Revolutionizing customer support: MaestroQA’s integration with Amazon Bedrock for actionable perception

This submit is cowritten with Harrison Hunter is the CTO and co-founder of MaestroQA.

MaestroQA augments name middle operations by empowering the standard assurance (QA) course of and buyer suggestions evaluation to extend buyer satisfaction and drive operational efficiencies. They help with operations akin to QA reporting, teaching, workflow automations, and root trigger evaluation.

On this submit, we dive deeper into considered one of MaestroQA’s key options—dialog analytics, which helps assist groups uncover buyer issues, handle factors of friction, adapt assist workflows, and determine areas for teaching by way of using Amazon Bedrock. We focus on the distinctive challenges MaestroQA overcame and the way they use AWS to construct new options, drive buyer insights, and enhance operational inefficiencies.

Amazon Bedrock is a completely managed service that provides a selection of high-performing basis fashions (FMs) from main AI firms, akin to AI21 Labs, Anthropic, Cohere, Meta, Mistral, Stability AI, and Amazon by way of a single API, together with a broad set of capabilities to construct generative AI functions with safety, privateness, and accountable AI.

The chance for open-ended dialog evaluation at enterprise scale

MaestroQA serves a various clientele throughout varied industries, together with ecommerce, marketplaces, healthcare, expertise acquisition, insurance coverage, and fintech. All of those prospects have a standard problem: the necessity to analyze a excessive quantity of interactions with their prospects. Analyzing these buyer interactions is essential to enhancing their product, enhancing their buyer assist, offering buyer satisfaction, and figuring out key business indicators. Nonetheless, buyer interplay information akin to name middle recordings, chat messages, and emails are extremely unstructured and require superior processing methods with a purpose to precisely and robotically extract insights.

When prospects obtain incoming calls at their name facilities, MaestroQA employs its proprietary transcription know-how, constructed by enhancing open supply transcription fashions, to transcribe the conversations. After the information is transcribed, MaestroQA makes use of know-how they’ve developed together with AWS companies akin to Amazon Comprehend to run varied forms of evaluation on the client interplay information. For instance, MaestroQA affords sentiment analysis for purchasers to determine the sentiment of their finish buyer throughout the assist interplay, enabling MaestroQA’s prospects to type their interactions and manually examine the perfect or worst interactions. MaestroQA additionally affords a logic/keyword-based guidelines engine for classifying buyer interactions primarily based on different elements akin to timing or course of steps together with metrics like Common Deal with Time (AHT), compliance or course of checks, and SLA adherence.

MaestroQA’s prospects love these evaluation options as a result of they permit them to repeatedly enhance the standard of their assist and determine areas the place they will enhance their product to raised fulfill their finish prospects. Nonetheless, they have been additionally concerned with extra superior evaluation, akin to asking open-ended questions like “What number of instances did the client ask for an escalation?” MaestroQA’s present guidelines engine couldn’t at all times reply a majority of these queries as a result of end-users may ask for a similar final result in many various methods. For instance, “Can I communicate to your supervisor?” and “I wish to communicate to somebody greater up” don’t share the identical key phrases, however are each asking for an escalation. MaestroQA wanted a technique to precisely classify buyer interactions primarily based on open-ended questions.

MaestroQA confronted a further hurdle: the immense scale of buyer interactions their purchasers handle. With purchasers dealing with anyplace from 1000’s to thousands and thousands of buyer engagements month-to-month, there was a urgent want for complete evaluation of assist crew efficiency throughout this huge quantity of interactions. Consequently, MaestroQA needed to develop an answer able to scaling to satisfy their purchasers’ intensive wants.

To begin growing this product, MaestroQA first rolled out a product known as AskAI. AskAI allowed prospects to run open-ended questions on a focused checklist of as much as 1,000 conversations. For instance, a buyer may use MaestroQA’s filters to seek out buyer interactions in Oregon throughout the previous two months after which run a root trigger evaluation question akin to “What are prospects annoyed about in Oregon?” to seek out churn danger anecdotes. Their prospects actually appreciated this characteristic and stunned MaestroQA with the breadth of use instances they coated, together with analyzing advertising campaigns, service points, and product alternatives. Prospects began to request the flexibility to run such a evaluation throughout all of their transcripts, which may quantity within the thousands and thousands, so they may quantify the impression of what they have been seeing and discover cases of necessary points.

Answer overview

MaestroQA determined to make use of Amazon Bedrock to deal with their prospects’ want for superior evaluation of buyer interplay transcripts. Amazon Bedrock’s broad selection of FMs from main AI firms, together with its scalability and security measures, made it a really perfect answer for MaestroQA.

MaestroQA built-in Amazon Bedrock into their present structure utilizing Amazon Elastic Container Service (Amazon ECS). The client interplay transcripts are saved in an Amazon Simple Storage Service (Amazon S3) bucket.

The next structure diagram demonstrates the request circulation for AskAI. When a buyer submits an evaluation request by way of MaestroQA’s net software, an ECS cluster retrieves the related transcripts from Amazon S3, cleans and codecs the immediate, sends them to Amazon Bedrock for evaluation utilizing the client’s chosen FM, and shops the ends in a database hosted in Amazon Elastic Compute Cloud (Amazon EC2), the place they are often retrieved by MaestroQA’s frontend net software.

MaestroQA affords their prospects the flexibleness to select from a number of FMs accessible by way of Amazon Bedrock, together with Anthropic’s Claude 3.5 Sonnet, Anthropic’s Claude 3 Haiku, Mistral 7b/8x7b, Cohere’s Command R and R+, and Meta’s Llama 3.1 fashions. This permits prospects to pick the mannequin that most accurately fits their particular use case and necessities.

The next screenshot reveals how the AskAI characteristic permits MaestroQA’s prospects to make use of the big variety of FMs accessible on Amazon Bedrock to ask open-ended questions akin to “What are among the frequent points in these tickets?” and generate helpful insights from customer support interactions.

To deal with the excessive quantity of buyer interplay transcripts and supply low-latency responses, MaestroQA takes benefit of the cross-Region inference capabilities of Amazon Bedrock. Initially, they have been doing the load balancing themselves, distributing requests between accessible AWS US Areas (us-east-1, us-west-2, and so forth) and accessible EU Areas (eu-west-3, eu-central-1, and so forth) for his or her North American and European prospects, respectively. Now, the cross-Area inference functionality of Amazon Bedrock permits MaestroQA to realize twice the throughput in comparison with single-Area inference, a crucial think about scaling their answer to accommodate extra prospects. MaestroQA’s crew now not has to spend effort and time to foretell their demand fluctuations, which is very key when utilization will increase for his or her ecommerce prospects across the vacation season. Cross-Area inference dynamically routes visitors throughout a number of Areas, offering optimum availability for every request and smoother efficiency throughout these high-usage durations. MaestroQA screens this setup’s efficiency and reliability utilizing Amazon CloudWatch.

Advantages: How Amazon Bedrock added worth

Amazon Bedrock has enabled MaestroQA to innovate quicker and achieve a aggressive benefit by providing their prospects highly effective generative AI options for analyzing buyer interplay transcripts. With Amazon Bedrock, MaestroQA can now present their prospects with the flexibility to run open-ended queries throughout thousands and thousands of transcripts, unlocking priceless insights that have been beforehand inaccessible.

The broad selection of FMs accessible by way of Amazon Bedrock permits MaestroQA to cater to their prospects’ numerous wants and preferences. Prospects can choose the mannequin that finest aligns with their particular use case, discovering the correct steadiness between efficiency and worth.

The scalability and cross-Area inference capabilities of Amazon Bedrock allow MaestroQA to deal with excessive volumes of buyer interplay transcripts whereas sustaining low latency, no matter their prospects’ geographical places.

MaestroQA takes benefit of the sturdy security measures and moral AI practices of Amazon Bedrock to bolster buyer confidence. These measures guarantee that consumer information stays safe throughout processing and isn’t used for mannequin coaching by third-party suppliers. Moreover, Amazon Bedrock availability in Europe, coupled with its geographic management capabilities, permits MaestroQA to seamlessly prolong AI companies to European prospects. This growth is achieved with out introducing extra complexities, thereby sustaining operational effectivity whereas adhering to Regional information laws.

The adoption of Amazon Bedrock proved to be a sport changer for MaestroQA’s compact improvement crew. Its serverless structure allowed the crew to quickly prototype and refine their software with out the burden of managing advanced {hardware} infrastructure. This shift enabled MaestroQA to channel their efforts into optimizing software efficiency moderately than grappling with useful resource allocation. Furthermore, Amazon Bedrock affords seamless compatibility with their present AWS surroundings, permitting for a clean integration course of and additional streamlining their improvement workflow. MaestroQA was ready to make use of their present authentication course of with AWS Identity and Access Management (IAM) to securely authenticate their software to invoke massive language fashions (LLMs) inside Amazon Bedrock. They have been additionally ready to make use of the acquainted AWS SDK to rapidly and effortlessly combine Amazon Bedrock into their software.

General, through the use of Amazon Bedrock, MaestroQA is ready to present their prospects with a strong and versatile answer for extracting priceless insights from their buyer interplay information, driving steady enchancment of their merchandise and assist processes.

Success metrics

The early outcomes have been exceptional.

A lending firm makes use of MaestroQA to detect compliance dangers on 100% of their conversations. Earlier than, brokers would increase inner escalations if a client complained concerning the mortgage or expressed being in a susceptible state. Nonetheless, this course of was handbook and error inclined, and the lending firm would miss many of those dangers. Now, they’re able to detect compliance dangers with nearly 100% accuracy.

A medical system firm, who’s required to report system points to the FDA, now not depends solely on brokers to report internally customer-reported points, however makes use of this service to investigate all of their conversations to ensure all complaints are flagged.

An schooling firm has been in a position to substitute their handbook survey scores with an automatic buyer sentiment rating that elevated their pattern measurement from 15% to 100% of conversations.

The most effective is but to come back.

Conclusion

Utilizing AWS, MaestroQA was in a position to innovate quicker and achieve a aggressive benefit. Corporations from totally different industries akin to monetary companies, healthcare and life sciences, and EdTech all share the frequent want to offer higher buyer companies for his or her purchasers. MaestroQA was in a position to allow them to try this by rapidly pivoting to supply highly effective generative AI options that solved tangible enterprise issues and enhanced total compliance.

Try MaestroQA’s characteristic AskAI and their LLM-powered AI Classifiers when you’re concerned with higher understanding your buyer conversations and survey scores. For extra about Amazon Bedrock, see Get started with Amazon Bedrock and study options akin to cross-Region inference to assist scale your generative AI options globally.

In regards to the Authors

Carole Suarez is a Senior Options Architect at AWS, the place she helps information startups by way of their cloud journey. Carole focuses on information engineering and holds an array of AWS certifications on a wide range of subjects together with analytics, AI, and safety. She is captivated with studying languages and is fluent in English, French, and Tagalog.

Ben Gruher is a Generative AI Options Architect at AWS, specializing in startup prospects. Ben graduated from Seattle College the place he obtained bachelor’s and grasp’s levels in Laptop Science and Information Science.

Harrison Hunter is the CTO and co-founder of MaestroQA the place he leads the engineer and product groups. Previous to MaestroQA, Harrison studied laptop science and AI at MIT.