update prompt and allow for up to 5 steps

agent.py

@@ -22,9 +22,9 @@ class Agent:
 
         # select the tools to use
         tools = [
-            FinalAnswer(),
             WebSearch(),
-            VisitWebpage()
+            VisitWebpage(),
+            FinalAnswer(),
         ]
 
         # load the prompt templates from the prompts.yaml file
@@ -36,7 +36,7 @@ class Agent:
             model=model,
             tools=tools,
             managed_agents=[],
-            max_steps=3,
+            max_steps=5,
             verbosity_level=1,
             grammar=None,
             planning_interval=None,

prompts.yaml

@@ -6,7 +6,7 @@
   Then in the Code sequence you should write the code in simple Python. The code sequence must be opened with '{{code_block_opening_tag}}', and closed with '{{code_block_closing_tag}}'.
   During each intermediate step, you can use 'print()' to save whatever important information you will then need.
   These print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.
-  In the end you have to return a final answer using the `final_answer` tool.
+  In the end you have to return a final answer using the `final_answer` tool. For the final answer you should only provide the answer to the task. Your final response will be evaluated by a exact match module, so make sure to return the answer without any additional text.
 
   Here are a few examples using notional tools:
   ---