Use Amazon SageMaker Unified Studio to construct complicated 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 atmosphere 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 technology of Amazon SageMaker is the middle on 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 atmosphere 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 may effectively construct generative AI purposes in a trusted and safe atmosphere utilizing Amazon Bedrock. You’ll be able to select from a number of high-performing basis fashions (FMs) and superior customization and tooling corresponding to Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails, Amazon Bedrock Agents, and Amazon Bedrock Flows. You’ll be able to quickly tailor and deploy generative AI purposes, and share with the built-in catalog for discovery.

On this put up, we show how you should utilize SageMaker Unified Studio to create complicated AI workflows utilizing Amazon Bedrock Flows.

Resolution overview

Contemplate FinAssist Corp, a number one monetary establishment creating a generative AI-powered agent help software. The answer gives the next key options:

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

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

The answer makes use of the next key elements:

• SageMaker Unified Studio – Gives the event atmosphere
• Movement app – Orchestrates the workflow, together with:
  • Data base queries
  • Immediate-based classification
  • Conditional routing
  • Agent-based response technology

The workflow processes consumer queries by means of the next steps:

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

Conditions

For this instance, you want the next:

• Access to SageMaker Unified Studio. (You will have the SageMaker Unified Studio portal URL out of your administrator). You’ll be able to authenticate utilizing both:
• The IAM consumer or IAM Id Heart consumer will need to have acceptable permissions for:
  • SageMaker Unified Studio.
  • Amazon Bedrock (together with Amazon Bedrock Flows, Amazon Bedrock Brokers, Amazon Bedrock Immediate Administration, and Amazon Bedrock Data Bases).
  • For extra info, consult with Identity-based policy examples.
• Access to Amazon Bedrock FMs (be sure that these are enabled on your account), for instance:Anthropic’s Claude 3 Haiku (for the agent).
• Configure access to your Amazon Bedrock serverless fashions for Amazon Bedrock in SageMaker Unified Studio tasks.
• Amazon Titan Embedding (for the data base).
• Pattern criticism information ready in CSV format for creating the data base.

Put together your information

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

complaint_id,product,sub_product,situation,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 situation","Escrow dispute","Buyer disputes mortgage fee enhance after current escrow evaluation","Reviewed escrow evaluation, defined property tax enhance influence, offered detailed fee breakdown","1. Ship written clarification of escrow evaluation 2. Schedule annual escrow assessment 3. Present fee help choices","Monetary Establishment-1","TX","Net","Closed with clarification","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 fee deadline","Situated wire switch in system, expedited processing, waived wire price","1. Affirm receipt with receiving financial institution 2. Replace buyer on supply 3. Doc course of enchancment wants","Monetary Establishment-2","FL","Cellphone","Closed with financial reduction","No"

Create a challenge

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

To create a challenge, full the next steps:

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

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

Create a immediate

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

1. In SageMaker Unified Studio, on the Construct menu, select Immediate below 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 criticism evaluation classifier. You'll obtain criticism information from a data base. Analyze the {{enter}} and reply with a single letter:
T: If the enter incorporates details about criticism decision timing, response time, or processing timeline (whether or not well timed or delayed)
F: For all different sorts of criticism info
Return solely 'T' or 'F' based mostly on whether or not the data base response is about decision timing. Don't add any extra textual content or clarification - 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 below 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 criticism info from a data base and questions on decision timing.
When responding to decision timing queries:
1. Use the offered criticism info to verify if it was resolved inside timeline
2. For well timed resolutions, present:
   - Affirmation of well timed completion
   - Particular actions taken (from the offered criticism information)
   - Subsequent steps that had been accomplished
2. For delayed resolutions, present:
   - Acknowledgment of delay
   - Commonplace compensation bundle:
     • $75 service credit score
     • Precedence Standing improve for six months
     • Service charges waived for present billing cycle
   - Actions taken (from the offered criticism information)
   - Contact info for follow-up: Precedence Line: ************** 
At all times reference the particular criticism particulars offered in your enter when discussing actions taken and backbone course of.

5. Select Save.

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

Create a circulation

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

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

2. Create a brand new circulation known as demo-flow.

Add a data base to your circulation software

Full the next steps so as to add a data base node to the circulation:

1. Within the navigation pane, on the Nodes tab, select Data 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 Data Base.
3. Within the Create Data 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 data base, select it within the circulation.
5. Within the particulars title, present the next info:
6. For Response technology mannequin, select Claude 3 Haiku.
7. Join the output of the circulation enter node with the enter of the data base node.
8. Join the output of the data base node with the enter of the circulation output node.

9. Select Save.

Add a immediate to your circulation software

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

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 data base node with the enter of the immediate node.
   
7. Select Save.

Add a situation to your circulation software

The situation node determines how the circulation handles various kinds of queries. It evaluates whether or not a question is about decision timing or basic criticism info, enabling the circulation 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 can obtain a direct response from the data 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 circulation software

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

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 prevailing circulation output node (FlowOutputNode).
   3. Join the output of the data base node (complaints_kb) to the enter of the next:
      1. The agent node (demo_agent).
      2. The circulation output node (FlowOutputNode).
   4. Join the output of the agent node (demo_agent) to a brand new circulation output node named FlowOutputNode_2.
      
4. Select Save.

Check the circulation software

Now that the circulation software is prepared, let’s take a look at it. On the suitable facet of the web page, select the increase icon to open the Check pane.

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

Clear up

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

Conclusion

On this put up, we demonstrated methods to construct an AI-powered criticism reference system utilizing a circulation software in SageMaker Unified Studio. Through the use of the built-in capabilities of SageMaker Unified Studio with Amazon Bedrock options like Amazon Bedrock Data Bases, Amazon Bedrock Brokers, and Amazon Bedrock Flows, you may quickly develop and deploy subtle AI purposes with out intensive coding.

As you construct AI workflows utilizing SageMaker Unified Studio, keep in mind to stick to the AWS Shared Responsibility Model for safety. Implement SageMaker Unified Studio security greatest practices, together with correct IAM configurations and information encryption. You can even consult with Secure a generative AI assistant with OWASP Top 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 tips helps set up strong AI purposes that preserve information integrity and system safety.

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

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

Concerning 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 obsessed with 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 flicks.

Vishal Naik is a Sr. Options Architect at Amazon Net Providers (AWS). He’s a builder who enjoys serving to prospects accomplish their enterprise wants and remedy complicated 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 brief movies on time journey and alternate universe themes.