Your First Copilot-Style Completion

Let's actually feel what autocomplete is like. Write a comment, pause, and watch a full function appear. Then learn what to do next.

30 min · Reviewed 2026

Ghost Text, Meet Real Text

Autocomplete shows suggested code in gray right where your cursor is. This is called ghost text. Press Tab to accept, Esc to dismiss, or just keep typing to ignore. That is the entire user interface.

The magic is in what triggers a good suggestion. The model sees your open file, nearby files, and any comment you just wrote. The more signal you leave, the better the guess.

Try this exact experiment

Open a new Python file named greetings.py
Type a single comment describing the function you want
Press Enter and wait two seconds
The AI will draft the whole function as ghost text
Press Tab to accept, then read every line

# Function that takes a name and a time of day (morning, afternoon, evening)
# and returns a friendly greeting string.

def greet(name, time_of_day):
    greetings = {
        "morning": "Good morning",
        "afternoon": "Good afternoon",
        "evening": "Good evening",
    }
    prefix = greetings.get(time_of_day, "Hello")
    return f"{prefix}, {name}!"One comment in, one working function out. This is the smallest possible AI-assisted coding loop.

What to do the moment it finishes typing

Read every line out loud in your head
Ask: does the dictionary cover all three cases I named?
Ask: what happens if time_of_day is something weird like None?
Run the function with a real name and see the output

Pro tip: type the function signature first

If you type the function name and its parameters first, the AI has to fit its body to your shape. That gives you more control than letting it invent everything. Builders who write signatures first get noticeably better suggestions.

Writing the first line of a function is the most valuable line of code you can write.
— An old engineering saying, still true with AI

The big idea: autocomplete is a conversation through your comments and signatures. Leave good breadcrumbs, and the AI will follow them to useful code.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-first-completion-builders

What is the term for the gray suggested code that appears directly at your cursor location in an AI code completion tool?
1. Ghost text
2. Suggestion overlay
3. Code shadow
4. Live preview
A developer sees gray text appear after writing a comment. They want to accept the suggestion. Which key should they press?
1. Tab
2. Enter
3. Escape
4. Ctrl+Space
A developer wants to make a suggestion disappear without accepting it. Which key is recommended for dismissing ghost text?
1. Backspace
2. Escape
3. Ctrl+Z
4. Shift+Tab
Which of the following provides the most signal for an AI autocomplete system to generate a useful code suggestion?
1. The file's creation date
2. The programmer's username
3. The operating system version
4. A detailed comment describing the desired function
Why is it recommended to read ghost text out loud after it appears?
1. Because the computer needs verbal confirmation
2. Because the AI will remember that you read it
3. Because reading aloud is required to accept the suggestion
4. Because fluent-looking code can still contain logical errors
A developer writes a function signature first (def greet(name, time_of_day):) before letting AI complete the body. What is the main advantage of this approach?
1. The function will run faster
2. The AI must fit its suggestion to the exact parameters and return type the developer defined
3. The code will automatically be commented
4. The AI will use less memory
What happens if you type a function's name and parameters before accepting any AI suggestion?
1. The AI ignores those details and generates whatever it wants
2. The AI becomes confused and stops suggesting code
3. The AI adjusts its suggestion to match your specified parameters and return expectations
4. The function automatically executes
A developer writes a comment saying 'function that calculates area of a circle' but the AI generates code for a rectangle. Why might this happen?
1. The comment syntax was wrong
2. The AI deliberately ignored the comment
3. The AI can only read comments in certain file types
4. The comment was ambiguous enough that the AI made an incorrect guess
What should a developer do immediately after seeing ghost text appear for a function they requested?
1. Post the code to a forum
2. Immediately run the code without reading
3. Read every line and verify it handles edge cases
4. Delete the file and start over
A student writes a comment 'make a function' and expects perfect code. The AI generates something unexpected. What went wrong?
1. The comment was too vague to give the AI useful direction
2. The AI has a limit of 10 characters for comments
3. Comments cannot be used with Python files
4. The student should have used a different programming language
Which of these best describes the relationship between comments and autocomplete suggestions?
1. Comments serve as a way to communicate intent to the AI, guiding what code it suggests
2. Comments slow down the AI significantly
3. Comments prevent the AI from generating any code
4. Comments are automatically converted to documentation
Why might accepting ghost text without reading it introduce bugs into your code?
1. Because unread code cannot be executed
2. Because the AI requires you to read before accepting
3. Because suggestions can look fluent and correct while containing logic errors
4. Because accepting without reading is technically impossible
The quote 'Writing the first line of a function is the most valuable line of code you can write' emphasizes the importance of what?
1. Writing variable names in all capitals
2. Writing comments at the top of files
3. Writing a clear function signature to guide AI suggestions
4. Writing tests before code
A developer notices the AI suggested a dictionary with only two cases, but their comment mentioned three cases. What should they check?
1. Whether the comment uses proper grammar
2. Whether the file is saved
3. Whether the suggestion actually covers all the cases mentioned in the comment
4. Whether the AI has internet access
What does the lesson mean when it says 'autocomplete is a conversation through your comments and signatures'?
1. You must talk to the AI out loud while coding
2. The AI sends you emails about your code
3. You provide intent through comments and signatures, and the AI responds with code suggestions
4. The autocomplete feature includes a chat bot

← Back to interactive lesson

Tendril · Builders · AI-Assisted Coding

Your First Copilot-Style Completion

Let's actually feel what autocomplete is like. Write a comment, pause, and watch a full function appear. Then learn what to do next.

30 min · Reviewed 2026

Ghost Text, Meet Real Text

Autocomplete shows suggested code in gray right where your cursor is. This is called ghost text. Press Tab to accept, Esc to dismiss, or just keep typing to ignore. That is the entire user interface.

The magic is in what triggers a good suggestion. The model sees your open file, nearby files, and any comment you just wrote. The more signal you leave, the better the guess.

Try this exact experiment

Open a new Python file named greetings.py
Type a single comment describing the function you want
Press Enter and wait two seconds
The AI will draft the whole function as ghost text
Press Tab to accept, then read every line

# Function that takes a name and a time of day (morning, afternoon, evening)
# and returns a friendly greeting string.

def greet(name, time_of_day):
    greetings = {
        "morning": "Good morning",
        "afternoon": "Good afternoon",
        "evening": "Good evening",
    }
    prefix = greetings.get(time_of_day, "Hello")
    return f"{prefix}, {name}!"One comment in, one working function out. This is the smallest possible AI-assisted coding loop.

What to do the moment it finishes typing

Read every line out loud in your head
Ask: does the dictionary cover all three cases I named?
Ask: what happens if time_of_day is something weird like None?
Run the function with a real name and see the output

Pro tip: type the function signature first

Writing the first line of a function is the most valuable line of code you can write.
— An old engineering saying, still true with AI

The big idea: autocomplete is a conversation through your comments and signatures. Leave good breadcrumbs, and the AI will follow them to useful code.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-first-completion-builders

What is the term for the gray suggested code that appears directly at your cursor location in an AI code completion tool?
1. Ghost text
2. Suggestion overlay
3. Code shadow
4. Live preview
A developer sees gray text appear after writing a comment. They want to accept the suggestion. Which key should they press?
1. Tab
2. Enter
3. Escape
4. Ctrl+Space
A developer wants to make a suggestion disappear without accepting it. Which key is recommended for dismissing ghost text?
1. Backspace
2. Escape
3. Ctrl+Z
4. Shift+Tab
Which of the following provides the most signal for an AI autocomplete system to generate a useful code suggestion?
1. The file's creation date
2. The programmer's username
3. The operating system version
4. A detailed comment describing the desired function
Why is it recommended to read ghost text out loud after it appears?
1. Because the computer needs verbal confirmation
2. Because the AI will remember that you read it
3. Because reading aloud is required to accept the suggestion
4. Because fluent-looking code can still contain logical errors
A developer writes a function signature first (def greet(name, time_of_day):) before letting AI complete the body. What is the main advantage of this approach?
1. The function will run faster
2. The AI must fit its suggestion to the exact parameters and return type the developer defined
3. The code will automatically be commented
4. The AI will use less memory
What happens if you type a function's name and parameters before accepting any AI suggestion?
1. The AI ignores those details and generates whatever it wants
2. The AI becomes confused and stops suggesting code
3. The AI adjusts its suggestion to match your specified parameters and return expectations
4. The function automatically executes
A developer writes a comment saying 'function that calculates area of a circle' but the AI generates code for a rectangle. Why might this happen?
1. The comment syntax was wrong
2. The AI deliberately ignored the comment
3. The AI can only read comments in certain file types
4. The comment was ambiguous enough that the AI made an incorrect guess
What should a developer do immediately after seeing ghost text appear for a function they requested?
1. Post the code to a forum
2. Immediately run the code without reading
3. Read every line and verify it handles edge cases
4. Delete the file and start over
A student writes a comment 'make a function' and expects perfect code. The AI generates something unexpected. What went wrong?
1. The comment was too vague to give the AI useful direction
2. The AI has a limit of 10 characters for comments
3. Comments cannot be used with Python files
4. The student should have used a different programming language
Which of these best describes the relationship between comments and autocomplete suggestions?
1. Comments serve as a way to communicate intent to the AI, guiding what code it suggests
2. Comments slow down the AI significantly
3. Comments prevent the AI from generating any code
4. Comments are automatically converted to documentation
Why might accepting ghost text without reading it introduce bugs into your code?
1. Because unread code cannot be executed
2. Because the AI requires you to read before accepting
3. Because suggestions can look fluent and correct while containing logic errors
4. Because accepting without reading is technically impossible
The quote 'Writing the first line of a function is the most valuable line of code you can write' emphasizes the importance of what?
1. Writing variable names in all capitals
2. Writing comments at the top of files
3. Writing a clear function signature to guide AI suggestions
4. Writing tests before code
A developer notices the AI suggested a dictionary with only two cases, but their comment mentioned three cases. What should they check?
1. Whether the comment uses proper grammar
2. Whether the file is saved
3. Whether the suggestion actually covers all the cases mentioned in the comment
4. Whether the AI has internet access
What does the lesson mean when it says 'autocomplete is a conversation through your comments and signatures'?
1. You must talk to the AI out loud while coding
2. The AI sends you emails about your code
3. You provide intent through comments and signatures, and the AI responds with code suggestions
4. The autocomplete feature includes a chat bot

← Back to interactive lesson