Back to resources
Kind
Mental model
Reading time
3 min read
agents

Agents in One Paragraph

A compact mental model for understanding what an AI agent is, what it can do, and where its behavior comes from.

Topics

  • agents
  • llms
  • mental models

The short version

An AI agent is a software system that repeatedly uses a model to choose its next step. A useful way to picture one is as a digital worker: the harness supplies tools, rules, and access to persistent information, while the model predicts what action should happen next from the context it can currently see.

The model may live in the cloud or run locally. What makes the system useful is not the metaphorical brain by itself, but the way the surrounding software assembles context, limits actions, executes tools, and checks results.

System map

The agent execution loop

The agent execution loop An agent assembles context, asks a model for the next action, uses a tool, observes the result, and repeats the loop. Long-term memory feeds context assembly. AGENT EXECUTION LOOP 01 / INPUT Goal & rules What should happen? 02 / ASSEMBLE Active context What is on the desk? 03 / PREDICT Model inference Choose the next step 04 / ACT Tool or response Change the world 05 / OBSERVE Result Learn what happened SIDE CHANNEL Long-term memory Retrieve when useful
An agent turns a goal into a series of context, prediction, action, and observation steps.

What is actually happening?

At the start of a task, the harness collects the current goal, instructions, conversation history, retrieved information, and available tool definitions. That bundle becomes the model’s active context. The model then produces the next response or tool call based on the information and constraints in that context.

If a tool is called, the harness executes it and adds the result to the next context. The loop can continue until the task is complete, a policy blocks an action, or a human takes over.

Three things to keep separate

Context is not memory

The context window is the capacity of the active working surface. Its size is limited by the selected model, and its contents change from step to step. A database, file, or vector store can hold persistent information, but the harness must deliberately retrieve useful pieces and put them into the active context.

Prediction is not a guarantee

The model is very good at continuing patterns in language and tool-use examples, but a confident response is not proof that an action is correct. Production systems need validation, permissions, evaluation, and observability around the model.

Tools define the action space

An agent with no tools can only produce information. An agent with unrestricted tools can create unacceptable risk. The useful middle is a small, explicit capability surface with clear input validation, authorization, and failure handling.

Use this model when designing a system

When an agent behaves unexpectedly, inspect the system in this order:

  1. What goal and rules were placed in the active context?
  2. What information was retrieved, and what important information was missing?
  3. What tools and permissions were available at that step?
  4. What result came back from the tool?
  5. What evaluation or human review would have caught the failure?

That sequence turns a vague question about whether a model is “smart enough” into a set of engineering questions that can be tested.

Apply the pattern

Have a real system to work through?

I help teams turn useful AI ideas into clear architectures, working prototypes, and production practices.

Start a conversation