AI Agents Fundamentals
Build a bounded agent loop and learn the practical difference between chatbots, workflows, tool-using systems, and agents.
Production project
Incident Triage Agent
An operations team receives incident reports and needs consistent severity classification, investigation suggestions, and a concise handoff summary.
Who this is for
- •Developers entering agentic AI
- •Engineers who want to avoid wrapping a chatbot and calling it an agent
How this helps
- •You understand where agency adds value and where it adds risk
- •You can build a small agent with explicit control boundaries
What you will learn
The capabilities, not just the keywords.
- •Distinguish deterministic workflows from agent loops
- •Define a bounded goal and action space
- •Implement observe-decide-act iteration
- •Add stop conditions and failure handling
- •Identify where human review should begin
Real production project
Incident Triage Agent
An operations team receives incident reports and needs consistent severity classification, investigation suggestions, and a concise handoff summary.
What we build
- •Incident intake
- •severity classification
- •tool selection stub
- •investigation plan
- •final triage summary
Stack
- •Python
- •LLM API
- •structured output
- •simple tools
Production concerns
- •Bounded autonomy
- •incorrect severity
- •tool failure
- •human escalation
- •traceability
Finished deliverables
- •Working agent loop
- •agent state model
- •failure scenarios
- •architecture diagram
Prerequisites
Required
- •Basic LLM API understanding
Helpful, but optional
- •AI03 or function-calling experience
Before the session
Come ready to build.
- •Python or Node.js
- •LLM API access
- •Git
What to expect
What you get
Something useful after the call ends.
- •Source code
- •agent design checklist
- •test scenarios
- •next-step LangGraph path
Where to go next
LLM Tools → Agent Loops → Production Agent Systems
Every session can be booked independently. If you already know the prerequisite material, skip ahead.
Teaching proof
Review the evidence first.
See workshop delivery, technical projects, and teaching proof before booking.
Ready?
Request AG01: AI Agents Fundamentals
Share your current level and what you want to build. The session can be adapted without changing its core outcome.
Request this sessionFAQ
Can I book only this session?
Yes. Every session is designed to work independently.
Can I bring my own project?
Yes, when it fits the session outcome. We can map the concepts onto your project instead of the default example.
What if I already know part of the topic?
We can move faster through familiar material and spend more time on implementation, failure modes, and production trade-offs.
Is the session recorded?
Recording is not promised by default. Confirm this before the session if you need it.
What should I install?
The preparation section above lists the default setup. You will receive any session-specific setup notes before the call.
Are API or cloud charges included?
No. Any third-party API or cloud usage is paid directly through your own account unless explicitly agreed otherwise.