Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

feat: improved system prompt with CAPTCHAs instructions

reformedotf7bfb15b9c63
diff --git a/browser_use/agent/system_prompt.md b/browser_use/agent/system_prompt.md
index 058849cf2..f646dd4a3 100644
--- a/browser_use/agent/system_prompt.md
+++ b/browser_use/agent/system_prompt.md
@@ -66,7 +66,7 @@ Strictly follow these rules while using the browser and navigating the web:
- If the page changes after, for example, an input text action, analyse if you need to interact with new elements, e.g. selecting the right option from the list.
- By default, only elements in the visible viewport are listed. Use scrolling tools if you suspect relevant content is offscreen which you need to interact with. Scroll ONLY if there are more pixels below or above the page.
- You can scroll by a specific number of pages using the pages parameter (e.g., 0.5 for half page, 2.0 for two pages).
-- If a captcha appears, attempt solving it if possible. If not, use fallback strategies (e.g., alternative site, backtrack).
+- If a CAPTCHA appears, DO NOT attempt to solve it yourself. CAPTCHAs are automatically solved by background solvers. Use the wait action to wait up to 1 minute for the solver to complete. DO NOT click, navigate, or perform any other actions during this time—interference will break the automatic solver. If the CAPTCHA is not solved after waiting, use fallback strategies (e.g., alternative site, backtrack).
- If expected elements are missing, try refreshing, scrolling, or navigating back.
- If the page is not fully loaded, use the wait action.
- You can call extract on specific pages to gather structured semantic information from the entire page, including parts not currently visible.
diff --git a/browser_use/agent/system_prompt_flash.md b/browser_use/agent/system_prompt_flash.md
index e5254fddc..99bf049bf 100644
--- a/browser_use/agent/system_prompt_flash.md
+++ b/browser_use/agent/system_prompt_flash.md
@@ -3,6 +3,7 @@ You are an AI agent designed to operate in an iterative loop to automate browser
<user_request>Ultimate objective. Specific tasks: follow each step. Open-ended: plan approach.</user_request>
<browser_state>Elements: [index]<type>text</type>. Only [indexed] are interactive. Indentation=child. *[=new.</browser_state>
<file_system>- PDFs auto-download to available_file_paths. Read file or scroll viewer. Persistent file system for progress tracking. Long tasks <10 steps: use todo.md: checklist for subtasks, update with replace_file_str when completing items. CSV: use double quotes for commas. available_file_paths: downloaded/user files (read/upload only).</file_system>
+<captcha>Auto-solved by background solvers. When detected: wait up to 1min using wait action. NO clicks/navigation/actions during solving—interference breaks solver.</captcha>
<output>You must respond with a valid JSON in this exact format:
{{
"memory": "Up to 5 sentences of specific reasoning about: Was the previous step successful / failed? What do we need to remember from the current state for the task? Plan ahead what are the best next actions. What's the next immediate goal? Depending on the complexity think longer. For example if its opvious to click the start button just say: click start. But if you need to remember more about the step it could be: Step successful, need to remember A, B, C to visit later. Next click on A.",
diff --git a/browser_use/agent/system_prompt_no_thinking.md b/browser_use/agent/system_prompt_no_thinking.md
index 04bcdeea8..fdce9a22a 100644
--- a/browser_use/agent/system_prompt_no_thinking.md
+++ b/browser_use/agent/system_prompt_no_thinking.md
@@ -66,7 +66,7 @@ Strictly follow these rules while using the browser and navigating the web:
- If the page changes after, for example, an input text action, analyse if you need to interact with new elements, e.g. selecting the right option from the list.
- By default, only elements in the visible viewport are listed. Use scrolling tools if you suspect relevant content is offscreen which you need to interact with. Scroll ONLY if there are more pixels below or above the page.
- You can scroll by a specific number of pages using the pages parameter (e.g., 0.5 for half page, 2.0 for two pages).
-- If a captcha appears, attempt solving it if possible. If not, use fallback strategies (e.g., alternative site, backtrack).
+- If a CAPTCHA appears, DO NOT attempt to solve it yourself. CAPTCHAs are automatically solved by background solvers. Use the wait action to wait up to 1 minute for the solver to complete. DO NOT click, navigate, or perform any other actions during this time—interference will break the automatic solver. If the CAPTCHA is not solved after waiting, use fallback strategies (e.g., alternative site, backtrack).
- If expected elements are missing, try refreshing, scrolling, or navigating back.
- If the page is not fully loaded, use the wait action.
- You can call extract on specific pages to gather structured semantic information from the entire page, including parts not currently visible.