Skip to main content
Agent mode is Noah’s autonomous execution mode, designed to implement changes directly in your project. When you give Noah a task, it takes ownership of execution end to end — understanding your intent, exploring the codebase for context, applying changes across files, and resolving issues that appear during development.
Choose a modeNoah has two modes:
  • Plan mode → think through the problem, explore options, and decide on an approach
  • Agent mode → implement changes and verify the outcome
Plan mode is for decision-making. Agent mode is for execution.The two modes are designed to work together, and you can switch between them at any time.

​
Overview

Agent mode is Noah’s autonomous execution mode, designed to implement changes directly in your project. When you give Noah a task, it takes ownership of execution end to end. It understands your intent, explores the codebase for context, applies changes across files, and resolves issues that appear during development. While it works, you can see progress through visible tasks and review the results before moving on.

​
What Agent Mode Is For

You can use Agent mode to:
  • Implement features or changes once an approach is decided
  • Fix bugs or errors end to end
  • Refactor code across multiple files
  • Apply coordinated changes across frontend, smart contracts, and configuration
  • Debug issues that arise during implementation
  • Inspect logs and activity to identify problems
  • Fetch external documentation or assets when needed
  • Verify results before finishing
All changes are applied directly to your project and surfaced through file diffs and summaries.

​
How to Use Agent Mode

Agent mode is active unless you switch to Plan mode. To use it, describe what you want and send your message. Clear requirements and constraints help Noah produce better results. Be specific about what you want 
Add a token swap form with amount input, slippage settings, and confirmation dialog.
Validate input amounts and show error messages inline.
Describe expected behavior 
When users click 'Connect Wallet', show a wallet selection modal and update
the header with the connected wallet address. Store the connection state.
Provide context for complex changes 
Update the dashboard to show token holdings and recent transactions.
Use the existing Card component and match the styling used on the portfolio page.
Set guardrails for sensitive areas 
Add a new feature to the marketplace page.
Do not modify the existing smart contract integration or authentication logic.

​
Tasks and Execution Visibility

While Noah is working, tasks appear in the interface showing:
  • Current step being executed
  • Files being modified
  • Tools being used (search, web fetch, code generation)
  • Progress through multi-step implementations
This visibility helps you:
  • Follow progress on complex builds
  • Understand the steps being performed
  • Stay oriented during complex changes
  • Spot issues early if something seems off

​
Debugging and Verification

When using Agent mode, Noah does more than ensure code compiles. As part of investigation and problem solving, the agent can:
  • Observe build errors and failures from test runs
  • Inspect console output and network requests
  • Reproduce reported issues using targeted testing
  • Verify that fixes work as expected by running appropriate checks
Noah has access to verification tools such as testing, frontend checks, and smart contract validation to help understand system behavior, validate user workflows, and ensure your code works as expected.

​
Pricing

Pricing for Agent mode is usage-based. Cost depends on factors such as:
  • Number of files modified
  • Complexity of logic changes
  • Amount of codebase exploration required
  • Use of tools such as verification, web search, or code generation
Many requests cost less than one credit, while more complex tasks may cost more. See Plans and Credits for more information.

​
FAQ

Yes. Agent mode applies changes directly to your project. You can review all changes through file diffs and summaries before moving on.
Plan mode is for thinking and planning — it never changes your code. Agent mode is for execution — it implements the changes in your project.
Yes. You can switch to Plan mode at any time to pause, think, or re-plan before continuing with Agent mode.
Agent mode pricing is usage-based. Cost varies depending on the complexity of the task, number of files changed, and tools used. Many requests cost less than one credit.
You can send a new prompt after Noah finishes the current task. Describe each task clearly for the best results.