Skip to main content
qabash
Learning Paths
intermediate

Python for AI

Go from Python scripting to building and testing real AI features — data wrangling, classic machine learning, LLM APIs, RAG, and agents — with a QA engineer's focus on evaluating whether any of it actually works.

+500 XPon completion
24 hours394 min of lessons
25 lessons6 modules
0enrolled

What you'll learn

  • NumPy & pandas for real datasets
  • scikit-learn workflow & metrics
  • Calling LLM APIs with structured output
  • Building and measuring RAG
  • Tool calling & agent loops
  • Evaluating and testing AI systems
pythonaimachine-learningllmragevals

Curriculum— 6 modules, 25 lessons

The Python AI Stack — What Each Library Is ForFREE12mNumPy — Arrays, Vectors, and Why Loops Are SlowFREE15m
pandas — Loading, Filtering, and Grouping Data15m
Cleaning Messy Data15m
Exercise — Analyze a Flaky Test Dataset20m
How Machine Learning Actually Learns12m
The scikit-learn Workflow — Split, Fit, Predict15m
Metrics — Accuracy Lies, Precision and Recall Do Not15m
Overfitting, Data Leakage, and Other Silent Failures15m
Your First LLM API Call — Messages, Roles, Parameters15m
Prompt Engineering That Survives Production15m
Structured Output — Getting JSON You Can Trust15m
Streaming, Tokens, Cost, and Rate Limits12m
Exercise — Build a Bug Report Triage Classifier20m
Embeddings — Turning Meaning into Numbers15m
Chunking and Vector Search15m
Building a RAG Pipeline End to End18m
Measuring Retrieval Quality15m
Tool Calling — Letting the Model Use Your Functions15m
Agent Loops — Plan, Act, Observe15m
Guardrails, Prompt Injection, and Safe Tool Design15m
Evals — Testing Software That Is Not Deterministic15m
Golden Datasets and LLM-as-Judge15m
Exercise — Capstone: A Tested Test-Case Generator25m
Checkpoint — Python for AI Comprehensive Review20m