An agent is not a smarter chatbot. It is a stack.

From Models to Agents is the eras map: chat, reasoning, tools, then the enterprise playbook. AI Right Now Part 6 is control — what it may touch, what you must approve. This series is the wiring diagram. Eight pieces. One machine.

If you only remember the picture, remember this: the language model is an engine. Memory, planning, tools, retrieval, and a loop around them are what make it an agent. Evaluation is how you know the machine did what you think it did.

The stack

Goal
  │
  ▼
Orchestration  (who calls what, when to stop)
  │
  ├── LLM               language engine
  ├── Memory            what persists across steps
  ├── Planning          goal → steps → re-plan
  ├── Function calling  structured tool requests
  ├── Tools             the runtime actually executes
  ├── RAG               retrieve, then ground
  └── Evaluation        score the path, not the end result

Read the diagram top-down once, then left-to-right as a checklist. Orchestration is the clock. The LLM proposes. Memory is the notebook. Planning is the agenda. Function calling is the order form. Tools are the hands. RAG is the library card. Evaluation is the inspector who watches the whole trip, not the last sentence.

None of these pieces is optional in a serious system. You can hide them behind a vendor brand. You cannot delete them.

Three named gears

The picture is not eight marketing words. It is a small number of published gears, wired together.

The loop. ReAct (Yao et al.) interleaves a thought, an action, and an observation from the environment, then continues. Google’s short note is the public explainer. In this series that loop is planning plus tools plus memory: the agenda changes because the world talked back.

The knowledge. Lewis et al. (2020) named retrieval-augmented generation: fetch from a corpus you index, then condition the next tokens on those passages. That is RAG. Acting after the quote is a later choice, not a different kind of model.

The runtime. Someone has to call the model, run the tool, append the observation, and stop. OpenAI’s agents guide is one instance of that scheduler. A while with a max-step counter is the same architecture in a generic term.

The eight parts unpack those gears. They do not replace them.

The series

  1. The language model — the engine is not the vehicle
  2. Memory — working context, session, longer-lived store
  3. Planning — goal → steps, then re-plan after observations
  4. Tools — callable capabilities the runtime runs
  5. Function calling — name + arguments; model proposes, code executes
  6. RAG — retrieve from an approved corpus, then ground
  7. Orchestration — the loop and the stop
  8. Evaluation — measure the trajectory

Sources