Where to learn AI agent fundamentals from scratch?
A developer building AI agents at a UK startup says they can wire things together in n8n but feel they are missing the underlying concepts. They are asking the community for courses, video series, or docs that explain core agentic AI ideas — including how memory works, how tools are connected, and how orchestration patterns function.
Key points
- Being able to build with n8n does not mean understanding what happens inside the agent
- Core concepts to learn: memory management, tool use, and orchestration patterns
- Structured learning is needed alongside hands-on building to optimize cost and reliability
- Community recommendation threads like this are practical starting points for self-study
Quick term guide
- agentic AI
- AI that tries to complete a goal by taking several steps, not just answering one question.
- orchestration patterns
- Ways of coordinating multiple AI steps or agents so they run in the right order and under the right conditions
- orchestration pattern
- A common way to organize how different steps in a system run together.
- orchestration
- Coordinating multiple AI agents or steps to run in a specific order or in parallel to complete a task
- tool calls
- Times when an AI system uses another function, such as search or file access.
- token usage
- Token usage is a count of how much text an AI tool processes.
- reliability
- How consistently a tool works without failing or behaving unexpectedly.
- liability
- Legal responsibility for causing an accident or damage.