AI Foundations
Understand machine learning, generative AI, large language models, and the ideas behind today's AI tools.
Course catalog
22 courses
Understand machine learning, generative AI, large language models, and the ideas behind today's AI tools.
Explore how AI assistants can support research, planning, writing, analysis, and everyday tasks.
Learn to frame objectives, provide context, structure requests, and evaluate AI-generated outputs.
Explore practical workflows for meetings, documents, research, analysis, and task planning.
Explore how AI may support content planning, audience research, and marketing workflows.
Consider realistic AI applications across marketing, customer service, operations, and planning.
Understand workflow automation, triggers, actions, AI steps, testing, and reliability.
Use AI thoughtfully as a learning partner while strengthening independent thinking and creativity.
Explore practical ways to build future-ready skills and apply AI across professional tasks.
Explore use cases, adoption barriers, evaluation, governance, and responsible organizational change.
Design, build, evaluate, and deploy applications on top of large language model APIs, with structured outputs, tool calling, streaming, and safety built in.
Build retrieval-augmented generation systems with embeddings, vector databases, hybrid search, and reranking, and learn to evaluate and run them in production.
Engineer reliable AI agents and multi-step workflows with tool use, MCP, orchestration frameworks, memory, guardrails, observability, and human approval steps.
Use AI coding assistants to write, test, refactor, and review code faster while keeping quality, security, and team standards intact.
Take machine learning and LLM applications from notebook to production with tracking, CI/CD, serving, monitoring, evaluation, and governance.
Apply AI to Python and SQL work, data quality, pipelines, feature engineering, and LLM-based extraction, then present results in dashboards.
Go from raw, messy files to clear, defensible insights using Python, pandas, NumPy, and modern visualization libraries, and learn to present findings as a story.
Write advanced analytical SQL, design dimensional models, and build tested warehouse transformations with dbt on modern cloud and open-source warehouses.
Build reliable batch ETL and ELT pipelines with Python, Airflow, and dbt, using incremental loads, idempotent design, testing, lineage, and lakehouse storage formats.
Build, validate, tune, and explain supervised and unsupervised models with scikit-learn, with emphasis on sound evaluation and responsible practice.
Build event-driven systems and large-scale processing jobs with Apache Kafka and Apache Spark, covering delivery semantics, windowing, scaling, cost, and reliability.
Build neural networks in PyTorch, apply CNNs and transformers, fine-tune models with Hugging Face, and evaluate and deploy them with care.