3 Agents
Conceptual summary of agents:
- Agent = any external (to the LLM) program that calls the LLM API. Basically plays the role of a human during chat (but can do much more).
- Agent + AI = an LLM is used as a useful assistant.
Agentic AI evolution (about this diagram)

3.1 Agentic (no AI). Core concepts and basic demos
The core control loop is traditional non-AI deterministic programming
3.2 Agentic + AI. Core concepts and basic demos
The core control loop is traditional non-AI deterministic programming that performs (with the help of an LLM)
- Input and output (of “messy” human language representations)
- Task planning (breaking up complex human language tasks into smaller deterministic tasks)
- Rule injection (by AI into the main loop)
3.3 Agentic AI projects (full demo projects (WIP) with Github repo and docs)
“Spinning up” real-world projects quickly with minimal code analysis or manual coding.
26.0524