#Agentforce318 debatiendo

Hi @Deepti Srivastava

I also encountered difficulties when creating a support case, so I contacted the support team in Japan for assistance, and they explained the process to me.

In the Agentforce chat input field, simply enter "Create a case" or "Case creation". Agentforce will then ask you for the necessary information and create the case based on your responses.

Alternatively, instead of waiting for Agentforce to prompt you for the required details, you can enter all the information that you would normally provide when submitting a case in a single message in the chat text box, as shown below, and request case creation directly. 

Hi @Manohar Goud

This is a common issue when we work with multiple subagents and actions in Agentforce.

Here are a few things I would suggest: 

1. Clear Responsibilities: Give each subagent a specific job. Try to avoid overlapping responsibilities.
2. Proper Instructions: Clearly explain when to use a subagent, when not to use it, and what it should do.
3. Meaningful Names: Use clear names and descriptions for subagents and actions so Agentforce can understand their purpose.
4. Avoid Similar Actions: If two actions perform almost the same task, try to combine them or clearly separate their use cases.
5. Use Agent Script: For complex or critical scenarios, use conditions and explicit routing instead of depending completely on AI decisions.
6. Availability Conditions: Use available when conditions wherever applicable to control which subagents or actions can be selected.
7. Handle Unclear Requests: If the user request is confusing, let the agent ask a follow-up question instead of choosing the wrong action.
8. Test Multiple Scenarios: Test different ways users might ask the same question, including negative and overlapping scenarios.
9. Monitor Agent Behavior: Review session traces regularly to understand why a particular subagent or action was selected.

For example:

If we have three subagents for Order Inquiry, Order Cancellation, and Order Modification, each should have clear instructions about which requests it handles.

In my view, the best approach is to start with fewer subagents and actions, test them properly, and then gradually add more. 

One important point: Don't depend only on AI instructions for critical business processes. Use proper conditions, permissions, and validations to control execution.

Hope this helps! 

Thank you, 

Venkat Yadav.

Hi @Santhosh Gorantala Good question!  

Testing Agentforce before moving to production is very important because, unlike traditional automation, the same question can be asked in different ways, and the agent may select different subagents or actions. 

I would recommend the following approach:

1. Testing Center: Use Agentforce Testing Center to test multiple user questions and validate whether the correct subagent and actions are selected.
2. Positive Scenarios: Test normal business scenarios with valid inputs and expected results.
3. Negative Scenarios: Test invalid inputs, missing records, incomplete information, and questions outside the agent's scope.
4. Permission Testing: Test with different user profiles and permission sets. Make sure the agent respects Salesforce security and doesn't expose restricted data.
5. Action Failure Testing: Check how the agent responds when Apex, Flow, or external API actions fail, time out, or return empty results.
6. Conversation Testing: Test follow-up questions, context switching, ambiguous requests, and multiple questions in the same conversation.
7. Session Tracing: Review session traces to identify incorrect subagent selection, action execution issues, and response-generation problems.
8. Regression Testing: Maintain a reusable set of test cases and run them whenever you modify agent instructions, subagents, actions, or grounding configurations.

When is an agent ready for production?

I would consider it ready when critical business scenarios pass consistently, security tests are successful, actions work reliably, and there are no unresolved high-severity issues. 

I also recommend starting with a limited group of users in production and monitoring the agent's responses before rolling it out to everyone. 

My suggestion: Don't test only whether the agent gives the correct answer. Also verify whether it selected the correct subagent, executed the right action, respected user permissions, and handled failures properly.

Hope this helps! 

Thank you, 

Venkat Yadav.

Hi @Santhosh Gorantala

Good question! This is one of the common challenges we see with Agentforce. Sometimes the agent retrieves the correct data, but the final response is still incomplete or inaccurate. 

I would suggest checking a few things:

1. Session Tracing: First, check the session trace to understand which subagent and actions were executed, what data was returned, and where the response might have gone wrong.
2. Action Output: Verify whether the Apex, Flow, or Knowledge action is returning complete and accurate information. Sometimes the issue is with how the output is structured.
3. Grounding: Make sure the agent is actually using the retrieved data while generating the response.
4. Agent Instructions: Keep instructions simple and specific. Clearly tell the agent to use the available data and avoid making assumptions when information is missing.
5. Testing Center: Test the same question with different inputs and scenarios. This helps identify whether the issue happens consistently or only in certain situations.
6. Apex or Flow: For important business calculations, validations, or complex logic, it's better to handle them through Apex or Flow rather than relying completely on the LLM.

My suggestion:

Instead of adding more and more instructions, first identify exactly where the issue is happening. In many cases, improving the action output and grounding can make a big difference in response quality. 

You can also refer to this Salesforce article for more information:

https://help.salesforce.com/s/articleView?id=005305511&type=1

Hope this helps! 

Thank you, 

Venkat Yadav.

hi @SHRAWAN KUMAR

- 

Few points 

1. You need to have Einstein features for the org 

If its for learning  purpose kindly create a developer org with agentforce and data cloud. If its for commercial purpose you need to check with account executive for enabling the features. 

Thanks

Hi @Santhosh Gorantala

This is a common challenge when customer data comes from multiple systems.

I would normally start by checking the match rules and source data quality.

A few things I would suggest:

1. Match Rules: Check whether the rules are too strict. Sometimes small differences in names, emails, or phone numbers prevent matching.
2. Data Quality: Look for missing values, duplicate records, extra spaces, and inconsistent formats.
3. Normalization: Try normalized email and phone matching where applicable.
4. Data Mapping: Make sure Individual, Contact Point Email, and Contact Point Phone are mapped correctly, including their relationships.
5. Ruleset Execution: Check whether the Identity Resolution ruleset completed successfully and review the processing results.
6. Reconciliation Rules: If records are unified but the expected field values aren't showing, check which source is given priority.

Simple Example:

One system has "Santhosh Kumar" and another has "Santosh Kumar". An exact name match may fail, but fuzzy matching could help identify them as the same person. 

My suggestion is to take 2–3 customer records that should match, compare their source values, and test the matching rules step by step. 

One important point: Match rules decide which records get unified, while reconciliation rules decide which field values appear in the unified profile.

Hope this helps! 

Thank you, 

Venkat Yadav.