AI & Automation · Advanced
Agentic AI Engineering
Design AI agents that plan, call tools and finish real business tasks — with Python, APIs and vector search.
Agentic AI is the difference between a chatbot that answers and a system that acts. In this track you build agents that read a brief, choose tools, browse, write to a database and report back — the exact pattern behind modern automation products.
You will work with the OpenAI and Anthropic APIs, function calling, embeddings, vector databases and workflow orchestration, then ship two portfolio projects: a research agent and a customer-support agent connected to a knowledge base.
What you will be able to do
- ["Build multi-step agents with tool calling and memory", "Design retrieval pipelines with embeddings and vector search", "Evaluate, log and guard agent output safely", "Deploy an agent to a live endpoint and monitor cost"]
Course outline
| Module | What is covered |
|---|---|
| [{"title": "Foundations", "topics": "LLM APIs, tokens, temperature, structured output, cost control"}, {"title": "Tool use", "topics": "Function calling, JSON schemas, retries, error handling"}, {"title": "Retrieval", "topics": "Chunking, embeddings, pgvector, evaluation of answers"}, {"title": "Production agents", "topics": "Orchestration, guardrails, logging, deployment, billing"}] |