FlexStack: Python AI Principles 3 - Agentic AI Development

  • Overview
  • Course Content
  • Requirements & Materials
Overview

FlexStack: Python AI Principles 3 - Agentic AI Development

Course Description

The third and final course in the FlexStack: Python AI Principles Certificate equips professionals with the skills to design, implement, and deploy a production-ready assistant using an open, vendor-neutral stack. Participants will learn how to ingest and index knowledge with embeddings (FAISS – Facebook AI Similarity Search), implement retrieval-grounded answers with citations, add tool-calling and a planning loop, enforce guardrails and Personally Identifiable Information (PII) redaction, and persist short/long-term memory. The course culminates with learners deploying a custom-built agent to monitor text and create tailor-made responses to incoming support requests from individuals. Through hands-on labs, learners gain experience with FastAPI serving, health checks, logging, evaluation (ragas/pytest), and application webhooks.

Course Content

AGENT ARCHITECTURE 

  • Personas, Scoping, and Independent Operator (I/O) Contracts
  • Minimal Reasoning Loop, Timeouts, and Recovery
  • Retrieval with Citations, Context Windows, and Abstain Rules 

TOOLS AND MEMORY 

  • Tool Registry, Schemas, Validation, and Error Handling
  • Short- and Long-Term Memory with Redaction 

OPERATIONS 

  • FastAPI Serving, Health Checks, and Background Jobs
  • Monitoring, Cost/Latency, Drift, and Runbooks
Requirements & Materials

Requirements

A Windows or Mac laptop with a webcam is required to participate in the course. Tablets or other devices are not supported. Recommended: Additional monitor. 

Familiarity with using a computer and adequate typing ability. 

Course registration requires an approved application and advisor meeting. 

Participants are expected to have their cameras on during the interactive sessions and must attend 80% of the sessions to pass the course.

Prerequisites

Successful completion of FlexStack: Python AI Principles 1 - Large Language Models and FlexStack: Python AI Principles 2 - Applied Generative AI.

Materials

Provided:

  • Canvas
  • Vocareum
  • H5P
  • Lecture Materials

 

Who Should Attend

This course is designed for technical professionals comfortable with Python. It is ideal for data and operations analysts, product and program managers, educators, Information Technology (IT) generalists, and technical leads who want to learn how to select and deploy practical, auditable solutions.

Man who is a technical lead stands in front of screen with Python code as part of the FlexStack: Python AI Principles Certificate.

What You Will Learn

  • Agent architecture, personas, and Independent Operator (I/O) contracts
  • Minimal reasoning loops, timeouts, and planning limits
  • Knowledge ingestion, chunking, embeddings, and Facebook AI Similarity Search (FAISS)
  • Retrieval with grounded citations, context windows, and abstain rules
  • Tool calling with schemas, validation, and error recovery
  • Memory (short/long-term), guardrails, and Personally Identifiable Information (PII) redaction
  • FastAPI serving, health checks, monitoring, and runbooks
Woman sits in front of three monitors reviewing Python code with her male coworker for the FlexStack in Python AI Principles Certificate.

How You Will Benefit

  • Deliver a 24/7 help bot that answers with grounded citations and clear refusals when needed.
  • Reduce manual support workload by automating FAQ lookup, simple calculations, and ticket creation.
  • Improve reliability with schema validation, timeouts, retries, and error recovery paths.
  • Strengthen governance through guardrails, Personally Identifiable Information (PII) redaction, and auditable logs and policies.
  • Monitor cost, latency, and drift to keep service quality stable over time.
  • Ship a portable FastAPI service with health checks, runbooks, and rollback steps.

Want to learn more about this course?