Monthly Archives: January 2025

Given the value of data today, organizations across various industries are working with vast amounts of data across multiple formats. Manually reviewing and processing this information can be a challenging and time-consuming task, with a margin for potential errors. This is where intelligent document processing (IDP), coupled with the power of generative AI, emerges as a game-changing solution.

Enhancing the capabilities of IDP is the integration of generative AI, which harnesses large language models (LLMs) and generative techniques to understand and generate human-like text. This integration allows organizations to not only extract data from documents, but to also interpret, summarize, and generate insights from the extracted information, enabling more intelligent and automated document processing workflows.

The Education and Training Quality Authority (BQA) plays a critical role in improving the quality of education and training services in the Kingdom Bahrain. BQA reviews the performance of all education and training institutions, including schools, universities, and vocational institutes, thereby promoting the professional advancement of the nation’s human capital.

BQA oversees a comprehensive quality assurance process, which includes setting performance standards and conducting objective reviews of education and training institutions. The process involves the collection and analysis of extensive documentation, including self-evaluation reports (SERs), supporting evidence, and various media formats from the institutions being reviewed.

The collaboration between BQA and AWS was facilitated through the Cloud Innovation Center (CIC) program, a joint initiative by AWS, Tamkeen, and leading universities in Bahrain, including Bahrain Polytechnic and University of Bahrain. The CIC program aims to foster innovation within the public sector by providing a collaborative environment where government entities can work closely with AWS consultants and university students to develop cutting-edge solutions using the latest cloud technologies.

As part of the CIC program, BQA has built a proof of concept solution, harnessing the power of AWS services and generative AI capabilities. The primary purpose of this proof of concept was to test and validate the proposed technologies, demonstrating their viability and potential for streamlining BQA’s reporting and data management processes.

In this post, we explore how BQA used the power of Amazon Bedrock, Amazon SageMaker JumpStart, and other AWS services to streamline the overall reporting workflow.

The challenge: Streamlining self-assessment reporting

BQA has traditionally provided education and training institutions with a template for the SER as part of the review process. Institutions are required to submit a review portfolio containing the completed SER and supporting material as evidence, which sometimes did not adhere fully to the established reporting standards.

The existing process had some challenges:

• Inaccurate or incomplete submissions – Institutions might provide incomplete or inaccurate information in the submitted reports and supporting evidence, leading to gaps in the data required for a comprehensive review.
• Missing or insufficient supporting evidence – The supporting material provided as evidence by institutions frequently did not substantiate the claims made in their reports, which challenged the evaluation process.
• Time-consuming and resource-intensive – The process required dedicating significant time and resources to review the submissions manually and follow up with institutions to request additional information if needed to rectify the submissions, resulting in slowing down the overall review process.

These challenges highlighted the need for a more streamlined and efficient approach to the submission and review process.

Solution overview

The proposed solution uses Amazon Bedrock and the Amazon Titan Express model to enable IDP functionalities. The architecture seamlessly integrates multiple AWS services with Amazon Bedrock, allowing for efficient data extraction and comparison.

Amazon Bedrock is a fully managed service that provides access to high-performing foundation models (FMs) from leading AI startups and Amazon through a unified API. It offers a wide range of FMs, allowing you to choose the model that best suits your specific use case.

The following diagram illustrates the solution architecture.

The solution consists of the following steps:

1. Relevant documents are uploaded and stored in an Amazon Simple Storage Service (Amazon S3) bucket.
2. An event notification is sent to an Amazon Simple Queue Service (Amazon SQS) queue to align each file for further processing. Amazon SQS serves as a buffer, enabling the different components to send and receive messages in a reliable manner without being directly coupled, enhancing scalability and fault tolerance of the system.
3. The text extraction AWS Lambda function is invoked by the SQS queue, processing each queued file and using Amazon Textract to extract text from the documents.
4. The extracted text data is placed into another SQS queue for the next processing step.
5. The text summarization Lambda function is invoked by this new queue containing the extracted text. This function sends a request to SageMaker JumpStart, where a Meta Llama text generation model is deployed to summarize the content based on the provided prompt.
6. In parallel, the InvokeSageMaker Lambda function is invoked to perform comparisons and assessments. It compares the extracted text against the BQA standards that the model was trained on, evaluating the text for compliance, quality, and other relevant metrics.
7. The summarized data and assessment results are stored in an Amazon DynamoDB table
8. Upon request, the InvokeBedrock Lambda function invokes Amazon Bedrock to generate generative AI summaries and comments. The function constructs a detailed prompt designed to guide the Amazon Titan Express model in evaluating the university’s submission.

Prompt engineering using Amazon Bedrock

To take advantage of the power of Amazon Bedrock and make sure the generated output adhered to the desired structure and formatting requirements, a carefully crafted prompt was developed according to the following guidelines:

• Evidence submission – Present the evidence submitted by the institution under the relevant indicator, providing the model with the necessary context for evaluation
• Evaluation criteria – Outline the specific criteria the evidence should be assessed against
• Evaluation instructions – Instruct the model as follows:
  • Indicate N/A if the evidence is irrelevant to the indicator
  • Evaluate the university’s self-assessment based on the criteria
  • Assign a score from 1–5 for each comment, citing evidence directly from the content
• Response format – Specify the response as bullet points, focusing on relevant analysis and evidence, with a word limit of 100 words

To use this prompt template, you can create a custom Lambda function with your project. The function should handle the retrieval of the required data, such as the indicator name, the university’s submitted evidence, and the rubric criteria. Within the function, include the prompt template and dynamically populate the placeholders (${indicatorName}, ${JSON.stringify(allContent)}, and ${JSON.stringify(c.comment)}) with the retrieved data.

The Amazon Titan Text Express model will then generate the evaluation response based on the provided prompt instructions, adhering to the specified format and guidelines. You can process and analyze the model’s response within your function, extracting the compliance score, relevant analysis, and evidence.

The following is an example prompt template:

for (const c of comments) {
        const prompt = `
        Below is the evidence submitted by the university under the indicator "${indicatorName}":
        ${JSON.stringify(allContent)}
    
         Analyze and Evaluate the university's eviedence based on the provided rubric criteria:
        ${JSON.stringify(c.comment)}

        - If the evidence does not relate to the indicator, indicate that it is not applicable (N/A) without any additional commentary.
        
       Choose one from the below compliance score based on evidence submitted:
       1. Non-compliant: The comment does not meet the criteria or standards.
        2.Compliant with recommendation: The comment meets the criteria but includes a suggestion or recommendation for improvement.
        3. Compliant: The comment meets the criteria or standards.

        THE END OF THE RESPONSE THERE SHOULD BE EITHER SCORE: [SCORE: COMPLIANT OR NON-COMPLIANT OR COMPLIANT WITH RECOMMENDATION]
        Write your response in concise bullet points, focusing strictly on relevant analysis and evidence.
        **LIMIT YOUR RESPONSE TO 100 WORDS ONLY.**

        `;

        logger.info(`Prompt for comment ${c.commentId}: ${prompt}`);

        const body = JSON.stringify({
          inputText: prompt,
          textGenerationConfig: {
            maxTokenCount: 4096,
            stopSequences: [],
            temperature: 0,
            topP: 0.1,
          },
        });

The following screenshot shows an example of the Amazon Bedrock generated response.

Results

The implementation of Amazon Bedrock enabled institutions with transformative benefits. By automating and streamlining the collection and analysis of extensive documentation, including SERs, supporting evidence, and various media formats, institutions can achieve greater accuracy and consistency in their reporting processes and readiness for the review process. This not only reduces the time and cost associated with manual data processing, but also improves compliance with the quality expectations, thereby enhancing the credibility and quality of their institutions.

For BQA the implementation helped in achieving one of its strategic objectives focused on streamlining their reporting processes and achieve significant improvements across a range of critical metrics, substantially enhancing the overall efficiency and effectiveness of their operations.

Key success metrics anticipated include:

• Faster turnaround times for generating 70% accurate and standards-compliant self-evaluation reports, leading to improved overall efficiency.
• Reduced risk of errors or non-compliance in the reporting process, enforcing adherence to established guidelines.
• Ability to summarize lengthy submissions into concise bullet points, allowing BQA reviewers to quickly analyze and comprehend the most pertinent information, reducing evidence analysis time by 30%.
• More accurate compliance feedback functionality, empowering reviewers to effectively evaluate submissions against established standards and guidelines, while achieving 30% reduced operational costs through process optimizations.
• Enhanced transparency and communication through seamless interactions, enabling users to request additional documents or clarifications with ease.
• Real-time feedback, allowing institutions to make necessary adjustments promptly. This is particularly useful to maintain submission accuracy and completeness.
• Enhanced decision-making by providing insights on the data. This helps universities identify areas for improvement and make data-driven decisions to enhance their processes and operations.

The following screenshot shows an example generating new evaluations using Amazon Bedrock

Conclusion

This post outlined the implementation of Amazon Bedrock at the Education and Training Quality Authority (BQA), demonstrating the transformative potential of generative AI in revolutionizing the quality assurance processes in the education and training sectors. For those interested in exploring the technical details further, the full code for this implementation is available in the following GitHub repo. If you are interested in conducting a similar proof of concept with us, submit your challenge idea to the Bahrain Polytechnic or University of Bahrain CIC website.

About the Author

Maram AlSaegh is a Cloud Infrastructure Architect at Amazon Web Services (AWS), where she supports AWS customers in accelerating their journey to cloud. Currently, she is focused on developing innovative solutions that leverage generative AI and machine learning (ML) for public sector entities.

Read More

Amazon Q Business can increase productivity across diverse teams, including developers, architects, site reliability engineers (SREs), and product managers. Amazon Q Business as a web experience makes AWS best practices readily accessible, providing cloud-centered recommendations quickly and making it straightforward to access AWS service functions, limits, and implementations. These elements are brought together in a web integration that serves various job roles and personas exactly when they need it.

As enterprises continue to grow their applications, environments, and infrastructure, it has become difficult to keep pace with technology trends, best practices, and programming standards. Enterprises provide their developers, engineers, and architects with a range of knowledge bases and documents, such as usage guides, wikis, and tools. But these resources tend to become siloed over time and inaccessible across teams, resulting in reduced knowledge, duplication of work, and reduced productivity.

MuleSoft from Salesforce provides the Anypoint platform that gives IT the tools to automate everything. This includes integrating data and systems and automating workflows and processes, and the creation of incredible digital experiences—all on a single, user-friendly platform.

This post shows how MuleSoft introduced a generative AI-powered assistant using Amazon Q Business to enhance their internal Cloud Central dashboard. This individualized portal shows assets owned, costs and usage, and well-architected recommendations to over 100 engineers. For more on MuleSoft’s journey to cloud computing, refer to Why a Cloud Operating Model?

Developers, engineers, FinOps, and architects can get the right answer at the right time when they’re ready to troubleshoot, address an issue, have an inquiry, or want to understand AWS best practices and cloud-centered deployments.

This post covers how to integrate Amazon Q Business into your enterprise setup.

Solution overview

The Amazon Q Business web experience provides seamless access to information, step-by-step instructions, troubleshooting, and prescriptive guidance so teams can deploy well-architected applications or cloud-centered infrastructure. Team members can chat directly or upload documents and receive summarization, analysis, or answers to a calculation. Amazon Q Business uses supported connectors such as Confluence, Amazon Relational Database Service (Amazon RDS), and web crawlers. The following diagram shows the reference architecture for various personas, including developers, support engineers, DevOps, and FinOps to connect with internal databases and the web using Amazon Q Business.

In this reference architecture, you can see how various user personas, spanning across teams and business units, use the Amazon Q Business web experience as an access point for information, step-by-step instructions, troubleshooting, or prescriptive guidance for deploying a well-architected application or cloud-centered infrastructure. The web experience allows team members to chat directly with an AI assistant or upload documents and receive summarization, analysis, or answers to a calculation.

Use cases for Amazon Q Business

Small, medium, and large enterprises, depending on their mode of operation, type of business, and level of investment in IT, will have varying approaches and policies on providing access to information. Amazon Q Business is one of the AWS suites of generative AI services that provides a web-based utility to set up, manage, and interact with Amazon Q. It can answer questions, provide summaries, generate content, and complete tasks using the data and expertise found in your enterprise systems. You can connect internal and external datasets without compromising security to seamlessly incorporate your specific standard operating procedures, guidelines, playbooks, and reference links. With Amazon Q, MuleSoft’s engineering teams were able to address their AWS specific inquiries (such as support ticket escalation, operational guidance, and AWS Well-Architected best practices) at scale.

The Amazon Q Business web experience allows business users across various job titles and functions to interact with Amazon Q through the web browser. With the web experience, teams can access the same information and receive similar recommendations based on their prompt or inquiry, level of experience, and knowledge, ranging from beginner to advanced.

The following demos are examples of what the Amazon Q Business web experience looks like. Amazon Q Business securely connects to over 40 commonly used business tools, such as wikis, intranets, Atlassian, Gmail, Microsoft Exchange, Salesforce, ServiceNow, Slack, and Amazon Simple Storage Service (Amazon S3). Point Amazon Q Business at your enterprise data, and it will search your data, summarize it logically, analyze trends, and engage in dialogue with end users about the data. This helps users access their data no matter where it resides in their organization.

Amazon Q Business underscores prompting and response for prescriptive guidance. Optimizing Amazon Elastic Block Store (Amazon EBS) volumes as an example, it provided detailed migration steps from gp2 to gp3. This is a well-known use case asked about by several MuleSoft teams.

Through the web experience, you can effortlessly perform document uploads and prompts for summary, calculation, or recommendations based on your document. You have the flexibility to upload .pdf, .xls, .xlsx, or .csv files directly into the chat interface. You can also assume a persona such as FinOps or DevOps and get personalized recommendations or responses.

MuleSoft engineers used the Amazon Q Business web summarization feature to better understand Split Cost Allocation Data (SCAD) for Amazon Elastic Kubernetes Service (Amazon EKS). They uploaded the SCAD PDF documents to Amazon Q and got straightforward summaries. This helped them understand their customer’s use of MuleSoft Anypoint platform running on Amazon EKS.

Amazon Q helped analyze IPv4 costs by processing an uploaded Excel file. As the video shows, it calculated expenses for elastic IPs and outbound data transfers, supporting a proposed network estimate.

Amazon Q Business demonstrating its ability to provide tailored advice by responding to a specific user scenario. As the video shows, a user took on the role of a FinOps professional and asked Amazon Q to recommend AWS tools for cost optimization. Amazon Q then offered personalized suggestions based on this FinOps persona perspective.

Prerequisites

To get started with your Amazon Q Business web experience, you need the following prerequisites:

• An AWS account that will contain your AWS resources
• AWS IAM Identity Center configured for an Amazon Q Business application
• An Amazon Q Business subscription (Amazon Q Business Lite or Amazon Q Business Pro) and index (Starter or Enterprise) configured for an Amazon Q business application

Create an Amazon Q Business web experience

Complete the following steps to create your web experience:

• Create a sample Amazon Q Business application.
• Configure the Amazon Q Business application.
• Configure the Amazon Q Business data source connectors.
• Enhance the Amazon Q Business application.
• Customize the Amazon Q web experience.

The web experience can be used by a variety of business users or personas to yield accurate and repeatable recommendations for level 100, 200, and 300 inquiries. Amazon Q supports a variety of data sources and data connectors to personalize your user experience. You can also further enrich your dataset with knowledge bases within Amazon Q. With Amazon Q Business set up with your own datasets and sources, teams and business units within your enterprise can index from the same information on common topics such as cost optimization, modernization, and operational excellence while maintaining their own unique area of expertise, responsibility, and job function.

Clean Up

After trying the Amazon Q Business web experience, remember to remove any resources you created to avoid unnecessary charges. Complete the following steps:

1. Delete the web experience:
   • On the Amazon Q Business console, navigate to the Web experiences section within your application.
   • Select the web experience you want to remove.
   • On the Actions menu, choose Delete.
   • Confirm the deletion by following the prompts.
2. If you granted specific users access to the web experience, revoke their permissions. This might involve updating AWS Identity and Access Management (IAM) policies or removing users from specific groups in IAM Identity Center.
3. If you set up any custom configurations for the web experience, such as specific data source filters or custom prompts, make sure to remove these.
4. If you integrated the web experience with other tools or services, remove those integrations.
5. Check for and delete any Amazon CloudWatch alarms or logs specifically set up for monitoring this web experience.

After deletion, review your AWS billing to make sure that charges related to the web experience have stopped.

Deleting a web experience is irreversible. Make sure you have any necessary backups or exports of important data before proceeding with the deletion. Also, keep in mind that deleting a web experience doesn’t automatically delete the entire Amazon Q Business application or its associated data sources. If you want to remove everything, follow the Amazon Q Business application clean-up procedure for the entire application.

Conclusion

Amazon Q Business web experience is your gateway to a powerful generative AI assistant. Want to take it further? Integrate Amazon Q with Slack for an even more interactive experience.

Every organization has unique needs when it comes to AI. That’s where Amazon Q shines. It adapts to your business needs, user applications, and end-user personas. The best part? You don’t need to do the heavy lifting. No complex infrastructure setup. No need for teams of data scientists. Amazon Q connects to your data and makes sense of it with just a click. It’s AI power made simple, giving you the intelligence you need without the hassle.

To learn more about the power of a generative AI assistant in your workplace, see Amazon Q Business.

About the Authors

Rueben Jimenez is an AWS Sr Solutions Architect who designs and implements complex data analytics, machine learning, generative AI, and cloud infrastructure solutions.

Sona Rajamani is a Sr. Manager Solutions Architect at AWS.  She lives in the San Francisco Bay Area and helps customers architect and optimize applications on AWS. In her spare time, she enjoys traveling and hiking.

Erick Joaquin is a Sr Customer Solutions Manager for Strategic Accounts at AWS. As a member of the account team, he is focused on evolving his customers’ maturity in the cloud to achieve operational efficiency at scale.

Read More