diff --git a/oci-generative-ai-agents-fsi/2-setup/setup-tenancy.md b/oci-generative-ai-agents-fsi/2-setup/setup-tenancy.md
index e3828a39..3a3b402b 100644
--- a/oci-generative-ai-agents-fsi/2-setup/setup-tenancy.md
+++ b/oci-generative-ai-agents-fsi/2-setup/setup-tenancy.md
@@ -81,7 +81,20 @@ In order to facilitate those permissions, we will create a Dynamic Group which w
1. Name the dynamic group: _oci-genai-agents-service_
+
+ ```text
+
+ oci-genai-agents-service
+
+ ```
1. Provide an optional description (example: `This group represents the OCI Generative AI Agents service`)
+
+ ```text
+
+ This group represents the OCI Generative AI Agents service
+
+ ```
+
1. Select the **Match any rules defined below** option in the **Matching rules** section.
1. Enter the following expression in the **Rule 1** textbox:
@@ -108,7 +121,21 @@ Next, we will create the access policies:
1. Provide a name for the policy (example: _oci-generative-ai-agents-workshop_).
+
+ ```text
+
+ oci-generative-ai-agents-workshop
+
+ ```
+
1. Provide a description (example: _OCI Generative AI Agents Hands-On-Lab Policy_).
+
+ ```text
+
+ OCI Generative AI Agents Hands-On-Lab Policy
+
+ ```
+
1. Make sure that the root compartment is selected.
1. Enable the **Show manual editor** option.
1. In the **Policy Builder** textbox, enter the following policy statements:
diff --git a/oci-generative-ai-agents-fsi/3-setup-the-database/setup-the-database-tenancy.md b/oci-generative-ai-agents-fsi/3-setup-the-database/setup-the-database-tenancy.md
index 626559b9..fee3a773 100644
--- a/oci-generative-ai-agents-fsi/3-setup-the-database/setup-the-database-tenancy.md
+++ b/oci-generative-ai-agents-fsi/3-setup-the-database/setup-the-database-tenancy.md
@@ -38,7 +38,21 @@ In this task we are going to create a new ADB instance.
1. For the **Display name** use: _loan-compliance_.
+
+ ```text
+
+ loan-compliance
+
+ ```
+
1. For the **Database name** use: _loancompliance_.
+
+ ```text
+
+ loancompliance
+
+ ```
+
1. Under the **Compartment**, make sure that the **root** compartment is selected.
1. Under **Workload type** make sure that **Data Warehouse** is selected.
@@ -302,6 +316,13 @@ In this task we are going to create a Vault and an encryption key. We are going
1. Under the **Create in Compartment**, make sure that the **root** compartment is selected.
1. For the **Name** field use: _loan-compliance-secrets_
+
+ ```text
+
+ loan-compliance-secrets
+
+ ```
+
1. Click the **Create Vault** button at the bottom of the form.
@@ -318,6 +339,13 @@ In this task we are going to create a Vault and an encryption key. We are going
1. Under the **Create in Compartment**, make sure that the **root** compartment is selected.
1. For the **Name** field use: _loan-compliance-key_
+
+ ```text
+
+ loan-compliance-key
+
+ ```
+
1. Click the **Create Key** button.
@@ -338,6 +366,13 @@ In this section we are going to create a connection to our database. This connec
1. For the **Name** field use: _loan-compliance_
+
+ ```text
+
+ loan-compliance
+
+ ```
+
1. Under the **Compartment**, make sure that the **root** compartment is selected.
1. Make sure that the **Select database** option is selected under the **Database details** section.
1. In the **Database cloud service** drop-down, select **Oracle Autonomous Database**.
@@ -353,6 +388,13 @@ In this section we are going to create a connection to our database. This connec
This step will create a secret which will be stored in the Vault created earlier and will contain the password for connecting to the database.
1. For the **Name** field use: _loan-compliance-admin-password_
+
+ ```text
+
+ loan-compliance-admin-password
+
+ ```
+
1. Select the **loan-compliance-secrets** in the **Valut in...** drop-down.
1. Select the **loan-compliance-key** in the **Encryption key in...** drop-down.
1. In the **User password** field, type the password you've used when you created the ADB instance.
@@ -370,6 +412,13 @@ In this section we are going to create a connection to our database. This connec
1. For the **Name** field use: _loan-compliance-wallet-secret_
+
+ ```text
+
+ loan-compliance-wallet-secret
+
+ ```
+
1. Select the **loan-compliance-secrets** in the **Valut in...** drop-down.
1. Select the **loan-compliance-key** in the **Encryption key in...** drop-down.
1. Under the **Wallet** section, select the **Retrieve regional wallet from Autonomous Database** option.
diff --git a/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-sandbox.md b/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-sandbox.md
index b1625f32..fb8ad114 100644
--- a/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-sandbox.md
+++ b/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-sandbox.md
@@ -21,6 +21,10 @@ This lab assumes you have:
## Task 1: Create the agent
+1. In the OCI Console, click the **Region** selector in the top-right corner and switch to **US Midwest (Chicago)** for this workshop.
+
+ 
+
1. Click the navigation menu on the top left.
1. Click **Analytics & AI**.
1. Click **Generative AI Agents**.
@@ -33,10 +37,31 @@ This lab assumes you have:
-1. For the **Name** field use: _loan compliance agent_
+1. For the **Name** field use:
+
+ ``` text
+
+ loan compliance agent
+
+ ```
+
1. For the **Compartment** field, make sure that your compartment is selected.
-1. For the **Description** field, use: _This agent assists compliance officers in reviewing applications, workloads, and policy compliance_.
-1. For the **Welcome message** field, use: _Hello! I’m your compliance assistant. How can I help?_
+1. For the **Description** field, use:
+
+ ``` text
+
+ This agent assists compliance officers in reviewing applications, workloads, and policy compliance
+
+ ```
+
+1. For the **Welcome message** field, use:
+
+ ``` text
+
+ Hello! I’m your compliance assistant. How can I help?
+
+ ```
+
1. Click the **Next** button.
@@ -49,7 +74,20 @@ This lab assumes you have:
1. Select the **RAG** tool option.
1. Under the **RAG Configuration** section, use _Knowledge base loan policy articles_ in the **Name** field.
-1. For the **Description** field, use: _Retrieves lending policy manuals and underwriting rules (DTI, credit score thresholds, FHA/VA limits, manual underwriting guidance)_.
+
+ ``` text
+
+ Knowledge base loan policy articles
+
+ ```
+
+1. For the **Description** field, use:
+
+ ``` text
+
+ Retrieves lending policy manuals and underwriting rules (DTI, credit score thresholds, FHA/VA limits, manual underwriting guidance)
+
+ ```
It is very important to provide a high-level description of the knowledge that this tool can retrieve. This allows the agent to make accurate decisions when choosing to invoke this tool.
@@ -61,6 +99,13 @@ This lab assumes you have:
1. In the **New knowledge base** form, use: _Compliance officer knowledge base loan policy articles_ for the **Name** field.
+
+ ``` text
+
+ Compliance officer knowledge base loan policy articles
+
+ ```
+
1. Make sure that your compartment is selected in the **Compartment** field.
1. In the **Data store type** field, we will select **Object storage** to be able to retrieve information from our storage bucket.
1. Make sure that **Enable hybrid search** is checked. Enabling this option instructs the system to combine lexical and semantic search when scanning our documents.
@@ -69,6 +114,13 @@ This lab assumes you have:
1. In the **Specify data source** form, use: _loan policy docs_ for the **Name** field.
+
+ ``` text
+
+ loan policy docs
+
+ ```
+
1. Make sure that the **Enable multi-modal parsing** option is **not** checked. This option enables parsing of rich content, such as charts and graphics, to allow responses based on visual elements. However, we do not have any images in our knowledge articles so right now this option is not required.
1. Under the **Data bucket** option, select the _loan-policy-manuals_ bucket into which we've previously uploaded the knowledge articles PDF files.
1. Check the **Select all in bucket option**. This option will automatically flag all of the file in the bucket for ingestion instead of us having to select each file individually.
@@ -97,8 +149,21 @@ This lab assumes you have:
1. Click the **SQL** option.
-1. For the **Name** field, use: _Loan Applications database_.
-1. For the **Description** field, use: _Tables contain applicants, loan applications, statuses, and officers for compliance review._
+1. For the **Name** field, use
+
+ ``` text
+
+ Loan Applications database
+
+ ```
+
+1. For the **Description** field, use:
+
+ ``` text
+
+ Tables contain applicants, loan applications, statuses, and officers for compliance review
+
+ ```
@@ -190,8 +255,9 @@ This lab assumes you have:
1. For **Model customization**, select the **Small** option.
1. For **Dialect**, select **Oracle SQL**.
-1. In the **Database tool connection in...** select the **connection-loancomplianceXXXX** connection we've previously created.
- >💡 _If your database tool connection does not appear (“Option not available”), select Cancel and re-add the SQL tool by repeating Task 3: Add the SQL Tool_
+1. In the **Database tool connection**, select _your compartment_, then choose the **connection-loancomplianceXXXX** connection we previously created.
+
+ >💡 _If your database tool connection does not appear in your compartment (“Option not available”), select Cancel and re-add the SQL tool by repeating Task 3: Add the SQL Tool._
13. Click the **Test connection** button. You should see a successful connection attempt.
14. Enable the **SQL execution** option. This option will instruct the tool to execute the SQL queries generated by the tool as a result of the user's requests. This will allow the agent to craft intelligent responses based on the data returned from the queries.
diff --git a/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-tenancy.md b/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-tenancy.md
index 3254da3a..20c2d75d 100644
--- a/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-tenancy.md
+++ b/oci-generative-ai-agents-fsi/4-create-the-agent/create-the-agent-tenancy.md
@@ -36,9 +36,30 @@ This lab assumes you have:
1. For the **Name** field use: _loan compliance agent_
+
+ ```text
+
+ loan compliance agent
+
+ ```
+
1. For the **Compartment** field, make sure that your compartment is selected.
1. For the **Description** field, use: _This agent assists compliance officers in reviewing applications, workloads, and policy compliance_.
+
+ ```text
+
+ This agent assists compliance officers in reviewing applications, workloads, and policy compliance.
+
+ ```
+
1. For the **Welcome message** field, use: _Hello! I’m your compliance assistant. How can I help?_
+
+ ```text
+
+ Hello! I'm your compliance assistant. How can I help?
+
+ ```
+
1. Click the **Next** button.
@@ -51,8 +72,21 @@ This lab assumes you have:
1. Select the **RAG** tool option.
1. Under the **RAG Configuration** section, use _Knowledge base loan policy articles_ in the **Name** field.
+
+ ```text
+
+ Knowledge base loan policy articles
+
+ ```
+
1. For the **Description** field, use: _Retrieves lending policy manuals and underwriting rules (DTI, credit score thresholds, FHA/VA limits, manual underwriting guidance)_.
+ ```text
+
+ Retrieves lending policy manuals and underwriting rules (DTI, credit score thresholds, FHA/VA limits, manual underwriting guidance).
+
+ ```
+
It is very important to provide a high-level description of the knowledge that this tool can retrieve. This allows the agent to make accurate decisions when choosing to invoke this tool.
@@ -63,6 +97,13 @@ This lab assumes you have:
1. In the **New knowledge base** form, use: _Compliance officer knowledge base loan policy articles_ for the **Name** field.
+
+ ```text
+
+ Compliance officer knowledge base loan policy atricles
+
+ ```
+
1. Make sure that your compartment is selected in the **Compartment** field.
1. In the **Data store type** field, we will select **Object storage** to be able to retrieve information from our storage bucket.
1. Make sure that **Enable hybrid search** is checked. Enabling this option instructs the system to combine lexical and semantic search when scanning our documents.
@@ -71,6 +112,13 @@ This lab assumes you have:
1. In the **Specify data source** form, use: _loan policy docs_ for the **Name** field.
+
+ ```text
+
+ loan policy docs
+
+ ```
+
1. Make sure that the **Enable multi-modal parsing** option is **not** checked. This option enable parsing of rich content, such as charts and graphics, to allow responses based on visual elements. However, we do not have any images in our knowledge articles so right now this option is not required.
1. Under the **Data bucket** option, select the _loan-policy-manuals_ bucket into which we've previously uploaded the knowledge articles PDF files.
1. Check the **Select all in bucket option**. This option will automatically flag all of the file in the bucket for ingestion instead of us having to select each file individually.
@@ -84,7 +132,7 @@ This lab assumes you have:
-1. The knowledge base will take a few minutes to create and ingest the data.
+1. The knowledge base will take a few minutes to create and ingest the data. You may proceed to the next step while the knowledge base provisions.
1. Back at the **Add knowledge bases** panel, make sure that the checkbox next to the knowledge base name is checked.
>💡 _If your knowledge base does not appear (“No items found”), you can still continue to the next step. The knowledge base is already selected and provisioning in the background. You may open a new tab and navigate to Agents > Knowledge Bases to confirm it is provisioning._
@@ -100,8 +148,21 @@ This lab assumes you have:
1. Click the **SQL** option.
1. For the **Name** field, use: _Loan Applications database_.
+
+ ```text
+
+ Loan Applications database.
+
+ ```
+
1. For the **Description** field, use: _Tables contain applicants, loan applications, statuses, and officers for compliance review._.
+ ```text
+
+ Tables contain applicants, loan applications, statuses, and officers for compliance review.
+
+ ```
+
1. Under **Import database schema configuration for this tool**, selec the **Inline** option which will allow us to use the same schema text we've used when we created the database.
@@ -150,7 +211,7 @@ This lab assumes you have:
);
```
-
+1. Under the **in-context learning examples**, leave the **None** option selected.
1. Under the **Description of tables and columns**, select the **Inline** option.
1. Copy and paste the following text into the **Description of tables and columns**. This verbal description contains details about each table and column. This will allow the tool to better understand the data stored in our database:
@@ -192,7 +253,7 @@ This lab assumes you have:
1. For **Model customization**, select the **Small** option.
1. For **Dialect**, select **Oracle SQL**.
-1. In the **Database tool connection in...** select the **connection-loancomplianceXXXX** connection we've previously created.
+1. In the **Database tool connection**, select your compartment, then choose the **connection-loancomplianceXXXX** connection we've previously created.
>💡 _If your database tool connection does not appear (“Option not available”), select Cancel and re-add the SQL tool by repeating Task 3: Add the SQL Tool_
13. Click the **Test connection** button. You should see a successful connection connection attempt.
diff --git a/oci-generative-ai-agents-fsi/4-create-the-agent/images/chicagoregion.png b/oci-generative-ai-agents-fsi/4-create-the-agent/images/chicagoregion.png
new file mode 100644
index 00000000..7444c412
Binary files /dev/null and b/oci-generative-ai-agents-fsi/4-create-the-agent/images/chicagoregion.png differ
diff --git a/oci-generative-ai-agents-fsi/5-test-the-solution/images/finalquestionresponse.png b/oci-generative-ai-agents-fsi/5-test-the-solution/images/finalquestionresponse.png
new file mode 100644
index 00000000..3a9f4752
Binary files /dev/null and b/oci-generative-ai-agents-fsi/5-test-the-solution/images/finalquestionresponse.png differ
diff --git a/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-sandbox.md b/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-sandbox.md
index e61e7e5f..d191df16 100644
--- a/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-sandbox.md
+++ b/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-sandbox.md
@@ -30,7 +30,7 @@ This lab assumes you have:
## Task 1: Overview of the chat page functionality
1. If the agent is still not showing as **Active**, give it a few more minutes to complete the provisioning process.
-1. Once the agent is showing as **Active**, click the **loan compliance officer** agent in the **Agents** list.
+1. Once the agent is showing as **Active**, click the **loan compliance agent** in the **Agents** list.
@@ -38,9 +38,9 @@ This lab assumes you have:
-1. In the chat page, on th left, make sure sure that both the **Agent compartment** and the **Agent endpoint compartment** are set to your compartment.
+1. In the chat page, on the left, make sure sure that both the **Agent compartment** and the **Agent endpoint compartment** are set to your compartment.
-1. On the top of the page, the **Agent** drop down should show **loan compliance officer** and the **Agent endpoint** drop down should show the newly created endpoint.
+1. On the top of the page, the **Agent** drop down should show **loan compliance agent** and the **Agent endpoint** drop down should show the newly created endpoint.
1. In the chat window, you'll be able to see the greeting message we have configured for the agent.
1. Other elements in the page include:
@@ -52,7 +52,14 @@ This lab assumes you have:
## Task 2: Let's test our agent
-1. To start, type the following question into you message box: _How many loan applications are pending review?_
+1. To start, type the following question into you message box:
+
+ ``` text
+
+ How many loan applications have been denied since June 2025?
+
+ ```
+
1. Click the **Submit** button.
@@ -71,33 +78,77 @@ This lab assumes you have:
1. The third trace shows how the agent composed the final response using the output of the previous steps.
-1. Click the **Close** button to close the traces pane.
1. Our next question would be: _Which loan officer has the most applications assigned?_ Let's see if the agent will be able to figure that out...
+
+ ``` text
+
+ Which loan officer has the most applications assigned?
+
+ ```
+
1. Click the **Submit** button.
-1. The agent shows the correct answer: **Olivia Brown**. Using the magic of Large Language Models (LLMs) and the clues we've left in the configuration of the agent and tools, the agent was able to decipher that the loan officer with the most applications assigned to them.
+1. The agent shows the correct answer: **Olivia Brown**. Using the magic of Large Language Models (LLMs) and the clues we've left in the configuration of the agent and tools, the agent was able to decipher that the loan agent with the most applications assigned to them.
1. Feel free to take a look at the **Traces** generated for this response.
-1. Next we'll ask the following: _List applications that have been pending for more than 7 days._
+1. Next we'll ask the following:
+
+ ``` text
+
+ List applications that have been in progress for more than 7 days.
+
+ ```
+
1. Click the **Submit** button.
-1. As you can see, the response included the type and amount for the two loans that have been pending for more than 7 days.
+1. The agent returned information on the one application that has been pending review for more than 7 days.
-1. Now that we have information about the tickets, let's see if we can pull up a loan policy document which can help us define "Debt-to-Income" limits. Type the following question: _Retrieve the policy document section that defines Debt-to-Income (DTI) limits and any exceptions._
+1. Now that we have information about the tickets, let's see if we can pull up a loan policy document which can help us define "Debt-to-Income" limits. Type the following question:
+
+ ``` text
+
+ Retrieve the policy document section that defines Debt-to-Income (DTI) limits and any exceptions.
+
+ ```
+
1. Click the **Submit** button.
+
+1. We can see the agent is able to pull important information about about limits for Back-End Debt-to-Income.
+
+ 
+
+1. Now we can see if there are any applications that violate a policy. Type into the message box:
+
+ ``` text
+
+ Identify any approved applications that violate policy (DTI or credit score); cite the rule and the record.
+
+ ```
+
+1. Click the **Submit** button.
+
1. As you can see, for this question, the agent figured out that the information required might be in the knowledge base articles. For this task it employed the RAG tool which searched for the relevant information in our loan policy docs stored in object storage. Feel free to look at the traces for this interaction which show the steps the agent took to give us the information we needed. In the response you can see that a summary of the document was provided, but, also, if you expand the **View citations** section, you'll be able to see a reference to the document(s) which were used to compose the reply with a direct link to the file(s), the page(s) from which content was extracted and more.
+ 
+
+1. Next we'll ask the following: _Identify any approved applications that violate policy (DTI or credit score); cite the rule and the record._
+1. Click the Submit button.
+
+ 
+
+1. The agent successfully detected an approved applicant whose credit score was inconsistent with the requirements outlined in the DTI and Credit Policy document.
+
1. We invite you to try some prompts of your own to experiment with agent.
@@ -108,16 +159,16 @@ Here are a few more prompts to try with the agent:
- _What is the minimum credit score for FHA vs Conventional loans?_
- _Show the distribution of credit scores by loan type_
-- _Identify any approved applications that violate policy (DTI or credit score); cite the rule and the record._
-- _Give me a risk dashboard: counts by status, average credit score and DTI by loan type, and total requested amount; include links to policy sections that define ‘risk’_
+- _Provide the policy language for VA loan eligibility and list the denied VA applications from the database_
+- _Provide the policy language for VA loan eligibility and list the denied VA applications from the database_
## Summary
-As you've experienced, the OCI Generative AI service allows you to ask complex questions about data stored in multiple locations and get intelligent answers. By simply pointing the various tools towards your data sources and providing the right context, the agent was able to automatically determine which data source should be accessed, retrieve the data for you, compile a coherent and concise response and provide references to the original data when applicable.
+As you've experienced, the OCI AI Agents service allows you to ask complex questions about data stored in multiple locations and get intelligent answers. By simply pointing the various tools towards your data sources and providing the right context, the agent was able to automatically determine which data source should be accessed, retrieve the data for you, compile a coherent and concise response and provide references to the original data when applicable.
-Another interesting advantage of building solutions on top the OCI Generative AI service is that the user is no longer restricted to tasks allowed by the application user interface. With a chat interface, the user can ask questions and get answers to any question which can be answered using the data in the system even if the system engineers did not plan for that specific scenario. For example, you can ask the agent to sort the results in any way that is supported by the data even if the application was not designed to give you that option.
+Another interesting advantage of building solutions on top the OCI AI Agents service is that the user is no longer restricted to tasks allowed by the application user interface. With a chat interface, the user can ask questions and get answers to any question which can be answered using the data in the system even if the system engineers did not plan for that specific scenario. For example, you can ask the agent to sort the results in any way that is supported by the data even if the application was not designed to give you that option.
-Although our use-case was focused on loan compliance, the OCI Generative AI service can be used to fuel many different use-cases which require deep understanding and retrieval of information from internal data sources, reasoning over the data, summarizing it, providing insights and more.
+Although our use-case was focused on loan compliance, the OCI AI Agents service can be used to fuel many different use-cases which require deep understanding and retrieval of information from internal data sources, reasoning over the data, summarizing it, providing insights and more.
## Learn More
@@ -125,5 +176,5 @@ Although our use-case was focused on loan compliance, the OCI Generative AI serv
## Acknowledgements
-- **Author** - Uma Kumar
-- **Contributors** - Hanna Rakhsha, Daniel Hart, Deion Locklear, Anthony Marino
+- **Author** - Deion Locklear
+- **Contributors** - Hanna Rakhsha, Daniel Hart, Uma Kumar, Anthony Marino
diff --git a/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-tenancy.md b/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-tenancy.md
index 1eb5adac..a1194504 100644
--- a/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-tenancy.md
+++ b/oci-generative-ai-agents-fsi/5-test-the-solution/test-the-solution-tenancy.md
@@ -53,6 +53,13 @@ This lab assumes you have:
## Task 2: Let's test our agent
1. To start, type the following question into you message box: _How many loan applications have been denied since June 2025?_
+
+ ```text
+
+ How many loan applications have been denied since June 2025?
+
+ ```
+
1. Click the **Submit** button.
@@ -76,6 +83,13 @@ This lab assumes you have:
1. Click the **Close** button to close the traces pane.
1. Our next question would be: _Which loan officer has the most applications assigned?_ Let's see if the agent will be able to figure that out...
+
+ ```text
+
+ Which loan officer has the most applications assigned?
+
+ ```
+
1. Click the **Submit** button.
@@ -86,10 +100,18 @@ This lab assumes you have:
1. Feel free to take a look at the **Traces** generated for this response.
1. Next we'll ask the following: _List applications that have been in progress for more than 7 days._
+
+ ```text
+
+ List applications that have been in progress for more than 7 days.
+
+ ```
+
1. Click the **Submit** button.
+1. The agent returned information on the one application that has been pending review for more than 7 days.
1. The agent returned information on the one application that has been pending review for more than 7 days.
@@ -105,6 +127,15 @@ This lab assumes you have:
+1. The agent successfully detected an approved applicant whose credit score was inconsistent with the requirements outlined in the DTI and Credit Policy document.
+
+ 
+
+1. Next we'll ask the following: _Identify any approved applications that violate policy (DTI or credit score); cite the rule and the record._
+1. Click the Submit button.
+
+ 
+
1. The agent successfully detected an approved applicant whose credit score was inconsistent with the requirements outlined in the DTI and Credit Policy document.
@@ -118,6 +149,7 @@ Here are a few more prompts to try with the agent:
- _What is the minimum credit score for FHA vs Conventional loans?_
- _Show the distribution of credit scores by loan type_
- _Provide the policy language for VA loan eligibility and list the denied VA applications from the database_
+- _Provide the policy language for VA loan eligibility and list the denied VA applications from the database_
## Summary