Use Amazon SageMaker Unified Studio to construct advanced AI workflows utilizing Amazon Bedrock Flows

Organizations face the problem to handle information, a number of synthetic intelligence and machine studying (AI/ML) instruments, and workflows throughout completely different environments, impacting productiveness and governance. A unified growth surroundings consolidates information processing, mannequin growth, and AI software deployment right into a single system. This integration streamlines workflows, enhances collaboration, and accelerates AI answer growth from idea to manufacturing.

The subsequent era of Amazon SageMaker is the middle to your information, analytics, and AI. SageMaker brings collectively AWS AI/ML and analytics capabilities and delivers an built-in expertise for analytics and AI with unified entry to information. Amazon SageMaker Unified Studio is a single information and AI growth surroundings the place you could find and entry your information and act on it utilizing AWS analytics and AI/ML providers, for SQL analytics, information processing, mannequin growth, and generative AI software growth.

With SageMaker Unified Studio, you’ll be able to effectively construct generative AI functions in a trusted and safe surroundings utilizing Amazon Bedrock. You possibly can select from a choice of high-performing basis fashions (FMs) and superior customization and tooling equivalent to Amazon Bedrock Information Bases, Amazon Bedrock Guardrails, Amazon Bedrock Brokers, and Amazon Bedrock Flows. You possibly can quickly tailor and deploy generative AI functions, and share with the built-in catalog for discovery.

On this publish, we exhibit how you should use SageMaker Unified Studio to create advanced AI workflows utilizing Amazon Bedrock Flows.

Answer overview

Take into account FinAssist Corp, a number one monetary establishment growing a generative AI-powered agent assist software. The answer provides the next key options:

• Criticism reference system – An AI-powered system offering fast entry to historic grievance information, enabling customer support representatives to effectively deal with buyer follow-ups, assist inside audits, and help in coaching new workers.
• Clever information base – A complete information supply of resolved complaints that shortly retrieves related grievance particulars, decision actions, and consequence summaries.
• Streamlined workflow administration – Enhanced consistency in buyer communications by standardized entry to previous case info, supporting compliance checks and course of enchancment initiatives.
• Versatile question functionality – An easy interface supporting numerous question situations, from buyer inquiries about previous resolutions to inside opinions of grievance dealing with procedures.

Let’s discover how SageMaker Unified Studio and Amazon Bedrock Flows, built-in with Amazon Bedrock Information Bases and Amazon Bedrock Brokers, deal with these challenges by creating an AI-powered grievance reference system. The next diagram illustrates the answer structure.

The answer makes use of the next key parts:

• SageMaker Unified Studio – Offers the event surroundings
• Movement app – Orchestrates the workflow, together with:
  • Information base queries
  • Immediate-based classification
  • Conditional routing
  • Agent-based response era

The workflow processes consumer queries by the next steps:

1. A consumer submits a complaint-related query.
2. The information base supplies related grievance info.
3. The immediate classifies if the question is about decision timing.
4. Based mostly on the classification utilizing the situation, the appliance takes the next motion:
   1. Routes the question to an AI agent for particular decision responses.
   2. Returns common grievance info.
5. The applying generates an applicable response for the consumer.

Conditions

For this instance, you want the next:

• Entry to SageMaker Unified Studio. (You’ll need the SageMaker Unified Studio portal URL out of your administrator). You possibly can authenticate utilizing both:
• The IAM consumer or IAM Id Heart consumer should have applicable permissions for:
  • SageMaker Unified Studio.
  • Amazon Bedrock (together with Amazon Bedrock Flows, Amazon Bedrock Brokers, Amazon Bedrock Immediate Administration, and Amazon Bedrock Information Bases).
  • For extra info, discuss with Id-based coverage examples.
• Entry to Amazon Bedrock FMs (make sure that these are enabled to your account), for instance:Anthropic’s Claude 3 Haiku (for the agent).
• Configure entry to your Amazon Bedrock serverless fashions for Amazon Bedrock in SageMaker Unified Studio initiatives.
• Amazon Titan Embedding (for the information base).
• Pattern grievance information ready in CSV format for creating the information base.

Put together your information

Now we have created a pattern dataset to make use of for Amazon Bedrock Information Bases. This dataset has info of complaints acquired by customer support representatives and determination info.The next is an instance from the pattern dataset:

complaint_id,product,sub_product,difficulty,sub_issue,complaint_summary,action_taken,next_steps,financial_institution,state,submitted_via,resolution_type,timely_response
FIN-2024-001,04/26/24,"Mortgage","Typical mortgage","Cost difficulty","Escrow dispute","Buyer disputes mortgage cost enhance after current escrow evaluation","Reviewed escrow evaluation, defined property tax enhance impression, offered detailed cost breakdown","1. Ship written rationalization of escrow evaluation 2. Schedule annual escrow evaluate 3. Present cost help choices","Monetary Establishment-1","TX","Internet","Closed with rationalization","Sure"
FIN-2024-002,04/26/24,"Cash switch","Wire switch","Processing delay","Worldwide switch","Wire switch of $10,000 delayed, buyer involved about worldwide cost deadline","Positioned wire switch in system, expedited processing, waived wire price","1. Verify receipt with receiving financial institution 2. Replace buyer on supply 3. Doc course of enchancment wants","Monetary Establishment-2","FL","Telephone","Closed with financial aid","No"

Create a undertaking

In SageMaker Unified Studio, customers can use initiatives to collaborate on numerous enterprise use instances. Inside initiatives, you’ll be able to handle information property within the SageMaker Unified Studio catalog, carry out information evaluation, manage workflows, develop ML fashions, construct generative AI functions, and extra.

To create a undertaking, full the next steps:

1. Open the SageMaker Unified Studio touchdown web page utilizing the URL out of your admin.
2. Select Create undertaking.
3. Enter a undertaking title and elective description.
4. For Challenge profile, select Generative AI software growth.
5. Select Proceed.

6. Full your undertaking configuration, then select Create undertaking.

Create a immediate

Let’s create a reusable immediate to seize the directions for FMs, which we’ll use later whereas creating the movement software. For extra info, see Reuse and share Amazon Bedrock prompts.

1. In SageMaker Unified Studio, on the Construct menu, select Immediate beneath Machine Studying & Generative AI.

2. Present a reputation for the immediate.
3. Select the suitable FM (for this instance, we select Claude 3 Haiku).
4. For Immediate message, we enter the next:

You're a grievance evaluation classifier. You'll obtain grievance information from a information base. Analyze the {{enter}} and reply with a single letter:
T: If the enter comprises details about grievance decision timing, response time, or processing timeline (whether or not well timed or delayed)
F: For all different sorts of grievance info
Return solely 'T' or 'F' based mostly on whether or not the information base response is about decision timing. Don't add any further textual content or rationalization - reply with simply the only letter 'T' or 'F'.

5. Select Save.

6. Select Create model.

Create a chat agent

Let’s create a chat agent to deal with particular decision responses. Full the next steps:

1. In SageMaker Unified Studio, on the Construct menu, select Chat agent beneath Machine Studying & Generative AI.
2. Present a reputation for the immediate.
3. Select the suitable FM (for this instance, we select Claude 3 Haiku).
4. For Enter a system immediate, we enter the next:

You're a Monetary Complaints Assistant AI. You'll obtain grievance info from a information base and questions on decision timing.
When responding to decision timing queries:
1. Use the offered grievance info to substantiate if it was resolved inside timeline
2. For well timed resolutions, present:
   - Affirmation of well timed completion
   - Particular actions taken (from the offered grievance information)
   - Subsequent steps that have been accomplished
2. For delayed resolutions, present:
   - Acknowledgment of delay
   - Normal compensation bundle:
     • $75 service credit score
     • Precedence Standing improve for six months
     • Service charges waived for present billing cycle
   - Actions taken (from the offered grievance information)
   - Contact info for follow-up: Precedence Line: ************** 
All the time reference the particular grievance particulars offered in your enter when discussing actions taken and determination course of.

5. Select Save.

6. After the agent is saved, select Deploy.
7. For Alias title, enter demoAlias.
8. Select Deploy.

Create a movement

Now that now we have our immediate and agent prepared, let’s create a movement that may orchestrate the grievance dealing with course of:

1. In SageMaker Unified Studio, on the Construct menu, select Movement beneath Machine Studying & Generative AI.

2. Create a brand new movement referred to as demo-flow.

Add a information base to your movement software

Full the next steps so as to add a information base node to the movement:

1. Within the navigation pane, on the Nodes tab, select Information Base.
2. On the Configure tab, present the next info:
   1. For Node title, enter a reputation (for instance, complaints_kb).
   2. Select Create new Information Base.
3. Within the Create Information Base pane, enter the next info:
   1. For Identify, enter a reputation (for instance, complaints).
   2. For Description, enter an outline (for instance, consumer complaints info).
   3. For Add information sources, choose Native file and add the complaints.txt file.
   4. For Embeddings mannequin, select Titan Textual content Embeddings V2.
   5. For Vector retailer, select OpenSearch Serverless.
   6. Select Create.

4. After you create the information base, select it within the movement.
5. Within the particulars title, present the next info:
6. For Response era mannequin, select Claude 3 Haiku.
7. Join the output of the movement enter node with the enter of the information base node.
8. Join the output of the information base node with the enter of the movement output node.

9. Select Save.

Add a immediate to your movement software

Now let’s add the immediate you created earlier to the movement:

1. On the Nodes tab within the Movement app builder pane, add a immediate node.
2. On the Configure tab for the immediate node, present the next info:
3. For Node title, enter a reputation (for instance, demo_prompt).
4. For Immediate, select financeAssistantPrompt.
5. For Model, select 1.
6. Join the output of the information base node with the enter of the immediate node.
   
7. Select Save.

Add a situation to your movement software

The situation node determines how the movement handles several types of queries. It evaluates whether or not a question is about decision timing or common grievance info, enabling the movement to route the question appropriately. When a question is about decision timing, it is going to be directed to the chat agent for specialised dealing with; in any other case, it is going to obtain a direct response from the information base. Full the next steps so as to add a situation:

1. On the Nodes tab within the Movement app builder pane, add a situation node.
2. On the Configure tab for the situation node, present the next info:
   1. For Node title, enter a reputation (for instance, demo_condition).
   2. Beneath Situations, for Situation, enter conditionInput == "T".
   3. Join the output of the immediate node with the enter of the situation node.
      
3. Select Save.

Add a chat agent to your movement software

Now let’s add the chat agent you created earlier to the movement:

1. On the Nodes tab within the Movement app builder pane, add the agent node.
2. On the Configure tab for the agent node, present the next info:
   1. For Node title, enter a reputation (for instance, demo_agent).
   2. For Chat agent, select DemoAgent.
   3. For Alias, select demoAlias.
3. Create the next node connections:
   1. Join the enter of the situation node (demo_condition) to the output of the immediate node (demo_prompt).
   2. Join the output of the situation node:
      1. Set If situation is true to the agent node (demo_agent).
      2. Set If situation is fake to the present movement output node (FlowOutputNode).
   3. Join the output of the information base node (complaints_kb) to the enter of the next:
      1. The agent node (demo_agent).
      2. The movement output node (FlowOutputNode).
   4. Join the output of the agent node (demo_agent) to a brand new movement output node named FlowOutputNode_2.
      
4. Select Save.

Take a look at the movement software

Now that the movement software is prepared, let’s check it. On the precise facet of the web page, select the develop icon to open the Take a look at pane.

Within the Enter immediate textual content field, we will ask a couple of questions associated to the dataset created earlier. The next screenshots present some examples.

Clear up

To scrub up your assets, delete the movement, agent, immediate, information base, and related OpenSearch Serverless assets.

Conclusion

On this publish, we demonstrated methods to construct an AI-powered grievance reference system utilizing a movement software in SageMaker Unified Studio. By utilizing the built-in capabilities of SageMaker Unified Studio with Amazon Bedrock options like Amazon Bedrock Information Bases, Amazon Bedrock Brokers, and Amazon Bedrock Flows, you’ll be able to quickly develop and deploy subtle AI functions with out intensive coding.

As you construct AI workflows utilizing SageMaker Unified Studio, keep in mind to stick to the AWS Shared Accountability Mannequin for safety. Implement SageMaker Unified Studio safety greatest practices, together with correct IAM configurations and information encryption. You can too discuss with Safe a generative AI assistant with OWASP Prime 10 mitigation for particulars on methods to assess the safety posture of a generative AI assistant utilizing OWASP TOP 10 mitigations for frequent threats. Following these pointers helps set up sturdy AI functions that keep information integrity and system safety.

To study extra, discuss with Amazon Bedrock in SageMaker Unified Studio and be part of discussions and share your experiences in AWS Generative AI Neighborhood.

We sit up for seeing the modern options you’ll create with these highly effective new options.

In regards to the authors

Sumeet Tripathi is an Enterprise Assist Lead (TAM) at AWS in North Carolina. He has over 17 years of expertise in expertise throughout numerous roles. He’s enthusiastic about serving to prospects to cut back operational challenges and friction. His focus space is AI/ML and Power & Utilities Phase. Outdoors work, He enjoys touring with household, watching cricket and films.

Vishal Naik is a Sr. Options Architect at Amazon Internet Providers (AWS). He’s a builder who enjoys serving to prospects accomplish their enterprise wants and clear up advanced challenges with AWS options and greatest practices. His core space of focus contains Generative AI and Machine Studying. In his spare time, Vishal loves making quick movies on time journey and alternate universe themes.