Replit AI
Replit Agent
Replit Agent uses AI to set up and create apps from scratch. Describe your app in everyday language, and it can set up and create your Replit App in minutes.
Agent uses powerful AI technology to transform your ideas into applications
and seamlessly add new features by describing what you want.
Chat with Agent in your Replit App to receive the following support:
You can access Agent in your Replit App workspace by selecting the Agent tool.
From the Agent tool, you can perform the following actions:
To communicate your request to Agent, enter a prompt in the text area.
A prompt is a natural language instruction that describes the task you want Agent to perform.
In addition to text, you can include the following data in your prompt:
You can access attachments from your prompts by opening the
Files tab
and navigating to the
A checkpoint is a comprehensive snapshot of your Replit App that captures completed work from Agent, including workspace contents, AI conversation context, and connected databases.
Agent creates meaningful checkpoints when it finishes implementing your request, ensuring you only pay for completed functionality.
When Agent receives your initial prompt to setup and create an app, it presents an implementation plan for your review.
Select Approve plan & start to let Agent start building your app.
Learn more about when and how to use these advanced features in the Dynamic Intelligence documentation.
The Progress tab shows a record of Agent’s actions. You can use it to view the following:
Features
Agent uses several industry-leading AI models to create your apps. The core technology uses the following models:
- Agent v2:
- Create full-stack apps from scratch
- Add advanced features and integrate complex APIs
- Design, create, and modify database structures
- Streamline environment setup and dependency management
Usage
Agent is available only in Replit Apps created from an Agent prompt.
How to access Agent
How to access Agent
From the Create a new App screen, select the Replit Agent tab to enter a description of the app you want as shown in the following animation:
If viewing a Replit App started by Agent, you can locate the Agent tool in your workspace in one of the following locations:From the left tool dock, select 
Agent as shown
in the following animation:From the Search bar:
Agent as shown
in the following animation:- Select the
magnifying glass at the top to open the search tool - Type “Agent” to locate the Agent tool and select it from the results
- Chat: Describe your app or feature in the text area and respond to Agent’s follow-up questions
- Add detailed requests: Upload files or import content from URLs to give Agent more information
- Manage conversations: Select New chat or select previous conversations from the
menu icon to start or resume a conversation - Track usage: Select the
usage icon at the top right to view your billing page - Reverse changes: Undo changes made by Agent by selecting
Rollback to here
Chat prompts
To communicate your request to Agent, enter a prompt in the text area.
A prompt is a natural language instruction that describes the task you want Agent to perform.
In addition to text, you can include the following data in your prompt:
- File attachments: Drag a file into the text area or select the
paperclip icon - Web content: Include text data from a webpage by entering a URL and selecting Copy page content
- Webpage screenshots: Include a screenshot of a webpage by entering a URL and selecting Take screenshot
When you select Take screenshot, Agent captures only the top of the webpage. If you must capture a different part,
use a screenshot tool to capture the content and attach the image or images.
Files tab
and navigating to the attached_assets directory.
You can also perform the following actions in the Agent prompt area:
- Prompt refinement: Let AI add detail to your first prompt by selecting
Improve prompt - Feedback: After Agent finishes processing a prompt, you can select Have feedback? to send feedback to Replit
- Pause: Stop Agent by selecting Pause above the text area
Your feedback helps Replit improve Agent. Use the feedback link to report issues, suggest improvements, or share your experience.
Checkpoints
A checkpoint is a comprehensive snapshot of your Replit App that captures completed work from Agent, including workspace contents, AI conversation context, and connected databases.
Agent creates meaningful checkpoints when it finishes implementing your request, ensuring you only pay for completed functionality.
How checkpoints work with effort-based pricing
Agent’s new effort-based pricing creates checkpoints that reflect the actual work performed:- One checkpoint per request: Agent bundles all work for your request into a single, meaningful checkpoint
- Variable pricing: Simple changes cost less, while complex builds cost more based on the effort required
- Transparent costs: Each checkpoint shows exactly what you’re paying for that completed work
- No intermediate billing: You’re not charged for Agent’s thinking or planning process
- Rollback: Undo changes made by Agent and return to the state of the previous checkpoint, including workspace contents, AI memory, and connected databases
- Track usage: Hover over the usage icon
in a checkpoint to view the amount billed for that checkpoint
For comprehensive details about what checkpoints capture and how rollbacks work across your entire development environment, see Checkpoints and Rollbacks.
Agent uses effort-based pricing where you pay based on the complexity and scope of your request. Simple changes typically cost less than complex builds.Initial planning and proposal stages are free - you only pay when Agent implements approved changes.Learn more about Agent billing.
Advanced capabilities
For complex projects, you can enable advanced Agent capabilities through toggles in the chat toolbar: Extended Thinking: Instructs Agent to analyze your request more thoroughly, considering multiple approaches and edge cases. Best for architectural decisions or when you need comprehensive solutions. High Power mode: Uses more sophisticated AI models for advanced problem-solving. Ideal for complex integrations, performance optimizations, or unfamiliar technologies.These advanced capabilities increase the effort Agent expends and therefore the cost, but they’re designed to deliver better solutions for complex builds.
Progress tab
How to access the Progress tab
How to access the Progress tab
- Select
All tools in the dock on the left - Select
Progress
- Select the magnifying glass at the top to open the search tool
- Type “Progress” to locate the Progress tool and select it from the results
- Real-time updates: monitor Agent’s progress and navigate directly to relevant files by selecting the
link icon - Chronological history: review Agent’s activities to understand the details of the changes and troubleshoot issues when needed
Getting the most from Agent
Best practices for prompts
- Be specific: Describe exactly what you want your app to do
- Provide context: Include relevant files, URLs, or examples
- Start simple: Begin with basic functionality and add complexity gradually
- Use examples: Show Agent similar apps or features you want to emulate
Managing costs effectively
- Start with free planning: Review Agent’s implementation plan before approving work
- Use simple requests: Break complex projects into smaller, focused tasks
- Set spending limits: Configure usage alerts and budgets to control costs
- Monitor usage: Track checkpoint costs to understand pricing patterns
Next steps
Ready to start building with Agent? Here’s how to begin:- Create your first app: Use the Create with AI quickstart
- Learn effective prompting: Follow our vibe coding guide
- Set up billing controls: Configure spending management
- Explore advanced features: Try Dynamic Intelligence (Extended Thinking and High Power) for complex projects