Agents

Learn about the LLM-powered agents that power Bolt

Agents are the large language models (LLMs) that Bolt uses to generate your code. They act as the brains behind how Bolt interprets your instructions, solves problems, and writes the code behind your website or app.

To learn more about large language models generally, see Introduction to LLMs.

Build with your preferred agent

Bolt gives you the choice of which AI agent powers your builds, so you can work in the way that suits you best. You can choose between two options:

• Claude Agent – Our most powerful agent is the best choice for building production-quality apps or doing serious work in Bolt. It is far more reliable, runs into fewer errors, and produces more complete web apps on the first try. While it takes a bit longer to run and uses more tokens initially, the improved results make it well worth it. It uses Claude Agent from Anthropic as its LLM, which is built on top of Claude Code. Claude Agent offers Plan Mode, a powerful tool for executing detailed and accurate build strategies.
• v1 Agent (legacy) – Based on the original Bolt experience, this agent is more likely to produce incomplete apps and require extra fixes, so it’s not recommended for production work. It is, however, faster, uses fewer tokens per prompt, and works well for quick prototypes or testing layouts and design ideas. It uses Anthropic Claude Sonnet as its LLM.

Bolt strongly recommends using Claude Agent if you want the best results and the smoothest building experience.

Claude Agent vs. v1 Agent (legacy) efficiency

While v1 Agent (legacy) might seem more efficient because it uses fewer tokens at the start, this can be misleading.

For any project beyond a quick mockup or prototype, you will likely save tokens overall by using Claude Agent. Its more comprehensive approach to building leads to higher quality planning, greater reliability, and fewer mistakes. This means less rework, fewer wasted calls, and more efficient use of your token budget over time.

Switch between Bolt agents

See Agents to learn more about switching between Claude Agent and v1 Agent (legacy) in Bolt.

You can switch between agents in two places: from the Bolt homepage when starting a build, or inside a project while working.

Switching between agents mid-project clears your chat history.

Resetting the chat history is intentional and helps prevent confusion between agents. Your new agent will still have full access to your project and files. Any general or ongoing instructions you want to preserve should be added to Project Knowledge.

On the homepage

When you’re on the Bolt homepage about to start a new chat, you can use the drop-down agent selector in the bottom of the chatbox to select your preferred agent.

In a project

When working inside a project, follow these steps to switch agents:

1. In the bottom-left corner of the chatbox, click the plus icon to open the menu.
2. Hover over the agent in use to view alternatives.
3. Click the name of the agent you want to select.
4. Confirm your choice.

Hovering over an agent’s name will reveal information about the agent.

Differences between agents

Bolt works a little differently depending on which agent you choose. Some features and parts of the interface change to match the agent’s strengths. If you switch agents, you may notice slight differences in the tools available or how the chat behaves.

Key differences include:

• Claude Agent works with Plan Mode, whereas the v1 Agent (legacy) works with Discussion Mode.
• Claude Agent can create Bolt Databases, or let you switch that database to your own Supabase account. It can also work with projects which used the v1 Agent (legacy) to integrate your own Supabase database.

Feature	Claude Agent	v1 Agent (legacy)
Plan Mode	✔	✗
Create Bolt databases	✔	✗
Works with Bolt databases	✔	✔
Discussion Mode	✗	✔