AI courses for developers
LLMs in production: APIs, RAG, agents, evaluation, cost and reliability.
The engineering track. Not "how to write a prompt" but how to build the system: APIs and context handling, embeddings and retrieval, RAG, tool calling and agents, evaluation, cost control and failure behaviour.
The material is text and dense: code, diagrams, and walk-throughs of why designs break on real data. Every block ends with a project graded against a rubric, not just marked as submitted.
This track is included in the Ultra plan along with every other course.
AI for developers: APIs and agents
APIs, RAG, agents and production.
Machine learning foundations
How ML works: concepts, task types and models — no heavy math.
Python for AI from scratch
Learn Python and libraries for AI and data work.
Working with LLM APIs: advanced
Streaming, tools, structured output and production reliability.
Building RAG systems
Answers over your data: indexing, retrieval and cited generation.
AI agents and multi-agent systems
Agents, tools, planning and safe autonomous behavior.
Fine-tuning and customizing models
When and how to fine-tune models for your tasks and data.
Vector databases and embeddings
Semantic search: embeddings, indexes and vector stores.
LLMOps and production
Cost, cache, monitoring, evals and safety of AI systems in production.
Computer vision with AI
Recognition, detection and segmentation of images in practice.
Natural language processing (NLP)
How machines understand text: tokens, embeddings, NLP tasks.
AI with local and open models
Run open models locally: privacy, cost and setup.
Prompt engineering for developers
Prompts as code: system prompts, tests, versions and reliable output.
AI for data analytics
From question to insight: cleaning, analysis and viz with AI.
Forecasting and time series
Forecast demand, sales and metrics with AI and statistics.
AI dashboards and BI
Interactive dashboards and self-serve analytics with AI for teams.