & Human-in-the-Loop
- Failure Classification & Recovery
- Context Compaction for Long-Running Agents
- Observability & Reliability
- Agent Harness & Reliability Canvas Design
- Industry AI Project Charter Design
- Industry AI PoV Prototype & Evaluation Design
- Enterprise AI Readiness Review
- Enterprise AI Pilot Execution & Evaluation
Required before starting
None
Recommended before starting
- AD 101 · AI Use Case Discovery
Course sequence
- 1.AI 101 Claude AI Workforce Fundamentals
- 2.AI 102 Context Engineering: What Should AI Know?
- 3.AI 103 Agentic AI Memory, Knowledge & Skills
- 4.AI 104 Agentic AI Workflow & Execution Design
- 5.AI 201 Model Context Protocol: Connecting AI to Tools & Trusted Data
- 6.AI 202 Agentic AI Planning & Reasoning
- 7.AI 301 Multi-Agent Collaboration & Orchestration
- 8.AI 302 Agent Harness Engineering & Reliable Automation
- 9.IL 101 IL 101 | Industry AI Project & Value Design
- 10.IL 201 IL 201 | Industry AI Proof-of-Value Co-creation Lab
- 11.IL 202 IL 202 | Enterprise AI Data, Governance & Integration Readiness
- 12.IL 301 IL 301 | Enterprise AI Pilot & Adoption Lab
Next step
AI 101 · Claude AI Workforce Fundamentals