GitHub Copilot Beginner tutorial

Beginner · step 1 of 7

What GitHub Copilot is (and isn't)

GitHub Copilot is an AI pair programmer in your editor, the CLI and on github.com, with completions, chat, agent mode and code review.

Good for:

• Inline completions for small edits
• Well-scoped issues assigned to an agent
• Writing tests for named cases

Not good for:

• Vague tasks across a whole repo
• Merging agent PRs without CI

Why this step matters: Knowing what it is good and bad at stops you using it for jobs where it will fail quietly.

Beginner · step 2 of 7

Get the official app

1. Start from github.com/features/copilot or the official app store listing.
2. Check the publisher is GitHub. Copycat apps use similar names.
3. Sign in so your history is saved.

Why this step matters: Copycat apps and unofficial installers are common; starting from the official source protects your account and data.

Beginner · step 3 of 7

Your first useful prompt

Give the bot a situation, a task and the format you want. Try this:

Write pytest tests for parse_invoice() in invoices.py: the happy path, a missing total, a negative amount, and a DD/MM date. Don't change the function.

Then ask one follow-up that narrows it down.

A good result: an answer in the format you asked for (list, table or draft), built only on what you gave it, ending with one question that narrows the task. If it starts generic advice instead, add the situation sentence again.

Why this step matters: A prompt with situation, task and format gets a usable answer first time, so you learn what the tool can actually do.

Beginner · step 4 of 7

Check the answer

1. Ask for the source of any fact you'll reuse.
2. Open the link and find the exact sentence (Ctrl+F).
3. If you can't find it, treat the claim as unverified.
4. For files, check two page or row references yourself.

Before you answer: separate what you checked from what you're assuming. Write "unknown" instead of guessing. Give a link for every number.

A good result: two lists, one labelled checked (with a source or page reference for each) and one labelled assumed. Anything in the second list is what you verify before you use it.

Why this step matters: Chatbots state wrong facts in the same confident tone as right ones. Checking is the only way to tell them apart.

Beginner · step 5 of 7

Privacy basics

Install the GitHub Copilot extension (VS Code, JetBrains or Visual Studio) and sign in with the same GitHub account.

• Don't paste passwords, ID numbers, card numbers or other people's private details.
• Assume the company can read and keep your chats unless its official policy says otherwise.
• For health, money or legal decisions, confirm with a professional or an official source.

Why this step matters: Anything you paste may be stored and read. Deciding what never goes in is easier than undoing a leak.

Beginner · step 6 of 7

What it costs

Pro $10/mo, Pro+ $39/mo, Max $100/mo, each with base plus flex credits. Set an extra-usage budget; alerts come at 75%, 90% and 100%. A $0 budget means no overage (GitHub).

Full plan table: GitHub Copilot step-by-step tutorial.

Why this step matters: Paying for features you don't use is the most common waste. Knowing the limits first tells you if the free tier is enough.

Beginner · step 7 of 7

Your first week

1. Day 1: three real tasks from your week.
2. Day 3: compare its answers with what you'd have done.
3. Day 7: decide if it's worth paying, based on what you actually used.

Why this step matters: A week of real tasks gives you evidence for whether it saves time, instead of a first impression.