A new way to work with Agent
So far, you’ve probably worked with Agent like a partner sitting next to you: you ask, you watch, you respond. Building in parallel is a different relationship. You hand a feature to Agent as a task, and it goes off and builds it in the background while you do something else. You already work this way in everyday life. You don’t stand in front of the washing machine until it finishes. You start the laundry, then go cook. Tasks work the same way: start one, and while it runs, start another, review something else, or just keep chatting with Agent in the main conversation. This changes your role. You stop being a passenger watching one build and become the director of several.Your app is safe while tasks run
The first question everyone asks: will a background task break my app while I’m not looking? No. Each task works on its own copy of your project. Your app doesn’t change until you review a task’s work and choose to apply it. Each task also gets its own Agent and inherits your full project context, so you don’t repeat yourself. Tasks are independent: you can start the next one the moment the first is running.A worked example: three features at once
Imagine a car rental app that already handles reservations and sign-in. You want to add three features:- An events page
- Event registration
- A contact form


Slice your work small
The skill that makes parallel building work is cutting features into small, self-contained tasks. Small tasks finish faster, are easier to review, and are less likely to interfere with each other. A useful rule: if your task description contains “and”, consider splitting it.- Good: “Add an events page”, “Add a contact form”
- Too big: “Add events and registration and email notifications and an admin view”
- Add a dark mode toggle
- Add a customer reviews section
- Let customers reply to reviews
- Translate the app into French
Answer
Answer
Tasks 1, 2, and 4 are independent and can all run at once. Task 3 depends on task 2: there’s nothing to reply to until reviews exist. You don’t need to catch this yourself. Agent detects the dependency and sequences those two tasks for you.
Why you update before you apply
Here’s the one concept that trips everyone up, so let’s take it slowly. Two friends each take home a copy of the same party invitation to improve it. One adds a map. The other rewrites the schedule. You accept the first friend’s version, and it becomes the real invitation. Now the second friend’s copy has a problem: their rewrite is based on an invitation that no longer exists. Before you can accept their work, they need to redo it on the newest version. Tasks work exactly like this. Each one copied your project when it started. The moment you apply one task’s changes, every other task’s copy is one version behind. For unrelated features that’s often fine, but since you’re not reading the code, you can’t be sure two tasks didn’t touch the same thing.Review like a manager
Parallel building makes you a manager, and the classic manager mistake is approving work you didn’t check. The discipline is a simple loop, one task at a time:1
Test the task's work
Open the finished task and try the feature. Click through it like a user would.
2
Apply it
Happy with it? Apply the changes to your main app.
3
Update the next task
Before touching the next finished task, update it so it syncs with the version you just changed.
4
Repeat
Test, apply, update, until every task has landed.

When to stay sequential
Parallel building is a tool, not a rule. Stay in the main conversation, one thing at a time, when:- Two ideas touch the same screen. “Redesign the home page” and “change the navigation” will collide. Do them in order.
- You’re exploring. In design work, the result of one attempt changes what you want next. Exploration is a conversation, not a work order.
- You can’t describe the task in one sentence. If you can’t state it simply, you’re not ready to delegate it.
Find your ceiling
The limit on parallel building isn’t Replit. It’s your attention. Every time you switch between tasks, you pay a small cost in focus, and everyone’s budget is different. Start with two tasks. If reviewing them feels comfortable, try three. Agents are good enough at building that you don’t need to supervise every step, so most builders find the speed is worth the switching. But this is a skill you practice, not a setting you enable.Next steps
- Task system: The full reference for how tasks work.
- Plan and Build modes: Why tasks start with a plan.
- Vibe coding 101: The build-in-small-slices mindset that makes slicing tasks natural.