AI-321
Building AI Agent Factory + CCA-F (Anthropic)
The construction quarter. Build production-grade Agent Factories using the Claude Agent SDK and OpenAI Agents SDK. Master MCP server development, FastAPI integration, and RAG pipelines. At the end of this quarter, students also sit Anthropic's official Claude Certified Architect — Foundations (CCA-F) exam as a supplementary industry certification.
Mode
Live Online Classes
Zia Tutor AI
Zia Tutor AI is a personal learning agent built as a digital twin of Zia Khan. It teaches the Agent Factory curriculum, remembers where you stopped, continues across sessions and weeks, teaches in the sequence appropriate for you, and checks whether you understood the previous concept before moving on.
Its mission is to help you gain the expertise to build AI Workers and Digital FTEs, and to become a Forward Deployed Engineer.
Learn MoreDetails
The construction quarter. Build production-grade Agent Factories using the Claude Agent SDK and OpenAI Agents SDK. Master MCP server development, FastAPI integration, and RAG pipelines. Includes Anthropic's Claude Certified Architect — Foundations (CCA-F) as a supplementary certification — a proctored 60-question scenario-based exam (passing score 720/1000) covering Agentic Architecture & Orchestration (27%), Tool Design & MCP Integration (18%), Claude Code Configuration & Workflows (20%), Prompt Engineering & Structured Output (20%), and Context Management & Reliability (15%).
What You'll Learn
Module 1Agent SDKs
Claude Agent SDK as the primary framework; OpenAI Agents SDK as comparative framework; Claude API for direct integration
Module 2Model Context Protocol (MCP)
Building MCP servers and connectors, tool boundaries, resources, and prompts
Module 3FastAPI & RAG
Production API endpoints for agent systems; Retrieval-Augmented Generation grounding agents in organisational knowledge
Module 4Agent Factory Architecture
The Factory Layer + Edge Layer pattern; multi-agent orchestration and handoff patterns
Module 5CCA-F Exam Preparation
Anthropic Academy courses, scenario walkthroughs, and practice questions across all five CCA-F domains
Course Outcomes
Build custom agents with the Claude Agent SDK
Develop comparative agents using the OpenAI Agents SDK
Integrate the Claude API directly for custom workflows
Build MCP servers and connectors using the Model Context Protocol
Create production API endpoints with FastAPI
Implement Retrieval-Augmented Generation (RAG) to ground agents in organisational knowledge
Apply the Factory Layer + Edge Layer Agent Factory architecture
Orchestrate multi-agent systems with handoff patterns
Prepare for and pass the Anthropic CCA-F exam
Prerequisites
Note: These prerequisites provide essential knowledge for success in this course. If you haven't completed these courses, consider taking them first or reviewing the relevant materials.