diff --git a/prompts/agent_prompt_generators.py b/prompts/agent_prompt_generators.py
index 5e247f8..aaa3844 100644
--- a/prompts/agent_prompt_generators.py
+++ b/prompts/agent_prompt_generators.py
@@ -187,7 +187,7 @@ def generate_pick_new_goal_guidance()-> str:
         str: A prompt string prompting the LLM to when to go to pick-new-goal
     """
     if is_multi_goal_mode(): 
-        return 'Next should only be "pick-new-goal" if all tools have been run for the current goal (use the system prompt to figure that out) or the user explicitly requested to pick a new goal. If next is "pick-new-goal" the tool should always be "ListAgents"'
+        return 'Next should only be "pick-new-goal" if all tools have been run for the current goal (use the system prompt to figure that out) and the last successful tool was not ListAgents, or the user explicitly requested to pick a new goal.'
     else: 
         return 'Next should never be "pick-new-goal".'
 
diff --git a/setup.md b/setup.md
index 6a41558..32c7f3c 100644
--- a/setup.md
+++ b/setup.md
@@ -210,6 +210,9 @@ FIN_START_REAL_WORKFLOW=FALSE #set this to true to start a real workflow
 #### Goals: HR/PTO
 Make sure you have the mock users you want in (such as yourself) in [the PTO mock data file](./tools/data/employee_pto_data.json).
 
+#### Goals: Ecommerce
+Make sure you have the mock orders you want in (such as those with real tracking numbers) in [the mock orders file](./tools/data/customer_order_data.json).
+
 
 ## Customizing the Agent Further
 - `tool_registry.py` contains the mapping of tool names to tool definitions (so the AI understands how to use them)
diff --git a/todo.md b/todo.md
index 00ad1d0..42c03cf 100644
--- a/todo.md
+++ b/todo.md
@@ -12,9 +12,9 @@
 
 [ ] for demo simulate failure  - add utilities/simulated failures from pipeline demo <br />
 
-[ ] ecommerce goals <br />
-- [ ] add to docs <br />
-- [ ] decide about api key names with Laine <br />
+[x] ecommerce goals <br />
+- [x] add to docs <br />
+- [x] decide about api key names with Laine <br />
 
 [ ] LLM failure->autoswitch: <br />
     - detect failure in the activity using failurecount <br />
diff --git a/tools/fin/move_money.py b/tools/fin/move_money.py
index f9569b7..7c0ca5f 100644
--- a/tools/fin/move_money.py
+++ b/tools/fin/move_money.py
@@ -77,8 +77,6 @@ async def move_money(args: dict) -> dict:
 # Async function to start workflow
 async def start_workflow(amount_cents: int, from_account_name: str, to_account_name: str)-> str:
  
-    # Connect to Temporal 
-    client = await get_temporal_client()
     start_real_workflow = os.getenv("FIN_START_REAL_WORKFLOW")
     if start_real_workflow is not None and start_real_workflow.lower() == "false":
         START_REAL_WORKFLOW = False
@@ -86,6 +84,8 @@ async def start_workflow(amount_cents: int, from_account_name: str, to_account_n
         START_REAL_WORKFLOW = True
     
     if START_REAL_WORKFLOW:
+        # Connect to Temporal 
+        client = await get_temporal_client()
         # Create the parameter object
         params = MoneyMovementWorkflowParameterObj(
             amount=amount_cents,  
diff --git a/tools/fin/submit_loan_application.py b/tools/fin/submit_loan_application.py
index 4093ec0..8e6771d 100644
--- a/tools/fin/submit_loan_application.py
+++ b/tools/fin/submit_loan_application.py
@@ -46,14 +46,14 @@ async def submit_loan_application(args: dict) -> dict:
 # Async function to start workflow
 async def start_workflow(amount: str, account_name: str, )-> dict:
  
-    # Connect to Temporal 
-    client = await get_temporal_client()
     start_real_workflow = os.getenv("FIN_START_REAL_WORKFLOW")
     if start_real_workflow is not None and start_real_workflow.lower() == "false":
         START_REAL_WORKFLOW = False
         return {'loan_application_status': "applied", 'application_details': "loan application is submitted and initial validation is complete",'transaction_id': "APPLICATION"+account_name, 'advisement': "You'll receive a confirmation for final approval in three business days", }  
     else:
         START_REAL_WORKFLOW = True
+         # Connect to Temporal 
+        client = await get_temporal_client()
     
         # Define the workflow ID and task queue
         workflow_id = "LOAN_APPLICATION-"+account_name+"-"+date.today().strftime('%Y-%m-%d')
diff --git a/tools/goal_registry.py b/tools/goal_registry.py
index a29e9d2..294036e 100644
--- a/tools/goal_registry.py
+++ b/tools/goal_registry.py
@@ -345,7 +345,7 @@ goal_fin_move_money = AgentGoal(
 )
 
 # this starts a loan approval process
-# it also uses a separate workflow/tool, see ./setup.md for details #todo
+# it also uses a separate workflow/tool, see ./setup.md for details 
 goal_fin_loan_application = AgentGoal(
     id = "goal_fin_loan_application",
     category_tag="fin",
@@ -353,7 +353,7 @@ goal_fin_loan_application = AgentGoal(
     agent_friendly_description="Initiate loan application.",   
     tools=[
         tool_registry.financial_check_account_is_valid,
-        tool_registry.financial_submit_loan_approval, #todo 
+        tool_registry.financial_submit_loan_approval, 
     ],
     description="The user wants to apply for a loan at the financial institution. To assist with that goal, help the user gather args for these tools in order: "
     "1. FinCheckAccountIsValid: validate the user's account is valid"
@@ -375,7 +375,6 @@ goal_fin_loan_application = AgentGoal(
     ),
 )
 # ----- E-Commerce Goals ---
-#todo: add goal to list all orders for last X amount of time?
 # this tool checks account balances, and uses ./data/customer_account_data.json as dummy data
 goal_ecomm_order_status = AgentGoal(
     id = "goal_ecomm_order_status",
diff --git a/workflows/agent_goal_workflow.py b/workflows/agent_goal_workflow.py
index 8f9cd5d..3b2757b 100644
--- a/workflows/agent_goal_workflow.py
+++ b/workflows/agent_goal_workflow.py
@@ -172,21 +172,33 @@ class AgentGoalWorkflow:
 
                 # else if the next step is to pick a new goal, set the goal and tool to do it
                 elif next_step == "pick-new-goal":
-                    workflow.logger.info("All steps completed. Resetting goal.")
-                    self.change_goal("goal_choose_agent_type")
-                    next_step = tool_data["next"] = "confirm"
-                    current_tool = tool_data["tool"] = "ListAgents"
-                    waiting_for_confirm = True
-                    self.tool_data = tool_data
-                    if self.show_tool_args_confirmation:
-                        self.confirmed = False 
-                    # if we have all needed arguments (handled above) and not holding for a debugging confirm, proceed:
+                    if self.goal.id != "goal_choose_agent_type":
+                        self.add_message("agent", tool_data)
+                        workflow.logger.info("All tools completed and new Agent Goal recommended. Resetting goal.")
+                        self.change_goal("goal_choose_agent_type")
+                        next_step = tool_data["next"] = "confirm"
+                        current_tool = tool_data["tool"] = "ListAgents"
+                        waiting_for_confirm = True
+                        self.tool_data = tool_data
+                        if self.show_tool_args_confirmation:
+                            self.confirmed = False 
+                        # if we have all needed arguments (handled above) and not holding for a debugging confirm, proceed:
+                        else:
+                            self.confirmed = True
+                        continue 
                     else:
-                        self.confirmed = True
-                    #self.print_useful_workflow_vars("before adding agent message<-- tool data")
-                    # maybe want to do this sometimes? for now it loops self.add_message("agent", tool_data)
-                    self.print_useful_workflow_vars("after pick-new-goal")
-                    continue # try with this out
+                        if not current_tool == "ListAgents":
+                            current_tool = tool_data["tool"] = "ListAgents"
+                            waiting_for_confirm = True
+                            
+                            self.tool_data = tool_data
+                            next_step = tool_data["next"] = "confirm"
+                            if self.show_tool_args_confirmation:
+                                self.confirmed = False 
+                            # if we have all needed arguments (handled above) and not holding for a debugging confirm, proceed:
+                            else:
+                                self.confirmed = True
+
                 
                 # else if the next step is to be done with the conversation such as if the user requests it via asking to "end conversation"
                 elif next_step == "done":
@@ -357,14 +369,12 @@ class AgentGoalWorkflow:
             self.prompt_queue
         )
 
-        #set new goal if we should
+        # set new goal if we should
         if len(self.tool_results) > 0:
             if "ChangeGoal" in self.tool_results[-1].values() and "new_goal" in self.tool_results[-1].keys():
                 new_goal = self.tool_results[-1].get("new_goal")
-                workflow.logger.info(f"Booya new goal!: {new_goal}")
                 self.change_goal(new_goal)
             elif "ListAgents" in self.tool_results[-1].values() and self.goal.id != "goal_choose_agent_type":
-                workflow.logger.info("setting goal to goal_choose_agent_type")
                 self.change_goal("goal_choose_agent_type")
         return waiting_for_confirm
         
@@ -372,6 +382,8 @@ class AgentGoalWorkflow:
     # also don't forget you can look at the workflow itself and do queries if you want
     def print_useful_workflow_vars(self, status_or_step:str) -> None:
         print(f"***{status_or_step}:***")
+        if self.goal:
+            print(f"current goal: {self.goal.id}")
         if self.tool_data:
             print(f"force confirm? {self.tool_data['force_confirm']}")
             print(f"next step: {self.tool_data.get('next')}")