Junie knows how to create files and even entire applications. Let's start small – ask it to create a file in the root of your project that describes in detail how the application works. We've prepared a draft of this file for you, and you'll be editing it a bit later.

Create a file named task-description.txt in the root of my project. Add the following content to it: The application is simple console chatbot that allows user to ask questions and get answers. 1. Use OpenRouter API by passing base url and API key to Langchain's implementation 2. Use model: 3. Use OpenRouter API with provided credentials:

API Key:
API Host: https://openrouter.ai/api/v1
Use Langchain for interacting with LLM
just pass provided base url and key. DO NOT EXTEND LANGCHAIN'S CLASSES

4. Create and always use Python virtual environment 5. No fixed package versions required 6. Run the application, test it in a console and fix all issues if needed 7. Provide user instructions to run the application

Learning how to write clear descriptions is the most important part of working with code generation tools. Creating applications with AI is still software engineering — AI just helps along the way. The good news is that AI excels at explaining complex terms and concepts.

Put its abilities to the test: in the chat window, you can attach any file by pressing the "+" button and ask it to clarify something or perform a task based on the file's contents.

Adding files to context

Usually, Junie is quite good at navigating the project on his own but if you want Junie to be laser-focused, you can hit the "+" button to attach specific files or folders. This is how you give Junie access to custom parts of your project—like your README, API guidelines, or folder structures.

Adding files to context

You can attach:

Config or certain files;
Entire directories (e.g., /src/controllers);
Single files with tricky logic or expanded instructions.

This is a huge help in larger projects. Instead of explaining everything to Junie, just show it.

Don't forget to add task-description.txt file to the context. Explain to me all the technical terms and details in the task-description.txt file the way one would explain to a teenager with poor computer skills. Use metaphors and analogies. Make me understand how the application works, what different parts of it are responsible for, what libraries perform what role.

Console Chat with LLM (Junie)

Stages