> Source URL: /research/learning-agent/learning-agent.project
---
title: Build a simple learning agent
outcomes:
  - understand basic unix-based command line interface
  - understand how agents can use unix-based commans to gather context
  - create a simple agent looop that checks a user's work against an outcome and logs feedback to a file
---

# Build a simple learning agent??

In this project, we will build a simple learning agent that

- Given an outcome description (e.g. `my-project.outcome.md`), the agent will check a user's work against the outcome and
  - Create a learning path for the user to follow to achieve the outcome (e.g. `my-project.path.md`)
  - Track the user's progress at an interval (e.g. every 30s) to see what's changed and update the progress
  - Give the user feedback on demand (e.g. "How am I doing?" what should I do next?)

## Setup

We're going to do a deep dive on using the terminal so it's a good idea to install a good one. I reccomend using [Ghostty](https://ghostty.org/download).

## How agents "see" the world

Agents are able to see"the world (aka your computer and the internet) by using simple command line tools.

Many of these tools have been around for decades and are well-documented and widely used. Agents are very good at them because they are very good at following instructions.

Here are some of the most common command line tools:

- `ls`: list directory contents
- `cd`: change directory
- `pwd`: print working directory
- `mkdir`: create a directory
- `rm`: remove a file or directory
- `cp`: copy a file or directory
- `mv`: move a file or directory
- `ln`: create a symbolic link

## Project Steps

1. Setup a cli tool

2. read the outcome file

3. scan the source dir

4. create the plan prompt

5. create the "next step" ommand `agent next-step`

```bash
learning-agent.py plan-next-step
starting...
snapshoting state
reading path/project/project-1.outcome.md...
assessing progress
createing next step
next step created: ./plan/step-4/index.path.md
```


---

## Backlinks

The following sources link to this document:

- [Learning Agent](/research/index.path.llm.md)