Skip to content

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

added better data grounding in done action

Saurav Panda179d5267865e
diff --git a/browser_use/agent/system_prompts/system_prompt.md b/browser_use/agent/system_prompts/system_prompt.md
index 4e1af5b57..900114480 100644
--- a/browser_use/agent/system_prompts/system_prompt.md
+++ b/browser_use/agent/system_prompts/system_prompt.md
@@ -147,7 +147,7 @@ BEFORE calling `done` with `success=true`, you MUST perform this verification:
3. **Verify actions actually completed:**
- If you submitted a form, posted a comment, or saved a file — check the page state or screenshot to confirm it happened.
- If you took a screenshot or downloaded a file — verify it exists in your file system.
-4. **Verify data grounding:** Every URL, price, name, and value must appear verbatim in your tool outputs or browser_state. Never construct URLs or use "representative" values. If not extracted, say not found — do not substitute.
+4. **Verify data grounding:** Every URL, price, name, and value must appear verbatim in your tool outputs or browser_state. Do NOT use your training knowledge to fill gaps — if information was not found on the page during this session, say so explicitly. Never fabricate or invent values.
5. **If ANY requirement is unmet, uncertain, or unverifiable — set `success` to `false`.**
Partial results with `success=false` are more valuable than overclaiming success.
</pre_done_verification>
diff --git a/browser_use/agent/system_prompts/system_prompt_anthropic_flash.md b/browser_use/agent/system_prompts/system_prompt_anthropic_flash.md
index 8022537b9..78dafdcc9 100644
--- a/browser_use/agent/system_prompts/system_prompt_anthropic_flash.md
+++ b/browser_use/agent/system_prompts/system_prompt_anthropic_flash.md
@@ -95,7 +95,7 @@ BEFORE calling `done` with `success=true`, you MUST perform this verification:
3. **Verify actions actually completed:**
- If you submitted a form, posted a comment, or saved a file — check the page state or screenshot to confirm it happened.
- If you took a screenshot or downloaded a file — verify it exists in your file system.
-4. **Verify data grounding:** Every URL, price, name, and value must appear verbatim in your tool outputs or browser_state. Never construct URLs or use "representative" values. If not extracted, say not found — do not substitute.
+4. **Verify data grounding:** Every URL, price, name, and value must appear verbatim in your tool outputs or browser_state. Do NOT use your training knowledge to fill gaps — if information was not found on the page during this session, say so explicitly. Never fabricate or invent values.
5. **If ANY requirement is unmet, uncertain, or unverifiable — set `success` to `false`.**
Partial results with `success=false` are more valuable than overclaiming success.
</pre_done_verification>
diff --git a/browser_use/agent/system_prompts/system_prompt_browser_use.md b/browser_use/agent/system_prompts/system_prompt_browser_use.md
index 372771e09..3b5fe1d03 100644
--- a/browser_use/agent/system_prompts/system_prompt_browser_use.md
+++ b/browser_use/agent/system_prompts/system_prompt_browser_use.md
@@ -14,5 +14,5 @@ You must ALWAYS respond with a valid JSON in this exact format:
"action": [{{"action_name": {{...params...}}}}]
}}
Action list should NEVER be empty.
-DATA GROUNDING: Only report data observed in browser state or tool outputs. Never fabricate URLs, prices, or values. If not found, say so.
+DATA GROUNDING: Only report data observed in browser state or tool outputs. Do NOT use training knowledge to fill gaps — if not found on the page, say so explicitly. Never fabricate values.
</output>
diff --git a/browser_use/agent/system_prompts/system_prompt_browser_use_flash.md b/browser_use/agent/system_prompts/system_prompt_browser_use_flash.md
index 0a04cf5e1..435d77a85 100644
--- a/browser_use/agent/system_prompts/system_prompt_browser_use_flash.md
+++ b/browser_use/agent/system_prompts/system_prompt_browser_use_flash.md
@@ -11,5 +11,5 @@ You must respond with a valid JSON in this exact format:
"action": [{{"action_name": {{...params...}}}}]
}}
Action list should NEVER be empty.
-DATA GROUNDING: Only report data observed in browser state or tool outputs. Never fabricate URLs, prices, or values. If not found, say so.
+DATA GROUNDING: Only report data observed in browser state or tool outputs. Do NOT use training knowledge to fill gaps — if not found on the page, say so explicitly. Never fabricate values.
</output>
diff --git a/browser_use/agent/system_prompts/system_prompt_browser_use_no_thinking.md b/browser_use/agent/system_prompts/system_prompt_browser_use_no_thinking.md
index ca5be037b..e33b4f978 100644
--- a/browser_use/agent/system_prompts/system_prompt_browser_use_no_thinking.md
+++ b/browser_use/agent/system_prompts/system_prompt_browser_use_no_thinking.md
@@ -13,5 +13,5 @@ You must ALWAYS respond with a valid JSON in this exact format:
"action": [{{"action_name": {{...params...}}}}]
}}
Action list should NEVER be empty.
-DATA GROUNDING: Only report data observed in browser state or tool outputs. Never fabricate URLs, prices, or values. If not found, say so.
+DATA GROUNDING: Only report data observed in browser state or tool outputs. Do NOT use training knowledge to fill gaps — if not found on the page, say so explicitly. Never fabricate values.
</output>
diff --git a/browser_use/agent/system_prompts/system_prompt_flash.md b/browser_use/agent/system_prompts/system_prompt_flash.md
index 984707949..b7c0a1927 100644
--- a/browser_use/agent/system_prompts/system_prompt_flash.md
+++ b/browser_use/agent/system_prompts/system_prompt_flash.md
@@ -15,5 +15,5 @@ Instructions containing "do NOT", "never", "avoid", "skip", or "only X" are hard
"action":[{{"navigate": {{ "url": "url_value"}}}}]
}}
Before calling `done` with `success=true`: re-read the user request, verify every requirement is met (correct count, filters applied, format matched), confirm actions actually completed via page state/screenshot, and ensure no data was fabricated. If anything is unmet or uncertain, set `success` to `false`.
-DATA GROUNDING: Only report data observed in browser state or tool outputs. Never fabricate URLs, prices, or values — including "representative" ones. If not found, say so.
+DATA GROUNDING: Only report data observed in browser state or tool outputs. Do NOT use training knowledge to fill gaps — if not found on the page, say so explicitly. Never fabricate values.
</output>
diff --git a/browser_use/agent/system_prompts/system_prompt_flash_anthropic.md b/browser_use/agent/system_prompts/system_prompt_flash_anthropic.md
index 7fd4edc06..64d45560a 100644
--- a/browser_use/agent/system_prompts/system_prompt_flash_anthropic.md
+++ b/browser_use/agent/system_prompts/system_prompt_flash_anthropic.md
@@ -30,5 +30,5 @@ Instructions containing "do NOT", "never", "avoid", "skip", or "only X" are hard
Always put `memory` field before the `action` field.
Before calling `done` with `success=true`: re-read the user request, verify every requirement is met (correct count, filters applied, format matched), confirm actions actually completed via page state/screenshot, and ensure no data was fabricated. If anything is unmet or uncertain, set `success` to `false`.
-DATA GROUNDING: Only report data observed in browser state or tool outputs. Never fabricate URLs, prices, or values — including "representative" ones. If not found, say so.
+DATA GROUNDING: Only report data observed in browser state or tool outputs. Do NOT use training knowledge to fill gaps — if not found on the page, say so explicitly. Never fabricate values.
</output>
diff --git a/browser_use/agent/system_prompts/system_prompt_no_thinking.md b/browser_use/agent/system_prompts/system_prompt_no_thinking.md
index c666a86a9..4fc53bc0a 100644
--- a/browser_use/agent/system_prompts/system_prompt_no_thinking.md
+++ b/browser_use/agent/system_prompts/system_prompt_no_thinking.md
@@ -132,7 +132,7 @@ BEFORE calling `done` with `success=true`, you MUST perform this verification:
3. **Verify actions actually completed:**
- If you submitted a form, posted a comment, or saved a file — check the page state or screenshot to confirm it happened.
- If you took a screenshot or downloaded a file — verify it exists in your file system.
-4. **Verify data grounding:** Every URL, price, name, and value must appear verbatim in your tool outputs or browser_state. Never construct URLs or use "representative" values. If not extracted, say not found — do not substitute.
+4. **Verify data grounding:** Every URL, price, name, and value must appear verbatim in your tool outputs or browser_state. Do NOT use your training knowledge to fill gaps — if information was not found on the page during this session, say so explicitly. Never fabricate or invent values.
5. **If ANY requirement is unmet, uncertain, or unverifiable — set `success` to `false`.**
Partial results with `success=false` are more valuable than overclaiming success.
</pre_done_verification>
diff --git a/browser_use/tools/views.py b/browser_use/tools/views.py
index a8102ecf9..89e15aa01 100644
--- a/browser_use/tools/views.py
+++ b/browser_use/tools/views.py
@@ -83,7 +83,15 @@ class InputTextAction(BaseModel):
class DoneAction(BaseModel):
- text: str = Field(description='Final user message in the format the user requested')
+ text: str = Field(
+ description=(
+ 'Final message to the user. '
+ 'ONLY report data you directly observed in browser_state, tool outputs, or screenshots during this session. '
+ 'Do NOT use training knowledge to fill gaps — if information was not found on the page, say so explicitly. '
+ 'Do NOT claim completion of steps from compacted_memory or prior session summaries '
+ 'unless you explicitly verified them yourself.'
+ )
+ )
success: bool = Field(default=True, description='True if user_request completed successfully')
files_to_display: list[str] | None = Field(default=[])