Autonomous Development with Wing Pro
Pro Only
Wing Pro includes an autonomous software development system. You provide a high-level specification for a new product or a major feature. Wing's Tasks Manager researches and fleshes out the specification, plans the work, splits it into tasks, and assigns them to a team of AI agents. It keeps the agents moving and on track for hours or days, as needed to complete the work. The agents write the code, unit tests, and documentation, commit in logical units, and find and fix bugs along the way.
Instead of reading individual agent sessions, you answer questions and review results in the Tasks tool. Each finished task reports a summary of its changes and decisions made. You can look at the code and diffs for any change, but the task and decision summaries are often the better level at which to ask for revisions. Your job is to describe what you want, answer strategic questions, and review the finished work. You are the product designer, and the agents do the rest.
This document explains how to get started with autonomous development. It assumes you already have your AI agent set up in Wing. If not, see Using Wing with an AI Agent first.
Getting Started
We recommend running agents in a reasonably isolated environment, such as a virtual machine. At the very least, agents should not be able to reach the keys to your server infrastructure, read sensitive data, or push to your main repository. Agents do not in general try to reach data or systems outside the scope of your requests, but these precautions are worth taking, particularly if you are using an agent other than Claude Code or Codex. See AI Agent Safety for details.
Claude Code and Codex are best for autonomous development, since their Auto-Approve feature checks the safety of each step. Antigravity, Copilot, and Cursor also run the Manager well, but without those safety checks. goose and OpenCode are not recommended. The table in AI Agent Safety compares them.
Setting Up Autonomous Development
(1) Create a new project with New Project... in the Welcome to Wing window when you start Wing, or later with New Project in the Project menu. The dialog opens in its Simple view. To start from scratch, choose New directory at the top of the dialog, enter a Name, and choose where to create it. Choose your agent with Set Up for AI Agent. In most cases you can leave the rest of the fields set to their defaults, which will create a new virtualenv and git repository along with the project.


After you press Create Project, Wing shows each step of creating the project and sets it up for use with your AI agent.
Note that you can also choose Existing directory in the New Project dialog, for code you already have, but it's better to just try things out with a new project when you are just getting started, particularly if your existing code isn't yet in revision control.
(2) Check the Tasks Manager's settings. The Manager's bar is at the top of the Execute tab of the Tasks tool. To review or change its settings, click the settings icon at the right of that bar. They control task scheduling, agent permissions, and whether code is committed automatically:


The default settings are a good place to start. Turning off automatic commits on the Commits tab keeps work from going on autonomously for long periods, since uncommitted work holds up later tasks that touch the same files until you review and commit it. We recommend leaving it on. You can still look over every committed task on the Review and History tabs, and request any changes you want. See Tasks Manager Settings for all of its settings.
A project that was set up without the autonomous Tasks Manager shows Turn On in the Manager's bar in the Execute tab of the Tasks tool. Pressing that shows the same settings and allows you to start the Manager.
(3) Write a specification or tasks. On the Plan tab of the Tasks tool, add one or more tasks and mark them Ready by clicking their Draft pill. A task can be anything from a bug report to a high-level specification for a whole new application. To try this out, start with a substantial task such as development of a new custom website. Your specification should describe the purpose and key features, and any technical constraints that matter from the start, but it doesn't need to be detailed about the internal design of the code. It's fine to be unsure how some of it will work or be packaged. If you focus on what the code should do, the Manager researches and fleshes out the plan, asks you questions along the way, and writes out tasks on the Plan tab, ready to run. This works for an empty project as well as an existing one. See Usage Tips below for help getting good results.


The Manager starts running tasks after you mark them Ready. You can watch its progress on the Execute tab of the Tasks tool. The Queues view shows the tasks of one queue at a time; click a queue's name to watch its session in the AI Agent tool. The Up Next view shows what tasks are running or will run next.
Problems that agents notice along the way, and follow-up tasks the Manager proposes, are added as drafts to the Plan tab. The Manager runs closely related ones right away, and leaves the rest for you to review, delete, or mark Ready.
(4) Answer questions. The Manager uses the Questions tab to ask about anything holding up decisions and progress, with an orange count on the tab. The Manager answers some questions itself when its research finds the answer, and may start other tasks while one waits for you.


You can also talk to the Manager directly, by typing into the Tell the Manager... area on the Execute tab or typing directly into the Manager's session in the AI Agent tool. Ask it about task status, tell it your preferred development workflow, or give it instructions such as "work autonomously but ask me first about anything that changes a file format." It can remember your instructions in a local memory, or project-wide in files that are committed and shared with other developers. To tell a running task something new, click Send Note on its row on the Execute tab.
(5) Review finished work. Finished tasks move from the Execute tab to the Review tab. Each reports a summary of the decisions and changes it made, with the reasoning and the alternatives it considered. If you commit work yourself, use Start Review to view and comment on the changes in a side-by-side diff, or Commit to commit them without detailed review. If the Manager committed the work, you can still read its report and use Revise to ask for changes to any of its decisions or to the task as a whole. Comments you add while reviewing code are addressed by the Manager or a worker agent.


Research and planning tasks offer Read Report or Read Plan, and Make Tasks, which opens a dialog to choose which steps of the plan become tasks. Its Save Draft button files them as Draft tasks on the Plan tab to run later, and Run Now has the Manager schedule and run them right away. See Reviewing Tasks for details.
Deciding When to Move to Autonomous Development
When to start using autonomous development is up to you. If you are new to agentic development, you may prefer to start by running tasks yourself in Wing, as described in Using Wing with an AI Agent, and review every change at the code level.
Your comfort with this will change over time. Once agents write and run tests reliably for your project, and you find yourself committing after reading only a task's report, you are ready to move on to autonomous development.
Your focus then shifts from individual agents and their output to specifying tasks, answering questions, and reading completion summaries, and you rarely if ever need to look at the code itself.
Usage Tips
These habits make autonomous development smoother and its results better:
Treat the Manager like a development team
Describe what you need rather than how to implement it. If something about the process is clunky, you don't know how to fit Wing into your existing workflow, or you aren't happy with some part of your application but don't know what to change, ask the Manager for help. It can investigate and solve most problems, much as an experienced developer would.
Let agents see your application
Ask the Manager early on to set up a way for it to see your application as you would. If you are writing a GUI application, also ask for test windows to be shown offscreen, so you can keep working while agents run tests.
Make sure agents write tests
Wing tells agents to write and run tests, but you may need to give them a nudge in some projects that don't yet have them. Tests are important because they force workers to fix problems in new code before they stop working.
The Testing Regimen on the AI Agent tab of Project Properties can be used to get specific about when agents should write and run tests.
Run reviews at key points
You can set up recurring tasks on the Checklists page of the Tasks tool to run routine checks for issues like security flaws, data loss bugs, gaps in test coverage, missing functionality, compatibility problems between versions, or anything else that matters to you.
Run these before pushing or merging code. Each review might turn up issues that become new tasks, which agents then fix.
Commit automatically on a separate branch
For development that goes on for long periods of time and commits work automatically, it's best to create and use a distinct revision control branch. That makes it easier to compare changes made by a particular development run, and makes sure that nothing goes into your main branch until you want it to.
Describe your workflow and policies
You can make choices about testing regimen and agent permissions on the AI Agent tab of Project Properties and in the Manager's settings, accessed from the settings icon in the Manager area of the Execute tab. Or talk to the Manager directly with the Tell the Manager... field on its bar, or in its session in the AI Agent tool. Be sure to tell it when policies are private or should be shared with other developers, so it knows where to remember them.
See Configuration for configuration details.
Use the application yourself
If possible, use your application as an end user and add tasks for bugs that need fixing and improvements you would like to see. In a very real sense, Wing and the Tasks Manager are now your development team. All you need to do is to tell them what you want.
See Using AI Agents Effectively for more guidance.
Related Documents
For more information see:
- AI Agent-Assisted Development documents Wing's AI agent features in detail, including AI Agent Safety, Setting Up an AI Agent, The Tasks Manager Agent, and Using AI Agents Effectively.
- Using Wing with an AI Agent describes the AI agent features and workflow common to all agents.
- The Autonomous Tasks Manager in the Tutorial walks through running tasks with the Manager.
- The demos on Wingware's website are complete projects built with the Tasks Manager, each with its code and a record of every task the Manager ran to build it.
- Wing Reference Manual documents Wing in detail.