diff --git a/config/config.yaml b/config/config.yaml
index 30168d81e..b0264e908 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -26,8 +26,6 @@ RPM: 10
 #GOOGLE_API_KEY: "YOUR_API_KEY"
 ## Visit https://programmablesearchengine.google.com/controlpanel/create to get id.
 #GOOGLE_CSE_ID: "YOUR_CSE_ID"
-## Visit https://serper.dev/ to get key.
-#SERPER_API_KEY: "YOUR_API_KEY"
 
 #### for TTS
 
diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py
index a390a8350..948185e45 100644
--- a/metagpt/actions/action.py
+++ b/metagpt/actions/action.py
@@ -13,7 +13,7 @@ from metagpt.actions.action_output import ActionOutput
 from tenacity import retry, stop_after_attempt, wait_fixed
 from pydantic import BaseModel
 from metagpt.utils.common import OutputParser
-
+from metagpt.logs import logger
 
 class Action(ABC):
     def __init__(self, name: str = '', context=None, llm: LLM = None):
@@ -46,7 +46,7 @@ class Action(ABC):
         system_msgs.append(self.prefix)
         return await self.llm.aask(prompt, system_msgs)
 
-    @retry(stop=stop_after_attempt(2), wait=wait_fixed(1))
+    @retry(stop=stop_after_attempt(1), wait=wait_fixed(1))
     async def _aask_v1(self, prompt: str, output_class_name: str,
                        output_data_mapping: dict,
                        system_msgs: Optional[list[str]] = None) -> ActionOutput:
@@ -55,8 +55,10 @@ class Action(ABC):
             system_msgs = []
         system_msgs.append(self.prefix)
         content = await self.llm.aask(prompt, system_msgs)
+        logger.info(content)
         output_class = ActionOutput.create_model_class(output_class_name, output_data_mapping)
         parsed_data = OutputParser.parse_data_with_mapping(content, output_data_mapping)
+        logger.info(parsed_data)
         instruct_content = output_class(**parsed_data)
         return ActionOutput(content, instruct_content)
 
diff --git a/metagpt/actions/write_prd.py b/metagpt/actions/write_prd.py
index 449f073c4..aa469bd5d 100644
--- a/metagpt/actions/write_prd.py
+++ b/metagpt/actions/write_prd.py
@@ -59,6 +59,7 @@ ATTENTION: Use '##' to SPLIT SECTIONS, not '#'. AND '## <SECTION_NAME>' SHOULD W
 
 ## Requirement Pool: Provided as Python list[str, str], the parameters are requirement description, priority(P0/P1/P2), respectively, comply with PEP standards; no more than 5 requirements and consider to make its difficulty lower
 
+## UI Design draft: Provide as Plain text. Be simple. Describe the elements and functions, also provide a simple style description and layout description.
 ## Anything UNCLEAR: Provide as Plain text. Make clear here.
 """
 FORMAT_EXAMPLE = """
@@ -105,6 +106,9 @@ The product should be a ...
 ]
 ```
 
+## UI Design draft
+Give a basic function description, and a draft
+
 ## Anything UNCLEAR
 There are no unclear points.
 ---
@@ -117,6 +121,7 @@ OUTPUT_MAPPING = {
     "Competitive Quadrant Chart": (str, ...),
     "Requirement Analysis": (str, ...),
     "Requirement Pool": (List[Tuple[str, str]], ...),
+    "UI Design draft":(str, ...),
     "Anything UNCLEAR": (str, ...),
 }
 
@@ -127,8 +132,7 @@ class WritePRD(Action):
 
     async def run(self, requirements, *args, **kwargs) -> ActionOutput:
         sas = SearchAndSummarize()
-        # rsp = await sas.run(context=requirements, system_text=SEARCH_AND_SUMMARIZE_SYSTEM_EN_US)
-        rsp = ""
+        rsp = await sas.run(context=requirements, system_text=SEARCH_AND_SUMMARIZE_SYSTEM_EN_US)
         info = f"### Search Results\n{sas.result}\n\n### Search Summary\n{rsp}"
         if sas.result:
             logger.info(sas.result)
@@ -136,5 +140,6 @@ class WritePRD(Action):
 
         prompt = PROMPT_TEMPLATE.format(requirements=requirements, search_information=info,
                                         format_example=FORMAT_EXAMPLE)
+        logger.info(prompt)
         prd = await self._aask_v1(prompt, "prd", OUTPUT_MAPPING)
         return prd
diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py
index 36269aed2..4ddb84252 100644
--- a/metagpt/roles/role.py
+++ b/metagpt/roles/role.py
@@ -114,6 +114,7 @@ class Role:
     def _set_state(self, state):
         """Update the current state."""
         self._rc.state = state
+        logger.info(self._actions)
         self._rc.todo = self._actions[self._rc.state]
 
     def set_env(self, env: 'Environment'):
@@ -170,8 +171,11 @@ class Role:
         if not self._rc.env:
             return 0
         env_msgs = self._rc.env.memory.get()
+        
         observed = self._rc.env.memory.get_by_actions(self._rc.watch)
+        
         already_observed = self._rc.memory.get()
+        
         news: list[Message] = []
         for i in observed:
             if i in already_observed: