Lessons & paths
Follow your curiosity.Build your understanding. 6 lessons · Learn at your pace
AI essentials Build a practical foundation, without a coding prerequisite.
AI, machine learning, and generative AI What does a language model actually do? Confident answers can still be wrong Give the task, the context, and the finish line When AI works with images, audio, and text Use AI with clear data boundaries
0 of 6 marked complete
Start path → 6 lessons · Learn at your pace
Agents & applied AI Connect evidence, tools, evaluation and action permissions.
Embeddings: finding related meaning RAG: give an answer the right evidence RAG or fine-tuning? Start with the problem How agents use tools, and where MCP fits Measure quality, reliability, and cost Put permissions outside the prompt
0 of 6 marked complete
Start path →
Explore the lessons 12 original lessons LevelAll levels Beginner Intermediate Advanced Find a lesson
12 matching lessons
Task →Rules or learned model
Beginner 4 min
AI, machine learning, and generative AI Tell apart learning from data, following rules, and generating new content.
Open lesson ↗ Prompt →Tokens
Beginner 4 min
What does a language model actually do? Understand how text generation differs from looking up a fact.
Open lesson ↗ Claim →Open source
Beginner 4 min
Confident answers can still be wrong Know what to check before trusting an AI-generated claim.
Open lesson ↗ Task →Context
Beginner 5 min
Give the task, the context, and the finish line Turn a vague prompt into a request you can evaluate.
Open lesson ↗ Image + question →Supported model
Beginner 4 min
When AI works with images, audio, and text Recognize what combining different kinds of input enables and where it can fail.
Open lesson ↗ Need →Allowed data
Beginner 4 min
Use AI with clear data boundaries Choose suitable information to share and check outcomes before acting.
Open lesson ↗ Question →Embedding
Intermediate 4 min
Embeddings: finding related meaning Explain why vector similarity can help search without proving an answer is correct.
Open lesson ↗ Question →Retrieve evidence
Intermediate 5 min
RAG: give an answer the right evidence Explain how retrieval helps answer questions about changing documents.
Open lesson ↗ Observed problem →Candidate technique
Intermediate 4 min
RAG or fine-tuning? Start with the problem Choose a starting technique based on freshness, behavior, and evidence requirements.
Open lesson ↗ Goal →Model selects tool
Intermediate 5 min
How agents use tools, and where MCP fits Separate the model, the agent loop, and the tool connection.
Open lesson ↗ Test cases →Baseline + candidate
Advanced 4 min
Measure quality, reliability, and cost Build an evaluation that reflects the task instead of relying on a memorable demo.
Open lesson ↗ Proposed action →Policy check
Advanced 5 min
Put permissions outside the prompt Identify where an agent’s proposed action must be checked.
Open lesson ↗ 
knowAIedgeA little more informed. Every day.