Logo Amp Owner’s Manual

Congratulations on installing Amp. This manual helps you get the most out of it.

Introduction

What is Amp?

Amp is an agentic coding tool built by Sourcegraph. It runs in VS Code (and compatible forks like Cursor, Windsurf, and VSCodium) and as a command-line tool. It’s also multiplayer — you can share threads and collaborate with your team.

Principles

  1. Amp is unconstrained in token usage (and therefore cost). Our sole incentive is to make it valuable, not to match the cost of a subscription.
  2. No model selector, always the best models. You don’t pick models, we do. Instead of offering selectors and checkboxes and building for the lowest common denominator, Amp is built to use the full capabilities of the best models.
  3. We assume that you want to access the raw power these models have to offer.
  4. Built to change. Products that are overfit on the capabilities of today’s models will be obsolete in a matter of months.

Getting Started

Sign in to ampcode.com and follow the instructions to install Amp in VS Code (or compatible forks like Cursor, Windsurf, and VSCodium) and the CLI.

Using Amp

How to Prompt

Amp currently uses Claude 3.7 Sonnet. For the best results, follow these guidelines:

  • Be explicit with what you want. Don’t try to make the model guess.
  • In Amp, you need to press Cmd/Ctrl+Enter to submit a message, not just Enter, to remind you to be deliberate with your requests.
  • Break very large tasks up into smaller sub-tasks, one per thread.
  • Use a project AGENT.md file to guide Amp on how to run your tests and build steps and to avoid doing inappropriate things.

Here are some examples of prompts we’ve used with Amp:

  • “Look at src/my/file.ext and extend it so that it sends the requests only every 200ms. Add tests in the existing test file.”
  • “Run <build command> and fix all the errors”
  • “Look at <local development server url> to see this UI component. Then change it so that it looks more minimal. Frequently check your work by screenshotting the URL.”
  • “Run git blame on the file I have open and figure out who added that new title”
  • “Run git diff to see the code someone else wrote; review the code thoroughly and point out any potential edge cases that were missed”
  • “Run git diff to see the current changes, remove debug statements”
  • “Find the commit that added this using git log, look at the whole commit, then help me change this feature”
  • “Explain the relationship between class AutoScroller and ViewUpdater using a diagram”
  • “Use psql to connect to my local database, then rewire all uploads in the image uploads table to be owned by my user, bob@example.com”

Also see Thorsten Ball’s How I Use Amp.

If you’re on a team, use Amp’s thread sharing to learn from each other.

AGENT.md

An AGENT.md file in your workspace provides the AI model with project-specific information about your codebase structure, development practices, and coding standards. Amp includes a button to generate one automatically if it doesn’t exist.

Planned: Support for scoped AGENT.md files in subdirectories and other more granular agent guidance.

Uploading Images

Amp supports image uploads, allowing you to share screenshots, diagrams, and visual references with the AI. Images can provide important context for debugging visual issues or understanding UI layouts.

To upload images, you can:

  • Copy and paste directly into the input area
  • Hold Shift while dragging files over the input area

Mentioning Files

You can mention files directly in your prompts by typing @ followed by a pattern to fuzzy-search. It can help speed up responses by avoiding the need to search the codebase.

Threads

Threads are conversations with the agent, containing all your messages, context, and tool calls. Your threads are synced to ampcode.com. If you’re on a team, your threads are also shared with your team by default, just like Git branches on a shared remote repository.

Including links to Amp threads with your changes when submitting for code review helps provide context. Reading and searching your team’s threads can help you see what’s going on and how other people are using Amp.

Privacy & Permissions

Threads can be public (visible to anyone on the internet with the link), team-shared (visible to your team members), or private (visible only to you).

If you’re on a team, your threads are shared by default with your team members.

If you are not on a team, your threads are only visible to you by default.

You can change a thread’s visibility at any time through the sharing menu at the top of the thread.

Managing Context

As you work with Amp, your thread accumulates context. Amp shows your token usage and warns when approaching limits, e.g. 80% of 168k tokens.

When a thread gets too large, you can hover over the token usage indicator and use the following:

  • Compact Thread — Summarizes the existing conversation to reduce token usage while preserving context
  • New Thread with Summary — Creates a fresh thread that starts with a summary of the current conversation

File Changes

Amp tracks changes that the agent makes to files during your conversation, which you can track and revert:

  • Hover over the files changed indicator (located just above the message input) to see which files were modified and by how much
  • Revert individual file changes, or all changes made by the agent

Editing a message in a thread automatically reverts any changes the agent made after that message

Teams

Teams provide collaborative workspaces where knowledge can be shared across your organization. Create a team from the settings page. To join a team, you need an invitation from an existing team member.

Sharing

Team threads are visible to all team members by default, making it easy to learn from others and build on their work.

Usage Credits

Teams provide pooled billing of usage credits, making it easier to manage costs across your organization. If a member of your team joins with free personal credits available, their free credits will be used before the paid team credits.

Leaderboard

Each team includes a leaderboard that tracks thread activity and contributions from team members, encouraging engagement and highlighting active participants.

Tools

Tools are what the underlying model uses to assist with tasks. For the highest quality results we recommend you use a curated set of tools, with prompts adjusted to fit the underlying model.

Built-in Tools

Amp comes with a curated set of built-in tools specifically designed for coding. You can find the list of built-in tools inside Amp’s extension settings.

Custom Tools

You can extend Amp’s capabilities through the Settings interface by adding MCP servers. These servers provide additional tools for specific needs. For best results, use MCP servers that expose a small number of high-level tools with high-quality descriptions.

Command Allowlisting

Amp has a built-in safety system specifically for terminal commands that determines which commands require explicit permission before execution.

By default, Amp automatically allows certain read-only and safe commands like ls, cat, and git status. Common development commands like go test, cargo build, and pnpm run build are also pre-approved. For all other commands, Amp will prompt for permission before execution to protect your system.

You can configure Amp to execute additional commands without prompting for permission each time by adding them to the "amp.commands.allowlist" array in your extension or CLI settings:

"amp.commands.allowlist": [
    "pnpm exec tsc --build",
    "pnpm -C web check",
    "pnpm -C server test"
]

Both the Amp extension and CLI use this same setting format. You can use simple command patterns like make build or wildcards like npm run * --test to allow multiple similar commands.

Account

Security

See the Amp Security Reference document.

Support & Community

Join the Amp Discord to connect with the Amp team and other Amp users, share tips and tricks, and get help from the community.

For billing questions, contact amp-billing-help@sourcegraph.com.

Pricing

Credits

Upon signing up, every user gets USD $10 (1,000 credits) in free usage.

Credits are consumed based on LLM usage and usage of certain other tools (like web search) that cost us to serve. We pass these costs through to you directly with no markup, for individuals and non-enterprise teams.

Enterprise

Enterprise Amp will soon be widely available.

Enterprise credits are more expensive than individual and team credits to pay for security, authentication, and other enterprise features.

Appendix

Share with Amp Support

We may ask you to share your thread with authorized Sourcegraph staff members to help diagnose response quality issues:

  1. In the Amp sidebar in VS Code or when viewing the thread on ampcode.com, open the sharing menu.
  2. Select Share Thread with Support.

This will allow authorized Sourcegraph staff members to view your thread for debugging purposes.

News

Follow Amp's News for the changelog and other updates from the Amp team.

Frequently Ignored Feedback

See Amp's Frequently Ignored Feedback for the most common valid feedback that we've chosen to not address.