Overcoming frequent contact middle challenges with generative AI and Amazon SageMaker Canvas

Nice buyer expertise offers a aggressive edge and helps create model differentiation. As per the Forrester report, The State Of Customer Obsession, 2022, being customer-first could make a large influence on a corporation’s steadiness sheet, as organizations embracing this system are surpassing their friends in income development. Regardless of contact facilities being underneath fixed strain to do extra with much less whereas bettering buyer experiences, 80% of companies plan to increase their level of investment in Customer Experience (CX) to supply a differentiated buyer expertise. Speedy innovation and enchancment in generative AI has captured our thoughts and a spotlight and as per McKinsey & Company’s estimate, making use of generative AI to buyer care capabilities may enhance productiveness at a worth starting from 30–45% of present perform prices.

Amazon SageMaker Canvas offers enterprise analysts with a visible point-and-click interface that means that you can construct fashions and generate correct machine studying (ML) predictions with out requiring any ML expertise or coding. In October 2023, SageMaker Canvas introduced support for foundation models among its ready-to-use models, powered by Amazon Bedrock and Amazon SageMaker JumpStart. This lets you use pure language with a conversational chat interface to carry out duties similar to creating novel content material together with narratives, experiences, and weblog posts; summarizing notes and articles; and answering questions from a centralized data base—all with out writing a single line of code.

A name middle agent’s job is to deal with inbound and outbound buyer calls and supply assist or resolve points whereas fielding dozens of calls every day. Maintaining with this quantity whereas giving clients quick solutions is difficult with out time to analysis between calls. Sometimes, name scripts information brokers by calls and description addressing points. Nicely-written scripts enhance compliance, cut back errors, and enhance effectivity by serving to brokers shortly perceive issues and options.

On this put up, we discover how generative AI in SageMaker Canvas might help clear up frequent challenges clients could face when coping with contact facilities. We present how one can use SageMaker Canvas to create a brand new name script or enhance an current name script, and discover how generative AI might help with reviewing current interactions to carry insights which might be tough to acquire from conventional instruments. As a part of this put up, we offer the prompts used to resolve the duties and focus on architectures to combine these ends in your AWS Contact Center Intelligence (CCI) workflows.

Overview of answer

Generative AI basis fashions might help create highly effective name scripts in touch facilities and allow organizations to do the next:

• Create constant buyer experiences with a unified data repository to deal with buyer queries
• Cut back name dealing with time
• Improve assist staff productiveness
• Allow the assist staff with subsequent greatest actions to remove errors and take the subsequent greatest motion

With SageMaker Canvas, you possibly can select from a bigger choice of basis fashions to create compelling name scripts. SageMaker Canvas additionally means that you can evaluate a number of fashions concurrently, so a consumer can choose the output that almost all matches their want for the particular job that they’re coping with. To make use of generative AI-powered chatbots, the consumer first wants to supply a immediate, which is an instruction to inform the mannequin what you plan to do.

On this put up, we handle 4 frequent use circumstances:

• Creating new name scripts
• Enhancing an current name script
• Automating post-call duties
• Submit-call analytics

All through the put up, we use giant language fashions (LLMs) out there in SageMaker Canvas powered by Amazon Bedrock. Particularly, we use Anthropic’s Claude 2 mannequin, a robust mannequin with nice efficiency for all types of pure language duties. The examples are in English; nonetheless, Anthropic Claude 2 helps a number of languages. Check with Anthropic Claude 2 to study extra. Lastly, all of those outcomes are reproducible with different Amazon Bedrock fashions, like Anthropic Claude On the spot or Amazon Titan, in addition to with SageMaker JumpStart fashions.

Stipulations

For this put up, just be sure you have arrange an AWS account with applicable assets and permissions. Specifically, full the next prerequisite steps:

1. Deploy an Amazon SageMaker area. For directions, check with Onboard to Amazon SageMaker Domain.
2. Configure the permissions to arrange and deploy SageMaker Canvas. For extra particulars, check with Setting Up and Managing Amazon SageMaker Canvas (for IT Administrators).
3. Configure cross-origin useful resource sharing (CORS) insurance policies for SageMaker Canvas. For extra data, check with Grant Your Users Permissions to Upload Local Files.
4. Add the permissions to make use of basis fashions in SageMaker Canvas. For directions, check with Use generative AI with foundation models.

Observe that the companies that SageMaker Canvas makes use of to resolve generative AI duties can be found in SageMaker JumpStart and Amazon Bedrock. To make use of Amazon Bedrock, be sure you are utilizing SageMaker Canvas within the Area the place Amazon Bedrock is supported. Check with Supported Regions to study extra.

Create a brand new name script

For this use case, a contact middle analyst defines a name script with the assistance of one of many ready-to-use fashions out there in SageMaker Canvas, coming into an applicable immediate, similar to “Create a name script for an agent that helps clients with misplaced bank cards.” To implement this, after the group’s cloud administrator grants single-sign entry to the contact middle analyst, full the next steps:

1. On the SageMaker console, select Canvas within the navigation pane.
2. Select your area and consumer profile and select Open Canvas to open the SageMaker Canvas software.

3. Navigate to the Prepared-to-use fashions part and select Generate, extract and summarize content material to open the chat console.
4. With the Anthropic Claude 2 mannequin chosen, enter your immediate “Create a name script for an agent that helps clients with misplaced bank cards” and press Enter.

The script obtained by generative AI is included in a doc (similar to TXT, HTML, or PDF), and added to a data base that can information contact middle brokers of their interactions with clients.

When utilizing a cloud-based omnichannel contact middle answer similar to Amazon Connect, you possibly can make the most of AI/ML-powered options to enhance buyer satisfaction and agent effectivity. Amazon Connect Wisdom reduces the time brokers spend looking for solutions and permits fast decision of buyer points by offering data search and real-time suggestions whereas brokers discuss with clients. On this specific instance, Amazon Join Knowledge can synchronize with Amazon Simple Storage Service (Amazon S3) as a supply of content material for the data base, thereby incorporating the decision script generated with the assistance of SageMaker Canvas. For extra data, check with Amazon Connect Wisdom S3 Sync.

The next diagram illustrates this structure.

When the shopper calls the contact middle, and both they undergo an interactive voice response (IVR) or particular key phrases are detected in regards to the objective of the decision (for instance, “misplaced” and “bank card”), Amazon Join Knowledge will present strategies on how one can deal with the interplay to the agent, together with the related name script that was generated by SageMaker Canvas.

With SageMaker Canvas generative AI, contact middle analysts save time within the creation of name scripts, and are capable of shortly attempt new prompts to tweak the scripts creation.

Improve an current name script

As per the next survey, 78% of shoppers really feel that their name middle expertise improves when the customer support agent doesn’t sound as if they’re studying from a script. SageMaker Canvas can use generative AI assist you to analyze the prevailing name script and counsel enhancements to enhance the standard of name scripts. For instance, chances are you’ll need to enhance the decision script to incorporate extra compliance, or make your script sound extra well mannered.

To take action, select New chat and choose Claude 2 as your mannequin. You need to use the pattern transcript generated within the earlier use case and the immediate “I need you to behave as a Contact Heart High quality Assurance Analyst and enhance the under name transcript to make it compliant and sound extra well mannered.”

Automate post-call duties

You may also use SageMaker Canvas generative AI to automate post-call work in name facilities. Frequent use circumstances are name summarization, help in name logs completion, and customized follow-up message creation. This will enhance agent productiveness and cut back the chance of errors, permitting them to concentrate on higher-value duties similar to buyer engagement and relationship-building.

Select New chat and choose Claude 2 as your mannequin. You need to use the pattern transcript generated within the earlier use case and the immediate “Summarize the under Name transcript to spotlight Buyer situation, Agent actions, Name consequence and Buyer sentiment.”

When utilizing Amazon Join because the contact middle answer, you possibly can implement the decision recording and transcription by enabling Amazon Connect Contact Lens, which brings different analytics options similar to sentiment evaluation and delicate information redaction. It additionally has summarization by highlighting key sentences within the transcript and labeling the problems, outcomes, and motion gadgets.

Utilizing SageMaker Canvas means that you can go one step additional and from a single workspace choose from the ready-to-use fashions to investigate the decision transcript or generate a abstract, and even evaluate the outcomes to seek out the mannequin that most closely fits the particular use-case. The next diagram illustrates this answer structure.

Buyer post-call analytics

One other space the place contact facilities can make the most of SageMaker Canvas is to know interactions between buyer and brokers. As per the 2022 NICE WEM Global Survey, 58% of name middle brokers say they profit little or no from firm teaching periods. Brokers can use SageMaker Canvas generative AI for buyer sentiment evaluation to additional perceive what different greatest actions they may have taken to enhance buyer satisfaction.

We observe comparable steps as within the earlier use circumstances. Select New chat and choose Claude 2. You need to use the pattern transcript generated within the earlier use case and the immediate “I need you to behave as a Contact Heart Supervisor and critique and counsel enhancements to the agent habits within the buyer dialog.”

Clear up

SageMaker Canvas will routinely shut down any SageMaker JumpStart fashions began underneath it after 2 hours of inactivity. Comply with the directions on this part to close down these fashions sooner to save lots of prices. Observe that there isn’t any have to shut down Amazon Bedrock fashions as a result of they’re not deployed in your account.

1. To close down the SageMaker JumpStart mannequin, you possibly can select from two strategies:
   1. Select New chat, and on the mannequin drop-down menu, select Begin up one other mannequin. Then, on the Basis fashions web page, underneath Amazon SageMaker JumpStart fashions, select the mannequin (similar to Falcon-40B-Instruct) and in the best pane, select Shut down mannequin.
   2. If you’re evaluating a number of fashions concurrently, on the outcomes comparability web page, select the SageMaker JumpStart mannequin’s choices menu (three dots), then select Shut down mannequin.
2. Select Log off within the left pane to log off of the SageMaker Canvas software to cease the consumption of SageMaker Canvas workspace instance hours. It will launch all assets utilized by the workspace occasion.

Conclusion

On this put up, we analyzed how you need to use SageMaker Canvas generative AI in touch facilities to create hyper-personalized buyer interactions, improve contact middle analysts and brokers’ productiveness, and produce insights which might be laborious to get from conventional instruments. As illustrated by the completely different use-cases, SageMaker Canvas act as a single unified workspace, while not having to make use of completely different level merchandise. With SageMaker Canvas generative AI, contact facilities can enhance buyer satisfaction, cut back prices, and enhance effectivity. SageMaker Canvas generative AI empowers you to generate new and progressive options which have the potential to remodel the contact middle trade. You may also use generative AI to establish developments and insights in buyer interactions, serving to managers optimize their operations and enhance buyer satisfaction. Moreover, you need to use generative AI to supply coaching information for brand spanking new brokers, permitting them to study from artificial examples and enhance their efficiency extra shortly.

Study extra about SageMaker Canvas features and get started today to leverage visible, no-code machine studying capabilities.

In regards to the Authors

Davide Gallitelli is a Senior Specialist Options Architect for AI/ML. He’s based mostly in Brussels and works carefully with clients throughout the globe that need to undertake Low-Code/No-Code Machine Studying applied sciences, and Generative AI. He has been a developer since he was very younger, beginning to code on the age of seven. He began studying AI/ML at college, and has fallen in love with it since then.

Jose Rui Teixeira Nunes is a Options Architect at AWS, based mostly in Brussels, Belgium. He at present helps European establishments and companies on their cloud journey. He has over 20 years of experience in data know-how, with a robust concentrate on public sector organizations and communications options.

Anand Sharma is a Senior Accomplice Improvement Specialist for generative AI at AWS in Luxembourg with over 18 years of expertise delivering progressive services and products in e-commerce, fintech, and finance. Previous to becoming a member of AWS, he labored at Amazon and led product administration and enterprise intelligence capabilities.