Amazon Q Developer: full guide & setup (2026).
Amazon Q Developer is AWS's AI coding assistant. It does inline completion, an in-IDE chat, multi-file feature agents (/dev), managed code upgrades (/transform), unit-test and documentation generation, and security scanning — across VS Code, JetBrains, Visual Studio, the CLI, and the AWS console. This guide covers every feature, the supported IDEs and languages, Free vs Pro pricing, how it stacks up against GitHub Copilot and Cursor, and how to set it up for a whole team.
- Update, October 2026: AWS says it will end support for the Amazon Q Developer IDE plugins on April 30, 2027, and points IDE users to Kiro for similar features (agentic coding, chat and MCP support). The notice names the IDE plugins, so plan new IDE rollouts with that date in mind.
- Amazon Q Developer is an AI coding assistant that lives in your IDE, CLI, and the AWS console. Beyond autocomplete it ships agents: /dev implements a multi-file feature from a prompt, /transform runs guided code/language upgrades, and it generates unit tests, docs, and security-scan findings — with deep AWS awareness baked in.
- It works in VS Code, JetBrains IDEs, Visual Studio, and Eclipse, plus a command-line agent and an assistant inside the AWS Management Console. It supports 15+ languages, with the strongest depth in Python, Java, JavaScript/TypeScript, C#, and Go.
- Pricing is two tiers: Free (capped, no AWS account needed to try) and Pro at about $19/user/month with higher limits, org license management via IAM Identity Center, and policy controls. On Pro, your content is not retained or used to train the model; the Free tier’s data settings differ, so check them. Confirm current pricing on the AWS pricing page.
IWhat Amazon Q Developer is
Amazon Q Developer is the coding half of the Amazon Q family — an AI assistant aimed at the full software lifecycle, not just autocomplete.
Amazon Q Developer is AWS's generative-AI assistant for software development. It is the successor to and superset of what AWS previously shipped as CodeWhisperer: it kept the inline code suggestions and added a chat interface, autonomous agents, code transformation, test and documentation generation, and security scanning. If you remember CodeWhisperer, Q Developer is that capability folded into the broader Amazon Q brand and substantially expanded.
It is built on Amazon Bedrock, so it inherits AWS's managed-inference data posture. The distinction that matters: Q Developer is a finished product where AWS manages the model for you, whereas Amazon Bedrock gives you raw model-level API access to build your own tools. You do not choose the model inside Q Developer; you choose the tier and configure how your team uses it.
Q Developer is one of two products under the Amazon Q name. Its sibling, Amazon Q Business, is an enterprise assistant that answers questions over your company data and is not a coding tool. If you landed here unsure which you need, the parent overview — Amazon Q: the complete guide — disambiguates the family.
The mental model: think of Q Developer less as "autocomplete with AWS branding" and more as "an AI teammate that can complete code as you type, answer questions about your codebase and your AWS account, take on a scoped feature, upgrade a legacy codebase, and flag security issues — without leaving your editor."
IIEvery Amazon Q Developer feature, explained
Q Developer is a bundle of distinct capabilities. Here is what each one does and when you reach for it.
It helps to group the features into three layers: (1) in-the-flow assistance while you type, (2) agents that take on a whole task, and (3) quality and safety tooling. The agentic layer — /dev and /transform — is what most distinguishes Q Developer from a pure completion tool.
In-the-flow assistance
- Inline code completion: Real-time, multi-line suggestions as you type, informed by your surrounding code, comments, and open files. Accept, cycle, or ignore — the standard pair-programmer loop.
- Chat in the IDE: A conversational panel for “how do I…”, “explain this function”, “refactor this”, or “why is this failing?” — grounded in the file or selection you have open.
- Inline chat / edit: Select code and ask for a change in place; Q proposes an edit you can apply directly in the editor.
- AWS-aware answers: Q Developer can reason about AWS services and, in the console, about your actual account and resources — answering AWS questions and diagnosing errors with that context.
Agents that take on a task
- /dev — feature agent: Describe a feature or change in natural language; the agent explores the repository, drafts an implementation plan across multiple files, and proposes the code changes for you to review and accept. It is for scoped tasks, not “build my whole app.”
- /transform — code transformation & upgrades: Guided, large-scale code transformations — most notably language/framework version upgrades (for example migrating older Java applications to a newer LTS). It analyzes the codebase, applies the changes, and surfaces what it did for review. This is a signature differentiator.
- Test generation: Generate unit tests for a function or file, including edge cases, to raise coverage with less manual effort.
- Documentation generation: Produce or update inline docs, README content, and code explanations from the code itself.
Quality & safety
- Security scanning: Scans your code for vulnerabilities and insecure patterns and proposes remediations — bringing a security pass into the editor rather than waiting for a later pipeline stage.
- Code references / attribution: When a suggestion resembles public training data, Q can flag the reference so you can make an informed licensing decision.
- Customization (Pro): On the Pro tier, organizations can customize completions to their own internal libraries and codebases so suggestions reflect house patterns and private APIs, not just public code.
IIISupported IDEs, the CLI & languages
Q Developer meets engineers where they already work — across the major IDE families, the terminal, and the AWS console.
IDEs. Amazon Q Developer is available as an extension/plugin for Visual Studio Code, the JetBrains family (IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider, and others), Visual Studio, and Eclipse. In each, you get both inline completion and the chat experience.
Command line. The Q Developer CLI agent (on macOS and Linux) completes commands, explains errors, and can translate a natural-language request into the right shell command — useful for ops and for anyone who lives in the terminal.
AWS Management Console & chat. Inside the console, Q Developer is an always-available assistant for AWS questions and troubleshooting. It is also reachable from Slack and Microsoft Teams via AWS Chatbot, so you can ask about your AWS resources without switching tools.
Languages. Q Developer supports 15+ programming languages. Depth is strongest in Python, Java, JavaScript/TypeScript, C#, and Go, with solid support for Rust, Ruby, PHP, Kotlin, C/C++, SQL, shell, and infrastructure-as-code (CloudFormation, CDK, Terraform). As with any AI assistant, suggestion quality tracks how well-represented a language and framework are.
| Surface | Inline completion | Chat | Agents (/dev, /transform) | Notes |
|---|---|---|---|---|
| VS Code | Yes | Yes | Yes | Most complete experience |
| JetBrains (IntelliJ, PyCharm, etc.) | Yes | Yes | Yes | Broad JetBrains family coverage |
| Visual Studio | Yes | Yes | Partial | Core completion + chat; some agent features evolving |
| Eclipse | Yes | Yes | Partial | Newer integration; check feature parity |
| CLI (macOS/Linux) | Command completion | Yes | n/a | Natural-language → shell; error explanation |
| AWS Console | n/a | Yes | n/a | AWS-aware help & troubleshooting |
IVAmazon Q Developer pricing: Free vs Pro
Two tiers, one per-seat decision. The figures below are representative as of 2026 — confirm current rates on the AWS pricing page.
Free tier. Individual developers can use Q Developer at no cost with a Builder ID — no AWS account required. The Free tier includes inline completion and chat, plus a capped monthly allowance of the heavier features (agent interactions such as /dev and /transform, and security scans). It is genuinely usable for solo work and for evaluating the product.
Pro tier. At roughly $19 per user per month, Pro raises the limits and adds the things teams need: centralized license management and access control through IAM Identity Center, administrative policy controls, customization to your private codebase, higher caps on agent interactions and security scanning, and the enterprise data-handling terms (your content is not retained or used to train the model). Pro is billed per active subscribed user.
Usage beyond the seat. Some high-volume agentic work — large code transformations in particular — can incur additional usage-based charges on top of the Pro seat, depending on the scale of the job. For most teams the predictable cost is simply seats × monthly price; model the transformation usage separately if you plan a big migration program.
| Capability | Free | Pro (~$19/user/mo) |
|---|---|---|
| Inline completion + chat | Yes | Yes |
| Agents (/dev, /transform) | Capped per month | Higher limits |
| Security scanning | Capped per month | Higher limits |
| Customization to private code | No | Yes |
| Org license mgmt (IAM Identity Center) | No | Yes |
| Admin policy controls | No | Yes |
| Content not retained / not used to train | Differs — check settings | Yes |
VAmazon Q Developer vs GitHub Copilot vs Cursor
The three tools most teams weigh against each other. A brief, honest read — the deep coding head-to-head lives on the dedicated comparison page.
GitHub Copilot is the market leader, tightly integrated with GitHub (pull requests, Codespaces) and now multi-model with a large IDE ecosystem and the broadest mindshare. Cursor is an AI-first editor (a fork of VS Code) prized for fast, agentic, whole-codebase editing and a slick UX, popular with developers who want the most aggressive AI workflow. Amazon Q Developer differentiates on AWS awareness, managed /transform upgrades, security scanning in-editor, and being governed inside your AWS account.
The decision usually comes down to gravity. If your team lives in GitHub and wants the safest, most widely adopted choice, Copilot is the default. If you want the most cutting-edge agentic editing experience and are happy to switch editors, Cursor is compelling. If your stack is AWS-heavy, you value managed legacy-code upgrades, and you want the assistant governed by the same IAM and account controls as the rest of your infrastructure, Q Developer is the natural fit.
For the detailed feature-by-feature breakdown against Copilot specifically — completion quality, agents, pricing, enterprise controls — see Amazon Q vs GitHub Copilot.
VIEnterprise setup & admin
Rolling Q Developer Pro out to a team is a short, well-trodden path through IAM Identity Center. Here is the shape of it.
For a larger rollout (wiring SSO, scoping customization across many repos, setting policy guardrails and measuring adoption), a vetted AWS partner can do the setup. CloudRoute can match you with one. See the next section.
- Enable the Pro subscription: In the Amazon Q Developer console, set up a Pro subscription for your organization. This is where licenses are managed centrally rather than per individual.
- Connect identity via IAM Identity Center: Federate to your existing identity provider (Okta, Microsoft Entra ID, Ping, etc.) so engineers sign in with corporate SSO and you assign/revoke Q access through groups.
- Assign seats to groups: Grant Pro access to the right teams via IAM Identity Center groups; deprovisioning is automatic when someone leaves the group.
- Set policy controls: Configure organizational settings — for example whether code-reference suggestions are allowed, and how customization is scoped — to match your compliance posture.
- Configure customization (optional): Point Q at approved internal repositories so completions reflect your private libraries and conventions. Customizations are isolated to your organization.
- Distribute the IDE extensions: Have engineers install the Q extension in VS Code / JetBrains / Visual Studio / Eclipse and sign in with corporate credentials; standardize via your usual extension-management tooling.
VIIData handling & IP — what happens to your code
For engineering leaders and security teams, this is the gating question. The short answer differs by tier.
On the Pro tier, your content — the code you write, your prompts, and your customization data — is not used to train the underlying foundation models and is handled under AWS's enterprise data terms. Customizations built on your private code are isolated to your organization and are not shared with other customers. Because Q Developer runs on Amazon Bedrock inside AWS's managed environment, the same data-boundary and regional guarantees that apply to Bedrock apply here.
On the Free tier, the data settings differ: by default some content may be used to improve the service unless you opt out, so individual users who care about this should review and adjust the data-sharing setting. For any team handling proprietary or regulated code, the Pro tier is the right choice precisely because of these stronger, default data-handling terms.
IP and licensing. The code-references feature flags suggestions that closely match public training data so you can decide whether to accept them and how to handle attribution/licensing — a meaningful control for organizations worried about inadvertently incorporating restrictively licensed code.
Auditability. Administrative controls and AWS logging let security teams see how Q is configured and used across the organization, so it can be governed with the same tooling already applied to the rest of the AWS estate.
On Pro, Amazon Q Developer does not use your code or prompts to train its models, and customizations stay isolated to your org. On Free, review the data-sharing setting and opt out if needed. Regulated teams should standardize on Pro.
VIIIGetting started in five minutes
Step 1 — Install. Add the Amazon Q extension from your IDE's marketplace (VS Code, JetBrains, Visual Studio, or Eclipse). For the CLI, install the Q command-line tool on macOS or Linux.
Step 2 — Sign in. Use a free Builder ID to start on the Free tier immediately — no AWS account needed. For Pro, sign in with the corporate identity your admin set up in IAM Identity Center.
Step 3 — Try inline completion. Open a file and start typing or write a descriptive comment; accept Q's suggestion to feel the loop.
Step 4 — Open chat and ask. Use the Q panel to explain a function, refactor a selection, or ask an AWS question. Then try an agent: /dev for a scoped feature, or /transform on a sample project to see a managed upgrade.
Step 5 — Decide on Pro. If you hit the Free-tier caps, want private-code customization, need SSO-managed licenses, or require the stronger data-handling terms, move the team to Pro through IAM Identity Center.
When the goal is a measured, organization-wide rollout, not just one developer trying it, CloudRoute can match you with a vetted AWS partner who handles the setup and adoption. If the rollout is part of new work on AWS, the partner can check whether it qualifies for POC or incremental workload (IW) funding.
Amazon Q Developer vs GitHub Copilot vs Cursor — at a glance
A scannable read across the three AI coding tools teams most often shortlist. Pricing is representative for 2026 and varies by tier/region — confirm on each vendor's page.
| Dimension | Amazon Q Developer | GitHub Copilot | Cursor |
|---|---|---|---|
| Form factor | IDE extension + CLI + AWS console | IDE extension + GitHub | Standalone AI-first editor (VS Code fork) |
| Standout strength | AWS awareness + /transform upgrades + security scan | Ecosystem, adoption, GitHub & PR integration | Aggressive whole-codebase agentic editing |
| Agents | /dev (feature), /transform (upgrades) | Copilot agents & coding agent | Composer / agent editing |
| Free tier | Yes (capped) | Limited free for individuals | Limited free tier |
| Paid (per user/mo) | ~$19 (Pro) | ~$10–$39 (Pro/Business/Enterprise) | ~$20 (Pro) |
| Code not used to train | Yes (Pro) | Yes (Business/Enterprise) | Yes (privacy mode) |
| Best for | AWS-heavy teams; legacy upgrades; governed in-account | GitHub-centric teams wanting the safe default | Devs wanting the most cutting-edge AI editor |
How a match works (example)
- You tell us about the work
You fill in a short form: what you run today, what you want to move, test or build, your stage and your region.
- We pick one partner
We read your answers and pick one vetted AWS consulting partner that fits the work, the stack and the region. We reply within 24 hours; your matched partner reaches out within 5 business days.
- The partner checks POC funding
Your matched partner scopes the test with you. Then it checks whether the test qualifies for POC (proof of concept) funding. A POC can fit whether or not you run on AWS today.
- The partner files, AWS decides
If the work qualifies, the partner files the funding request with AWS. AWS reviews it and decides. The amount depends on the workload.
- You pay nothing
CloudRoute is free for startups. Partners pay CloudRoute a monthly membership plus 10% of AWS-approved funding.
AWS Activate credits are separate, and you apply for them yourself. Use Activate Founders if no investor backs you. Use Activate Portfolio with the Org ID or invite from your VC, accelerator, incubator or angel group if it is an Activate Provider. A consulting partner cannot apply for Activate on your behalf.
Common questions
What is Amazon Q Developer?
How much does Amazon Q Developer cost?
Which IDEs and languages does Amazon Q Developer support?
What is the difference between Amazon Q Developer and GitHub Copilot?
Does Amazon Q Developer use my code to train its model?
What does /transform do?
Is Amazon Q Developer the same as CodeWhisperer?
How do I roll Amazon Q Developer out to a whole team, and can AWS credits help?
Want AI coding tools rolled out across your team, properly?
CloudRoute matches you with one vetted AWS partner who handles setup, SSO, customization and adoption. If the work is part of new AWS work that qualifies, the partner files POC or incremental workload (IW) funding, and AWS decides. Startups pay CloudRoute nothing.