From AI Chatbots to AI Agents
Start by defining and experiencing a normal AI chatbot conversation, then gradually add files, analysis, tools, search context, and a visual HTML capstone that shows what makes...
$ open "Start with chat"
Define AI chatbots and AI agents, then experience the chatbot baseline through normal conversation.
checkpoints run as you work
✓ checkpoint passed, lab 2 unlocked
What you'll build
Curriculum
8 labs, about 1.5 h
- 1
Start with chat
Define AI chatbots and AI agents, then experience the chatbot baseline through normal conversation.
6 min
- 2
Save the conversation
Move from temporary chat to durable workspace state by asking the agent to write notes.
8 min
Locked - 3
Read before answering
Ask the agent to inspect a customer message and order table before writing a grounded reply.
10 min
Locked - 4
Analyze a file
Have the agent summarize and count a CSV so it produces grounded operational guidance.
10 min
Locked - 5
Use a tool
Run a small local refund tool and use its output in a grounded response.
10 min
Locked - 6
Search for context
Use a local knowledge base as safe search context before updating a customer answer.
10 min
Locked - 7
Map the loop
Convert the previous runs into a clear agentic loop with concrete examples.
9 min
Locked - 8
Build the visual
Build a small HTML page that visualizes the transition from chatbot to agent.
14 min
Locked
Your instructor
Elvis Saravia
Founder, DAIR.AI
Elvis founded DAIR.AI and wrote the Prompt Engineering Guide, one of the most widely used references on working with language models. He has worked at companies like Meta AI and Elastic, and specializes in AI agents, RAG, and harness engineering.
How labs work
Live workspace
You run the real tools in a browser workspace. Nothing to install.
Checkpoints
Each lab checks your files and output, then unlocks the next one.
Your work stays
The workspace persists between labs so you finish with a project.