Learn Bash, Canvas and Clojurescript

Docker containers wrap a piece of software in a complete filesystem that contains everything needed to run: code, runtime, system tools, system libraries – anything that can be installed on a server. This guarantees that the software will always run the same, regardless of its environment.

docker

This lesson uses some advanced concepts and some bash scripting to build a better Dockerfile. By using the concepts showed here, you will be able to build more future-proof and production-ready containers. If you prefer to focus on the content about containers, feel free to ignore this lesson and come back to it later on if needed.

Currently, we use `sed` to overwrite the hard-coded path to the API. This works well when there is a single value to replace. Now if one of your team members replaced the value of localhost:3000, your build will break.

We'll use `jq` to fix this issue. Jq is a command-line tool that makes it easy to change values in a JSON file. The base image that we used for building the application does not contain this tool, but that is not an issue. To install `jq`, you will need to download the [binary](https://github.com/stedolan/jq/releases/download/jq-${JQ_VERSION}/jq-linux64.), we'll need that to execute `jq` commands in our Dockerfile. This will allow us to update specific properties i

Modify a JSON Configuration File with jq

Extracting meaningful data from strings is a crucial skill when working with bash, and bash gives us powerful tools to do so: `head`, `tail`, `cut`, `sed`, and `awk`. But these tools can be hard to understand without spending time to learn them, so many developers fall into a rut of blindly copying and pasting commands. No more! With this mini-course, you'll understand the basic ins and outs of these commands in under 15 minutes. 


Bash is a Unix shell and command language written by Brian Fox for the GNU Project as a free software replacement for the Bourne shell. Bash is a command processor that typically runs in a text window, where the user types commands that cause actions. Bash can also read and execute commands from a file, called a shell script.

bash

Manipulating strings in bash

In this lesson, we'll use the power of awk to select the columns and rows of data that match our condition. We'll pass a `,` (comma) to the `-F` flag (the F stands for field separator), to tell awk to split on commas. From there, the world is our oyster and we can tell awk to only return rows that match whatever parameters we pass.

Extract Columns of Data from a CSV with awk

`awk` is a specialized tool and programming language for querying and transforming text.   In this lesson, we’ll scratch the surface of the possibilities it provides by leveraging it in one of its most common use cases: extracting data from columns of text. Awk makes it easy to select and print just the columns and rows that we want from commands, like `ps`, that return a table of data.

Extract Data From Columns of Text with awk in Bash

Pandoc is a command-line tool built in Haskell that can convert almost any markup or word processing format interchangeably. You specify the input and the output types and pandoc will do the rest.

In this lesson we will convert a few markdown files to pdf. You will see how to convert a single file and then we'll write a script to loop through a couple files and convert them dynamically.

This lesson requires that you install `pandoc` and have `pdflatex` available.

You can install `pandoc` with brew: `brew install pandoc`
To access `pdflatex`, you can install `basictex` and set the path for `--pdf-engine` to `pdflatex`

Convert a File from Markdown to PDF with pandoc

🚀 In this collection, I will be going over some command line tools I use on a daily basis that make my life a lot easier.

[First up is fzf](https://github.com/junegunn/fzf).

> fzf is a general-purpose command-line fuzzy finder.

Upgrade Your Terminal and Make It a Joy to Work with

`fzf` is a fast cli finder tool. The `fzf` command will launch an interactive find session. You can type a path to a file and see a list of possible results.

Piping the output of commands (such as git branch) to `fzf` makes it easy to find the line you are looking for.

Interactively Find Anything By Piping it to fzf in the terminal

Many people just drop all of their Zsh functions inside of their .zshrc and forget about it. But as your collection of functions begins to grow, you start looking for a better way to organize everything. Since Zsh provides `autoload` for loading in functions dynamically, we can drop all of our functions into individual files, loop through that directory, then autoload each file as a function.

Store Zsh Functions in Individual Files Inside a Directory

SSH provides a secure way for your to [connect to and authenticate with GitHub's servers](https://help.github.com/en/github/authenticating-to-github/about-ssh). While HTTPS connections use usernames and passwords as credentials, SSH instead uses public and private key pairs. These can be generated on your system using a CLI like [`ssh-keygen`](https://help.github.com/en/github/authenticating-to-github/generating-a-new-ssh-key-and-adding-it-to-the-ssh-agent) and then associated with your GitHub account using the public key.

In some cases, you may need to connect to more than one GitHub account from the same system. For example, you may have [separate accounts for personal and professional projects](https://ryanharris.dev/managing-ssh-keys-for-github/), which can be difficult to manage manually. Using `ssh-agent` and a SSH configuration file, you can alleviate this pain point by automatically determining which key to use based on your GitHub repository's `git` URL.

Secure GitHub connections with SSH

When working with multiple GitHub accounts on the same system, you want to ensure that your commits have the proper author information. 

To do this, we'll create a global `git` configuration on our system that uses our personal account's information. Then, in our work-specific repositories, we'll add a local `git` configuration to override our global values.

We will be using the following commands in this lesson:

- `code`
- `git config`

Update gitconfig to Work with Multiple Accounts and SSH Keys

In this lesson, we have two local SSH keys: one associated with our personal GitHub account, the other with our work account. 

To more easily manage them, we will use `ssh-add` to add our keys to our system's key manager `ssh-agent`. Then, we will create a SSH configuration file, which will determine what key to use when connecting to GitHub based upon the URL. 

Once we have set up our configuration file, we can test our connections using `ssh -T` and clone repositories with `git clone`.

Commands we will be using in the lesson:

- `ls`
- `ssh-add`
- `touch`
- `ssh`
- `git clone`

Manage Keys with ssh-agent and Add SSH Configuration

In some cases, you may have multiple GitHub accounts that you need to interact with from the same system. For example, you could have an account for work and another for personal projects, but you don't want to re-authenticate each time you switch between then. By using public SSH keys for each account, you can eliminate this part of the process.

In this lesson, we will create two SSH keys in our terminal using `ssh-keygen` , copy them to our clipboard using `pbcopy` and then add them to our respective GitHub accounts.

Commands we'll be using include:

- `ssh-keygen`
- `ls`
- `pbcopy`

Generate SSH Keys for your GitHub Accounts

Parsing arguments in zsh functions can be a bit difficult to manage if you try and customize it for each new function. Luckily, that's where zparseopts comes in. zparseopts is a utility function which can parse out each of the arguments you define and store them inside of an associative array for easy access. This makes accessing arguments as easy as looking them up by name.

Pass Arguments to zsh Functions with zparseopts

Node.js is a platform built on Chrome's JavaScript runtime for easily building fast, scalable network applications. Node.js uses an event-driven, non-blocking I/O model that makes it lightweight and efficient, perfect for data-intensive real-time applications that run across distributed devices.

node

It can be difficult to work on multiple projects that use different versions of Node.

`nvm` ([Node Version Manger](https://github.com/nvm-sh/nvm)) make this easier by allowing you to download multiple versions and switch between them. You can also add a NVM configuration file (i.e. `.nvmrc`) to specify which version you want to use for each project.

In this lesson, we'll cover the following commands:

- `nvm install`
- `nvm ls`
- `nvm ls-remote`
- `nvm use`

Install and Manage Node.js Versions with nvm

Git is a free and open source distributed version control system designed to handle everything from small to very large projects with speed and efficiency.

Using the [GitHub CLI](https://github.com/cli/cli) and a shell script, we will automate the process of monitoring pull requests in repositories we maintain. Specifically, open PRs we have created and those awaiting our review.

Monitor Pull Requests with the GitHub CLI

When we run commands in OSX or Linux terminal which output long lines, these lines are wrapped making output sometimes not readable. This is especially true when dealing with tabular data outputted into console. In this lesson we will see a trick that you can do to disable this line wrapping while still being able to read the data.

Disable line wrapping in OSX or Linux terminal

`cut` makes it quick and easy to break a string into parts based on a delimiter or get a substring. In practice, it’s somewhat similar to JavaScript’s `String.split` method. In this video, we’ll look at using `cut` to work with semver strings and truncate a long string.

Split a String into Parts with `cut` in Bash

In this lesson, you'll learn how sed can be used to insert lines of text. We'll use sed's `i` command to insert a header at the top of every .js file in a directory. 

Insert Text with sed in Bash

In this lesson, you'll learn how sed can be used to delete lines of text. You can use a regex or line numbers to target a line for deletion. This makes a sed a powerful tool for automatically performing lots of tedious text deletions for you. 

Delete Lines of Text with sed in Bash

sed, which stands for stream editor, is probably most commonly used to replace text patterns with a new one, which is exactly what we’ll learn in this lesson. 

You'll learn how what flags you pass, the address argument as well as the commands that sed takes. The sed syntax can be summarized like this: `sed [flags] '[address]command[options]' [input file]`

Find and Replace Text with Sed in Bash

Head and tail are handy tools for getting just the beginning or end of a text stream. In this lesson, we’ll look at getting the first or last lines from the beginning or end of text. 

Use head and tail to Get the Start or End of Text in Bash

Hardcoding your script to search for only one type of file (like `.md`) is a major limitation. This lesson shows you how to make your script smarter by teaching it to infer the desired file type directly from the user's natural language prompt.

You'll implement a two-stage AI process. The first stage analyzes the user's request to determine the file extension they're interested in (e.g., `md`, `txt`). The second stage then uses that file type to dynamically search the file system, find the relevant files, and execute the command.

**Workflow demonstrated in this lesson:**

* Add a preliminary `generateObject` call to extract a `fileType` from the user's initial prompt.
* Define a list of supported `fileTypes` (e.g., `['md', 'txt']`) and use a detailed prompt to guide the AI, instructing it to choose from the list or use a default.
* Dynamically construct the `globby` pattern using the inferred `fileType` (e.g., `*.$[fileType]`).
* Implement error handling to inform the user if they request an unsupported file type or if no files of the specified type are found.
* Demonstrate how the script defaults to searching for Markdown files but can correctly search for other types when specified (e.g., "summarize my profile from my pdf").

This technique adds a significant layer of intelligence to your script, allowing it to adapt its behavior based on the user's intent and making it a far more flexible and intuitive command-line tool.

John Lindquist

Dynamically Inferring File Types from User Prompts in Local AI Scripts

Hardcoding command logic and prompts directly into your script makes it rigid and difficult to extend. This lesson demonstrates a more flexible and powerful pattern: defining your script's commands as individual Markdown files in a dedicated directory.

This approach allows you to easily add, remove, or modify commands without touching the core script logic. You'll learn how to dynamically load these command files, present them as options to the AI, and inject the corresponding instructions into your prompt, creating a truly modular and extensible tool.

**Workflow demonstrated in this lesson:**

* Create a `commands` directory to house your command definitions (e.g., `summarize.md`, `translate.md`).
* In each file, write the specific prompt or instructions for that command.
* Use `globby` to discover all available command files at runtime.
* Create a `commandMap` that maps the filename (e.g., "summarize") to its file content.
* Update the Zod schema to use an `enum` of the dynamically discovered command names.
* Dynamically construct the final text generation prompt by injecting the instructions from the user-selected command file.
* Add a `profile.md` file to demonstrate how the script can act on user-created content with the new file-based commands.

By the end of this lesson, your script will be architected for easy expansion, allowing you to build a robust library of custom commands simply by adding new text files.

Creating Dynamic, File-Based Commands for Local AI Scripts

AI models won't always give you the answer you expect; sometimes they'll return invalid data or "hallucinate" a response that doesn't fit your schema. This lesson teaches you how to make your local AI script more robust by implementing essential error handling for user commands.

You'll learn how to validate the AI's output against a predefined list of valid commands and gracefully catch errors when the model generates an unexpected response, ensuring your script fails predictably and provides helpful feedback to the user.

**Workflow demonstrated in this lesson:**

* Define a list of `validCommands` (e.g., `summarize`, `translate`, `review`) to constrain the AI's choices.
* Wrap the `generateObject` call in a `try...catch` block to handle cases where the AI's output doesn't match the Zod schema.
* Implement a type guard function (`isValidCommand`) to check if the command returned by the AI is in your list of valid commands.
* Provide clear error messages to the user, indicating what went wrong and what the valid commands are.
* Test the script with invalid commands (like "taco" or "delete") to confirm that the error handling works as expected.

By adding these checks, you make your script significantly more reliable and user-friendly, preventing it from crashing on bad input and guiding the user toward correct usage.

Handling Invalid Commands and AI Errors in Local Scripts

Once your script can understand a user's command and identify a target file, the next step is to perform an action. This lesson shows you how to use the Vercel AI SDK's `generateText` function to process a file's content and produce a relevant, AI-generated response.

You'll learn how to read the content from the file path you've already identified, combine it with the inferred command into a new, more detailed prompt, and then pass it back to your local AI model to generate a final text output, such as a summary or a review.

**Workflow demonstrated in this lesson:**

* Import the `generateText` function from the `ai` SDK.
* Read the file content from the `filePath` returned by `generateObject`.
* Construct a new, structured prompt that includes the original command (e.g., "summarize") and the full content of the file.
* Pass this new prompt to the `generateText` function.
* Log the resulting AI-generated text to the console.
* Run the script with commands like "Summarize our TypeScript config" or "Review my package file" to see the full, context-aware output.

This lesson completes the core cycle of your AI script: understanding a command, reading the relevant context, and generating a useful, text-based result, all on your local machine.

Generating Text with a Local AI Model Based on File Content

A command is useless without knowing what to act upon. This lesson elevates your local AI script by giving it context from your project's file system. You'll learn how to find all relevant files and empower the AI to intelligently select the correct one based on your prompt.

The core technique involves using the `globby` package to scan for files and then feeding that list into a Zod `enum`. This constrains the AI's choices to a valid set of files, allowing it to accurately determine which file you're referring to in a natural language command.

**Workflow demonstrated in this lesson:**

* Install and import the `globby` library to find files based on a pattern (e.g., all `.json` files).
* Add a `filePath` field to your Zod schema.
* Define the `filePath` as `z.enum(files)`, where `files` is the array of file paths returned by `globby`.
* Pass a natural language prompt like "Summarize our typescript config" to the script.
* Observe how the AI correctly identifies `tsconfig.json` from the list of available JSON files and returns it as structured data.

This lesson is a crucial step toward building powerful, context-aware tools that can intelligently interact with your project's files based on simple, human-readable commands.

Providing File System Context to Local AI Scripts with Globby and Zod Enums

Hardcoded prompts are great for testing, but a truly useful script needs to respond to dynamic user input. This lesson shows you how to make your local AI script interactive by capturing command-line arguments.

You'll learn how to use Node.js's built-in `parseArgs` utility to take a user's natural language command directly from the terminal and pass it to your local language model for processing.

**Workflow demonstrated in this lesson:**

* Import the `parseArgs` function from the `node:util` module.
* Configure `parseArgs` to accept positional arguments from the command line.
* Replace the static, hardcoded prompt with the dynamic input provided by the user.
* Run the script with different sentences (e.g., `"Download a file"` or `"I want to download a file"`) to demonstrate that the AI can correctly infer the core command regardless of the phrasing.

By the end of this short lesson, your script will be able to accept and process commands directly from the user, making it a flexible and reusable command-line tool.

Processing Dynamic User Input in Local AI Scripts

While command-line chats with local AI models are useful, the real power comes from scripting. This lesson walks you through the initial setup for creating powerful, local AI-driven scripts by combining Ollama, the Vercel AI SDK, and Zod.

You'll learn how to take a natural language command, like "Concatenate all of the markdown files in my Downloads folder into a single file," and use the `generateObject` function to intelligently extract structured, actionable data from it.

**Workflow demonstrated in this lesson:**

* Install and set up the `ollama-ai-provider`, `ai`, and `zod` packages.
* Create a local AI model instance using Ollama and the Gemma 3 model.
* Define a Zod schema to specify the exact data structure you want to extract (e.g., `{ command: string }`).
* Use `generateObject` to pass a natural language prompt to the local model and receive a structured JSON object that matches your schema.
* Run the script using `bun` to see the local model successfully infer the "concatenate" command from a full sentence.

This foundational lesson unlocks the ability to build sophisticated, automated workflows by translating human language into machine-readable commands, all running entirely on your local machine.

Scripting Local Language Models with Ollama and the Vercel AI SDK

### **Build Powerful, Local AI-Driven Command-Line Scripts**

Go beyond simple AI chats and unlock the true potential of local language models by learning to script them. This course will guide you step-by-step through the process of building a flexible and intelligent command-line tool that can understand natural language, interact with your file system, and automate complex tasks—all running entirely on your local machine.

Starting with a blank TypeScript file, you'll learn how to combine the power of **Ollama**, the **Vercel AI SDK**, and **Zod** to create a script that's not just functional, but smart. We'll begin by teaching the AI to parse a simple command from a sentence. From there, we'll progressively add layers of sophistication: processing dynamic user input, making the script aware of your project's files, and generating meaningful text-based output.

You'll also learn critical patterns for building robust and extensible tools. We'll cover how to handle invalid commands and unexpected AI responses gracefully. Then, you'll refactor the script to use a modular, file-based system for its commands, allowing you to easily add new functionality without touching the core logic. Finally, we'll add a layer of intelligence that allows your script to infer exactly what you mean, right down to the type of file you want it to process.

By the end of this course, you will have built a powerful, personalized AI assistant and gained the foundational skills to create sophisticated local automations for any task you can imagine.

**What You'll Learn:**

* How to script local language models using Ollama and the Vercel AI SDK.
* To parse and process dynamic user input from the command line.
* To use Zod schemas, including `enums`, to validate and structure AI model output.
* Techniques for providing file-system context to your scripts with `globby`.
* How to generate context-aware text based on file content.
* Robust error handling for invalid user commands and unexpected AI responses.
* To build a modular and extensible tool by defining commands in separate files.
* To intelligently infer user intent, such as dynamically determining file types from a prompt.

Build a local AI-powered command-line assistant from scratch. Learn to use Ollama, Vercel AI SDK & Zod to parse input, automate tasks, and run scripts offline.

This lesson demonstrates how to give Cursor direct access to your terminal output using the [Nx MCP extension](https://nx.dev/getting-started/ai-integration?utm_source=youtube&utm_medium=videos&utm_campaign=Nx-AI&utm_id=Nx-AI), enabling automatic error detection and fixing in monorepo projects.

**Workflow demonstrated in this lesson:**

- Encounter a runtime error when serving a Vite application in an Nx monorepo
- Install and configure the Nx Console extension with MCP integration
- Ask Cursor to check your terminal for errors and fix the underlying issues
- Watch as the AI accesses running task details and terminal output through Nx MCP tools
- Observe how it analyzes workspace relationships to identify incorrect imports and missing dependencies

**Key benefits:**

- Seamless Error Handling: AI gains direct access to terminal output and running task information
- Automatic Diagnosis: Accurately identify the root cause of errors without manual copying
- Context-Aware Fixes: Leverage workspace knowledge to implement proper solutions
- Reduced Context Switching: Eliminate the need to manually relay information between terminal and AI



Juri Strumpflohner

Enable Cursor to directly access the terminal to read the output and fix issues

See how Nx MCP gives AI coding assistants direct access to terminal output and running tasks, enabling automatic error detection and fixing.

This lesson demonstrates how to solve the predictability problem when using AI to generate code in monorepos by combining Cursor with Nx generators.

**Workflow demonstrated in this lesson:**

- Explore how Nx generators provide predictable scaffolding for new libraries
- Set up [Nx Console with MCP](https://nx.dev/features/enhance-AI?utm_source=egghead&utm_medium=videos&utm_campaign=Nx-AI&utm_id=Nx-AI) integration to expose generator capabilities to Cursor
- Use the AI assistant to brainstorm a new feature with the help of the Nx MCP tools
- Have Cursor leverage the Nx MCP tools to trigger the appropriate Nx generator for creating a React-based feature library
- Observe how the AI assistant takes the generated library and further integrates it into the codebase

**Key benefits:**

- **Predictable Code Structure**: Ensure generated libraries follow your project's and organization's conventions
- **Consistent Setup**: Maintain uniform configuration across TypeScript projects and package.json files
- **Guided Implementation**: Combine AI instructions with structured, predictable code generation

Enable Cursor to generate predictable project setups

Learn how to combine Cursor AI with Nx generators for predictable library creation in monorepos, ensuring consistent structure across your codebase.

Search

Search Results