AWS re:Invent 2023 - Principal Financial enhances CX using call analytics and generative AI (AIM223)

Summary

このトークは、Amazon BedrockのAartika Sardana Chandrasが主催したセッションで、新しい生成型AI時代において、顧客体験をどのように向上させるかについて議論しています。Amazon TranscribeのChris Lottと、Principal Financial GroupのMiguel Sanchezが参加し、コンタクトセンターにおけるAIと生成型AIの活用方法、既存の顧客のメリット、そして最新の生成型AIのイノベーションについて説明しています。彼らは、AIを用いた自動化されたチャットボットやリアルタイム分析ツール、会話分析を通じて、顧客サービスの改善を実現する方法を提案しています。

Takeaways

• 🤖 AIと生成型AIの新しい時代において、顧客体験を向上させる方法について議論する。
• 📊 顧客会話などのデータを使用して、アクション可能な洞察を導き出し、ビジネスを向上させる。
• 🗣️ 顧客は待ち時間の短縮とセルフサービスのソリューションを望んでいる。
• 💼 客服代理店は、電話でのサポートに集中することが困難であり、管理者は全ての通話を分析することができない。
• 🤖 対話型IVRやチャットボットを通じて、顧客が必要な時に答えを見つけられるようにする。
• 📞 リアルタイム通話分析と代理店支援ソリューションを導入し、通話の進行中にエージェントが迅速に対応できるようにする。
• 🔍 通話分析を使用して、通話の全体的なセンチメントや代理店のパフォーマンスを分析する。
• 🏦 WaFdBankは、AWSの対話型AIプラットフォームを使用して、顧客がシンプルな通話で費や時間を大幅に削減。
• 📈 Magellan Healthは、リアルタイム通話分析と代理店支援ソリューションを導入して、代理店のトレーニング時間を短縮。
• 📊 State Auto Insuranceは、通話分析により運営費用を大幅に削減し、TSB銀行は通話分析を100%にまで拡大。
• 🌐 AWSのコンタクトセンターソリューションは、どの業界にも適用できる横断的なソリューションである。

Q & A

アパルティーカ・サーダ・チャンドラスはどのような役職を務めていますか？

アパルティーカ・サーダ・チャンドラスはAmazon Bedrockの高級製品マーケティングマネージャーです。

今回のセッションの目的は何ですか？

今回のセッションの目的は、新しい時代の生成的AIにおいて、顧客体験をどのように影響を与え、連絡先センター空間で顧客体験を向上させる方法について議論することです。

クライアントとの会話から得られるデータはどのように役立つか？

クライアントとの会話から得られるデータは、行動可能な洞察を導き出し、パフォーマンスを向上させ、ビジネスを促進するために使用されます。

WaFdBankはどのようにして顧客体験を改善しましたか？

WaFdBankは、AWSが提供するセルサービス会話AIプラットフォームを使用して、シンプルな電話（例えば残高照会）で顧客が費やした時間を90%削減しました。

マゼラン・ヘルスはリアルタイムコール分析とエージェント支援ソリューションをどのように活用しましたか？

マゼラン・ヘルスは、リアルタイムコール分析とエージェント支援ソリューションを活用して、エージェントのトレーニング時間を3～5日間短縮し、1通あたり9～15秒の節約を達成しました。

ステート・オート・保険はポストコール分析によってどのくらいの費用削減を実現しましたか？

ステート・オート・保険は、ポストコール分析を利用して、約80万ドルの運営費用を削減しました。

TSB銀行はポストコール分析をどのように活用していますか？

TSB銀行は、1年間で500万回のコールを分析し、10～12%の分析率から100%にまで拡大し、顧客がコールする理由を特定し、顧客体験を向上させることができました。

アマゾン・トランスクリプトの新機能として発表されたものは何ですか？

アマゾン・トランスクリプトの新機能として、100以上のロケールをサポートする新しいマルチ十億パラメーターの音声基礎モデルが発表されました。また、コール要約を含むTranscribe Call Analytics APIの一部として、コールの要約を生成する機能も提供されるようになりました。

プリンシパル・フィナンシャル・グループはどのようにしてポストコール分析を活用していますか？

プリンシパル・フィナンシャル・グループは、ポストコール分析を使用して、1年以上にわたって100万以上のコールを処理し、複数のユースケースで使用しています。また、トピック階層定義やカスタマーインテントの特定、レポート機能の向上など、PCAフレームワークのカスタマイズと改善を進めています。

プリンシパル・フィナンシャル・グループのロードマップにはどのような計画が含まれていますか？

プリンシパル・フィナンシャル・グループのロードマップには、ポストコール分析の使用、メールインタラクションの追加、Google Analyticsとの統合、トピック階層定義の改善、AWSのQ&Aボットの展開など、多岐にわたる計画が含まれています。

セッションの最後に提供されるリソースは何ですか？

セッションの最後に提供されるリソースには、ディスカバリーワークショップやProof of Conceptの開始方法、Amazon Connectソリューションに関する情報、AWSのProServeチームやCCIパートナー、コンサルティングパートナー、ISVに連絡する方法などが含まれます。また、AIMLに関する他のセッションやワークショップ、チャットトーク、その他のブレイクアウトセッションの情報を提供しています。

Outlines

00:00

📣 イベントの開始と目的

イベントの司会であるAartika Sardana Chandrasが、Amazon Bedrockの製品マーケティングマネージャーとして、今日のイベントの目的と議題について説明しています。Generative AIの新しい時代において、顧客体験を向上させる方法について話し合い、特にコンタクトセンター空間でのAIMLとGenerative AIの活用に焦点を当てます。

05:01

🤖 顧客体験の向上とチャットボットの活用

Aartikaは、顧客が望むセルフサービスソリューションであるチャットボットや対話型アシスタントの重要性について説明し、コンタクトセンターの課題に対するAIMLの活用方法と、それがもたらす利点を紹介しています。また、Principal Financial GroupがAWSサービスを利用してポストコール分析ソリューションを構築し、顧客会話から洞察を得る方法についても触れています。

10:04

📊 顧客体験の改善と効果

Chris Lottが、WaFdBankやMagellan Health、State Auto Insurance、TSB Bankなどの企業がAWSのサービスを利用して、顧客体験を改善し、コスト削減を達成した事例を紹介しています。特に、WaFdBankがシンプルな電話での時間を大幅に短縮し、Magellan Healthがエージェントのトレーニング時間を短縮した例が挙げられています。

15:08

🛠️ ポストコール分析のアーキテクチャと活用

Chrisは、ポストコール分析のアーキテクチャとその活用方法について説明しています。オーディオフォーマットからAWSのLambda関数をトリガーし、ステップ関数ワークフローを開始して洞察を生成するプロセスを詳細に説明しています。また、Amazon Bedrockを利用してトピックやアクションアイテムを特定し、データレイクを構築する方法も触れています。

20:08

🌟 AWSの新しい機能とPCAの活用

Chrisは、Amazon Transcribeの新しい機能とPCAの活用方法について発表しています。新しい多億パラメーターの音声モデルの導入により、翻訳の正確性が向上し、さまざまな方言や環境でのサポートが強化されました。また、Transcribe Call Analytics APIの一部として提供される新しいコール要約機能についても説明しています。

25:09

Principal Financial GroupのPCA体験

Miguel Sanchezが、Principal Financial GroupがAWSと協力してPCAフレームワークを構築し、顧客体験を向上させる方法について話しています。PCAの導入により、1年以上で100万以上の通話が処理され、多角的なチャネルでの顧客エンゲージメントを提供することを目指しています。また、PCAのデータを使って、新しいチャットボットを展開し、トピック階層定義を改善する計画も紹介されています。

30:13

🗓️ 2024年のロードマップとPCAの未来

Miguelは、Principal Financial Groupの2024年のロードマップとPCAの未来について説明しています。PCAの成功をもとに、メールインタラクションの統合や、Google Analyticsとの連携、トピック階層定義の改善、新しいビジネスドメインへの対応、そしてAIエージェントの展開を計画しています。PCAデータを基に、AWS BedrockとKendraを活用して、カスタマーサービスを向上させる戦略も明らかされています。

35:19

📝 次のステップとリソース

Aartikaが、イベントの最後に参加者に対して、ディスカバリーワークショップやProof of Conceptの開始方法、AWSの専門家やパートナーとの連携、Amazon Connectソリューションについての詳細を提供し、今後のセッションやワークショップに参加するように呼びかけています。また、フィードバックを求めるアンケートを公開し、質問コーナーを開いています。

Keywords

💡Generative AI

生成型AIは、新しいデータやコンテンツを生成する能力を持つ技術です。このビデオでは、生成型AIがカスタマーサービスやコンタクトセンターの改善にどのように役立つかを説明しています。例えば、AIを利用することで、カスタマーのニーズをより迅速かつ効果的に満たすことができます。

💡Contact Center

コンタクトセンターは、企業が顧客サービスを提供する場所で、電話やチャットボットを通じて顧客の問い合わせや問題を解決します。このビデオでは、コンタクトセンターの課題やその改善方法について説明されています。

💡Customer Experience

顧客体験とは、顧客が企業の製品やサービスを利用する際に感じる満足度や価値についての総称です。このビデオでは、AI技術を活用して顧客体験を向上させる方法が提案されています。

💡AIML

AIML（Artificial Intelligence Markup Language）は、対話型AIアプリケーションのためのマークアップ言語です。このビデオでは、AIMLがコンタクトセンターでのカスタマーサービスの改善にどのように役立つかが説明されています。

💡Real-time Call Analytics

リアルタイムコール分析は、電話中の対話をリアルタイムで分析し、エージェントが迅速かつ適切な対応ができる技術です。このビデオでは、リアルタイムコール分析がどのようにエージェントのパフォーマンスを向上させるかが説明されています。

💡Post-call Analytics

ポストコール分析は、電話終了後に収集されたデータを分析し、ビジネスのトレンドや顧客のニーズを理解するための技術です。このビデオでは、ポストコール分析がどのように企業のビジネスパフォーマンスを向上させるかが説明されています。

💡Amazon Transcribe

Amazon Transcribeは、AWS提供の音声認識サービスで、音声をテキストに変換します。このビデオでは、Amazon Transcribeがコール分析や対話型AIアプリケーションにどのように役立つかが説明されています。

💡Amazon Comprehend

Amazon Comprehendは、AWS提供の自然言語処理（NLP）サービスで、テキストデータから感情やテーマを分析します。このビデオでは、Amazon Comprehendがコール分析にどのように役立つかが説明されています。

💡Amazon Bedrock

Amazon Bedrockは、AWS提供のAIサービスで、対話型AIアプリケーションの開発を支援します。このビデオでは、Amazon Bedrockがコール分析やビジネス洞察の生成にどのように役立つかが説明されています。

💡Amazon Connect

Amazon Connectは、AWS提供のコンタクトセンターソリューションで、企業が顧客サービスを提供するためのプラットフォームです。このビデオでは、Amazon Connectがコンタクトセンターの改善にどのように役立つかが説明されています。

💡AWS CCI Solutions

AWS CCI（Contact Center Intelligence）ソリューションは、AWSが提供するコンタクトセンター向けのAIサービスのセットです。このビデオでは、AWS CCIソリューションがコンタクトセンターの課題解決にどのように役立つかが説明されています。

Highlights

Aartika Sardana Chandras introduces the session on Generative AI's impact on customer experience in contact centers.

The focus is on using customer conversation data to derive actionable insights for business improvement.

Chris Lott and Miguel Sanchez join to discuss solutions for contact center challenges.

Customers prefer self-service solutions like chatbots, with over 80% seeking such options.

Contact center agents are often overburdened, with 30% of their time spent on administrative tasks.

Managers struggle to analyze all call data, with many unable to do so effectively.

Three solutions are presented: self-service virtual agents, real-time call analytics, and conversation analytics.

WaFdBank saw a 90% reduction in time for simple calls using AWS conversational AI platform.

Magellan Health reduced agent training time and saved significant hours per year with real-time call analytics.

State Auto Insurance saved $800,000 in operational expenses by analyzing all calls with post-call analytics.

TSB bank analyzed 5 million calls to identify call intents, improving customer experience by routing calls to the right agents.

AWS contact center solutions are industry-agnostic and can be applied across various sectors.

Amazon Connect and AWS CCI solutions are introduced as flexible options for call analytics and Generative AI.

Amazon Transcribe and Amazon Bedrock are key components in the AWS language AI services.

Post-call analytics uses a data lake approach to store and access insights from customer interactions.

Live Call Analytics, a sister solution to post-call analytics, provides real-time analysis during calls.

Amazon Transcribe launches a new multi-billion parameter speech model supporting over 100 locales.

Miguel Sanchez shares Principal Financial Group's journey with AWS Post Call Analytics and Generative AI.

Principal Financial Group aims to migrate all applications and data points to the cloud by 2026, with AWS as a strategic partner.

PCA has been successfully deployed at Principal Financial Group, processing over 1 million calls.

Principal Financial Group is working on integrating email interactions into the PCA framework for a holistic customer engagement view.

The company is also planning to deploy AWS Lex for virtual assistance, using PCA data to create conversational purposes.

Transcripts

- Good afternoon everyone.

Thank you so much for joining us today.

My name is Aartika Sardana Chandras

and I'm a senior product marketing manager

for Amazon Bedrock.

So why are we here today?

In this new era of Generative AI,

we thought we should discuss

how we can impact customer experience,

elevate customer experience use

in the contact center space,

using AIML as well as Generative AI.

We are gonna focus on how you can use all the data

that you've collected through your customer conversations

or other customer contacts,

and use it to derive actionable insights

to improve performance and boost your business.

Joining me today are my colleague Chris Lott

and our customer, Miguel Sanchez.

- Hey everybody, my name is Chris,

I'm a senior solutions architect for Amazon Transcribe.

- Good afternoon, I'm Miguel Sanchez.

I am an analytics director

and regional Chief data officer

at Principal Financial Group.

- Awesome.

So we do have a fully packed agenda

for the session today.

We are gonna start with the key contact center challenges,

the personas and what their day-to-day life looks like,

how you can use AIML

to form certain contact center solutions

to alleviate those challenges,

the benefits seen by some of our customers,

and then move on to some

of the latest innovations of Generative AI

and how Principal Financial Group

has used these solutions using AWS services

to form their post call analytic solutions

to derive insights from all their customer conversations.

So first of all, I wanna, you know,

start with three different personas

like I mentioned.

The first and the most important persona is our customers.

With a show of hands, how many of you

like to spend 10 minutes on a call?

Press one for this, press two for this,

press three for this.

No one, right?

Our customers don't like it either.

More than 80% of customers today

want self-service solutions.

They want a chatbot or a conversational assistant

to be able to solve their challenges.

Second, our agents.

They're the face of the company's

customer service department.

In the last couple of years, you all will agree

that the contact centers have been overburdened with calls.

With days like today, like a Cyber Monday

where people are sitting home and ordering things,

they want to call those contact centers

and solve all their problems.

And 30% of the times,

instead of being able to focus on calls,

these agents are spending time in admin jobs.

That's what we've heard from our customers,

so we need to solve that problem.

And lastly, managers and supervisors.

You are collecting data day in and day out,

but are you able to analyze those calls?

Our customers tell us, not all of them.

So we want to empower customers

to be able to analyze 100% of their calls,

which is why we have the three solutions

mapped to those three challenges.

The first one, as I was saying,

the self-service virtual agents, your conversational IVRs,

your chat bots, they're boosted using Generative AI

and attached to the same knowledge bases

that are used by company agents

so that customers can find answers when they want

at a time that's convenient to them.

The second solution for the challenges related to agents

happens while a conversation is still going on.

The real time call analytics and agent assist solution.

So this is the holy grail of understanding, you know,

what the customer wants,

when they are, you know, really troubled.

So you are able to pick up insights

like an ongoing call sentiment.

The agents are empowered to find answers faster

because they have prompts coming to them,

giving them responses off that ongoing conversation.

So they are more focused, the answers are given faster,

the call resolution time goes down

and of course the customers are happy.

Last but not the least,

and something we'll focus a lot on in today's presentation

is conversation analytics.

Like I was saying, you have millions of calls in a year,

but are you able to analyze them?

We have a post call analytics solution

that lets you do just that

so that you can derive insights like overall call sentiment,

how are your agents performing?

What are the upcoming business trends?

What are the top things your customers are complaining about

or maybe what are the top things they're happy about?

So that you can double down on those things

and boost your business performance.

So let's look at what some of our customers

have already seen in terms of the benefits.

Starting with WaFdBank,

which used the cell service conversational AI platform

provided by AWS.

They saw a 90% reduction in time

that customers spent on a simple call,

like a balance inquiry.

It went down from four and a half minutes to 28 seconds.

That's like huge.

And 30% of their calls

are now contained using these self-service solutions.

Moving on to Magellan Health,

which is using the real time call analytics

and agent assist solution.

They brought down the agent training time

by three to five days

and though it, you know, sounds like a small number,

they started saving 9 to 15 seconds per call.

But over 2.2 million calls per year,

they saved about 4,400 hours.

You can do the math by multiplying the agent salary

and other operational costs.

Then for our post-call analytics solution,

we have two customers, State Auto Insurance

that saved about $800,000 in operational expenses

because of being able to analyze all of their calls.

And TSB bank, they were able to analyze

5 million calls in a year.

They were analyzing about only 10 to 12%

and they moved to 100% call analysis

which helped them identify over 800 call intents,

the reason why their customers were calling,

which helped them improve customer experience

because they were able to transfer their calls

to the right agent that mapped to the intent of the call.

Now this is my favorite slide

because it shows the sweat and blood

that the team has put in

in making our customers happy

and trust us with contact center solutions.

AWS contact center solutions are horizontal.

No matter what industry you belong to,

I'm sure we can help you solve your challenges

by introducing AI and Generative AI

into your contact centers.

And with that, I'll hand over to my colleague Chris.

- Thanks Aartika.

So to get started quickly with call analytics

and Generative AI and AWS,

we have two flexible options.

The first one is Amazon Connect.

It's our contact center solution

that allows customers of any size

to get started with a contact center

and provide superior customer experience.

For those that are unable to move to Amazon Connect,

for example, if you have a custom solution

that you've already built

or you're locked into a contact center vendor,

we have what's called the AWS CCI solutions.

These are example APIs and code

that allow you to get started on AWS

no matter the contact center platform.

Now, regardless of which way you go,

they're both powered by AWS language AI services

such as Amazon Transcribe

to go from speech to text,

and we use Generative AI such as Amazon Bedrock.

Now the AWS CCI solutions cover the three use cases

that Aartika mentioned earlier, self-service chatbots,

real-time agent assist and conversational analytics.

The CCI solutions support many different contact sensors

such as 8x8, Cisco, Avaya and others.

And they do this by using industry standard file formats

and protocols such as WAV files, MP3s and (inaudible).

Today we're gonna be focusing on a solution

which is called post-call analytics,

and Miguel's gonna dive into the details

of how Principal Financial Group

is using post-call analytics.

But all these solutions are open source,

which means that you have access to all the code

and can get started quickly in building your solutions.

At the end of the session we're gonna show all the resources

that are available to you,

but one that's pretty easy to remember

that I put up there is amazon.com/post-call-analytics

When building post-call analytics,

we worked backwards from customer challenges

that we heard from customers with contact centers.

For example, lack of insights into why customers are calling

or challenges in being able to evaluate

how their agents are performing.

So we used AWS language AI services

such as Amazon Transcribe to generate call summaries.

We use Amazon Comprehend to do call analytics

and generate conversational insights.

And we do call summarization

and other Generative AI tasks with Amazon Bedrock.

And the result is being able to discover key business trends

and insights into identifying root causes

while your customers are calling

and improving agent productivity.

So now let's dive into the architecture

and see how post-call analytics works.

So first, like I mentioned,

it starts with standard audio formats

that are uploaded to AWS in an S3 bucket.

From here a lambda function is triggered

that starts a step function workflow

that will merge all those language AI services together

and use them to generate those insights.

Additionally, we use Amazon Bedrock

to go deeper into doing things like identifying topics

and identifying action items

that your agents have to perform at the end of the call.

We take all of this data,

the transcription, the insights,

and we store them in DynamoDB and Amazon S3.

Now it's important to note

that what we're doing here is building a data lake

of all of those insights.

Now we provide two different ways to access those insights.

The first one is post-call analytics contains

a react based user interface that's hosted in S3

and CloudFront that allow you to get started building

your own user interfaces on top of PCA.

And again, all of that source code is available

for you open source on GitHub.

Additionally, like I mentioned,

because we have this data lake in S3,

we can write SQL queries using Amazon Athena

and build aggregated insights.

And with that we can also build dashboards

with Amazon QuickSight.

Now finally I should call out

that post-call analytics actually has a sister solution

called Live Call Analytics

and that's powered by Amazon Chime SDK Voice connector.

With this, we can analyze the calls

in real time as they're happening

and the benefit of that of course,

like Aartika mentioned is we can provide agent assist

so for example, suggested responses

or completing tasks in real time.

So now I'm proud to announce a few new features

of Amazon Transcribe.

We've been seeing that

in order to effectively leverage Generative AI,

customers are increasingly looking to increase accuracy

and language support.

So today I'm excited to announce a launch

of a new multi-billion parameter speech foundation model

that powers Amazon Transcribe

that supports over 100 locales.

This multi-billion parameter model is trained

using the best in class supervision approach

and it learns the inherent patterns of universal speech

and accents across millions of hours

of unlabeled audio data.

The speech foundation model provides a 30% relative accuracy

improvement across all the locales,

and it also enhances the readability

with more accurate punctuation and capitalization.

The model provides expanded support for different accents,

noisy environments and other acoustic conditions,

and it supports the many features

that we love about Amazon Transcribe,

for example, automatic language identification

and speaker diarization.

The second announcement today, which is available as preview

is call summarization as part

of the Transcribe Call Analytics API.

So now with one single API Call,

you can transcribe the call,

generate insights such as issues, action items

and outcomes and sentiment,

and get a call summary again all with one single API call.

It optionally allows for redaction,

not of just the transcript but also the summary.

And with that I want to turn it over to Miguel Sanchez,

chief regional data officer of Principal financial Group

and he's gonna talk about how Principal

takes advantage of post-call analytics

and Generative AI on AWS.

- Thank you, Chris.

I'm so happy and glad to be here sharing our journey.

I'd like to take the first 30 seconds to honor someone.

My co-sign, Daniel Orozco Sanchez who used to work for AWS

and who passed away about a year ago.

We both had a dream to be presenting here at re:Invent.

So here we are, this is for Daniel.

(audience applauds)

I'm gonna be walking you through providing some context

on who we are, why we are working with AWS,

and specifically dealing

and working with the AWS Post Call Analytics framework.

Also, I'll be sharing the approach

that we still are having for deployment purposes,

sharing the roadmap that we are gonna be facing for 2024,

and also I'm gonna be sharing

some demos, demonstration, on the PCA console

with the latest features that Chris

was referring to summarization.

And also I'm gonna be sharing another

really important topic for us.

It is the topic hierarchy definition

that we assembled together with our business stakeholders.

So let's go to who we are.

So basically Principal Financial Group.

It's an established financial services firm

with more than 140 years in the market.

We are a global investment management leader

and serve more than 62 million customers around the world.

Right now we are accountable in managing

around $635 billion assets under management

and related with engagement centers,

it's worth to mention that we are

processing around 30,000 customer calls on a daily basis,

supported on more than 1,500 engagement centers.

The average call time, it's eight minutes.

The average speed to answer is 51 seconds

with callers waiting less than a minute

to talk to an available agent.

We are facing a real challenge

and we had to look for alternatives to improve

not only our engagement center operation,

but also to improve the customer experience.

Why AWS and PCA for Principle?

There is an strategic definition behind the scenes.

We set an aggressive goal

to migrate all the applications

and data points to the cloud by the end of 2026.

AWS is our strategic partner for that journey.

But in addition to that,

I am proudly leading a language AI team.

We had the chance to benchmark each one of the components

that are embedded within the PCA framework.

So we run a benchmark comparing

with another solutions offer in the industry.

We also validated that AWS is following

the enterprise architecture definitions.

And we found very high accuracy on one component

that Chris was referring to previously.

TCA, Transcribe Call Analytics.

To be honest with you, this is a unique component

that we didn't find in any other offering.

Basically it's the combination of transcription

with data mining,

and now it's getting infused by Gen AI.

This is a unique component that was, you know,

part of the rational that we used to define

to be working with PCA.

And the last, but not the least one,

it's the access to subject matter experts

and product owners.

We are so pleased to have the support

from people like Chris,

and Aartika to be working with us,

even debugging code and deploying the platform.

We have created a great partnership with AWS

for this specific journey.

Where we are at right now.

We started with PCA about year and a half ago.

Once we selected the platform,

we established a nice partnership with AWS

supported on two specific programs.

The first one our architect resident program

and the second one, something called a data lab.

So basically my language AI team

partnered with AWS supported on these programs

and we were able to refine

and personalize the PCA framework.

We were able to deploy it,

and then I'm very proud to say

that today we have been able to process

more than 1 million calls.

PCA has proven to be successful

and we are using it in multiple use cases

while actively improving scaling

and evaluating with product managers,

customer experience consultants and servicing leaders.

There is another important topic

that I would like to refer to.

It's an open source framework.

We've got a lot of flexibility

to incorporate additional components

and additional channels.

Right now we are bringing the customer email interaction

as a part of the PCA framework.

And of course with all these announcements now,

we are relying on Bedrock for multiple purposes.

I'm gonna be providing more details about it.

Now I'm gonna be pointing to the requirement

that we receive.

Basically this is the business requirement,

this is the challenge.

I already mentioned that we are dealing with a lot

of customer voice interactions

and we were looking to enable conversational analytics,

but this is related with the voice of customer program.

Basically we were told you need to find something out there,

an IT platform that it's gonna be basically dealing with

unstructured and unsolicited data

following some specific business rules.

Those rules are listen,

basically to provide the ability to capture data

from multiple data sources.

Interpret, synthesize data for actionable insights.

Act, implement enhancements to improve outcomes.

Monitor, which is quantify the performance

of customer experience efforts.

And last govern, align, commit and prioritize.

So those are the principles that were defined

by our business stakeholders.

The voice of customer program.

With that definition and that business requirement,

basically we define the approach.

How we are gonna be moving with PCA.

Once we selected the platform

and created this partnership with AWS,

we define three main phases.

The first phase was for technical deployment

and in there basically we were dealing with specific MVPs

and activities related with transcription.

I'm gonna be providing more details,

but we are dealing with Genesys Cloud

as our engagement center platform.

So we are pulling data from our Genesys Cloud platform

and we are going through PCA.

So the first step is to go through AWS Transcribe

and get transcripts, high quality transcripts.

We were able to provide sentiment analysis,

topic and intent identification,

PII reduction and obfuscation.

This is where the beauty of TCS is playing

a key role in here.

We are a high regulated industry

and we cannot expose our data to everyone.

So PII, it's a big, big deal for us.

So PII was also considered

for phase one and reporting.

It is also worth to mention

that we are relying on AWS QuickSight

and one particular feature called Q,

which is the NLP feature.

For phase two, we define the topic hierarchy definition.

This is (inaudible)

this is something that we created internally,

this is something that we refine

with our business stakeholders.

Basically we are relying on PCA data points

and supported by Bedrock,

we were able to create our own taxonomy,

topic taxonomy definition.

So this is something that we released

and this is a video that I'm gonna be sharing with you.

The second one was customer intent.

The customer intent is gonna be playing a key role

not only for voice of customer

but for the customer experience.

Because with the customer intent,

we are gonna be able to determine the why.

Why is the customer calling us?

And that why basically it's gonna be a foundational piece

for another initiative that was triggered by PCA,

which is virtual assistance, Lex,

we are gonna be deploying AWS Lex.

And the last two basically it's related

with reporting enhancements and additions

because we realized that considering

that we've got the voice interactions,

now let's bring additional channels into the equation.

The last one is related with virtual assistance.

I was already mentioning about this.

We are looking to deploy AWS Lex,

and the PCA data is being used to create

multiple conversational purposes.

There is another functionality that we've got in there

and that's relying on the topic hierarchy definition.

Basically it's the emerging team detection.

With that feature, we are able to detect

if there is something getting important

or perhaps something that it is creating friction

within the customer experience.

And there is another component here I would like to point

because it is related with Gen AI, it is model retraining.

I'm gonna be more specific on model retraining

because it is not related with Bedrock.

This is related with another feature

provided by AWS called SageMaker Jumpstart.

So for some specific and internal definitions,

we are working with the small pre-trained models

and that's where we are pointing to model retraining.

So that's basically the approach

that we are following for the PCA deployment.

I already mentioned that once we discovered

the power that we had with PCA,

our analyst and leaders were pointing to create

a holistic view on customer interactions.

So the first definition was

let's bring customer email interaction

and we are gonna be bringing more and more channels.

Right now we are working trying to glue the email

and voice interaction together,

and we are relying on a graph database approach,

working and dealing with another AWS component

called Neptune.

So we are gluing all those interactions

and now looking to bring customer surveys,

social media interaction and digital interaction.

Our goal as a company basically

is provide a comprehensive perspective

on multi-channel customer engagement.

How the PCA framework was implemented.

I already mentioned that we are integrated

with Genesys Cloud.

We are ingesting data on a daily basis

for some specific use.

It is also worth to mention

that we were not following a big bag approach.

Initially, we were dealing

with some specific business domains.

This is also important.

This is not an IT only related initiative.

This is a business initiative.

So the first business domain that we were working

and dealing with was money related with money out

and then we were moving on to money in.

So we were bringing data

and we're still bringing data on a daily basis

from Genesys cloud.

The data, the raw data is being saved

on an Amazon S3 bucket and relying on AWS Transcribe,

basically we are creating Metadata

and some basic KPIs related with the calls.

All that information is being exposed in a JSON format

and it is being consume using QuickSight.

From there, the workflow will be pointing to use Comprehend

and Comprehend basically it's gonna be related with TCA.

With Comprehend and Transcribe,

we are able to identify topics, intents,

issues, takeaways, sentiment analysis.

And now we've got Bedrock.

So with Bedrock, which is the next step within our workflow,

we are able to get call summaries

and also we can have Gen AI queries,

which is another cool feature

that you will be seeing on the video.

There is another component in here, Translate.

PCA was deployed for our US market,

but it was also deployed in Mexico.

So at some point we're foreseeing the need

to be sharing some of that information that we were getting.

Those topics, that topic hierarchy definition

that we created here perhaps can be extrapolated

for another member company.

The last component, Kendra,

and I would like to highlight Kendra

because Kendra is playing a key role on another initiative

that we are considering within our roadmap.

Kendra is the elastic search component

that will allow us to be looking for some specific keyword

that was mentioned within that customer interaction.

And we can go and search for that specific keyword,

and Kendra will be offering a rank

of all the multiple options

where that specific keyword was found.

We can go ahead, click on it,

and we can even listen to the conversation.

It is not only listening

because PII is there, it's part of TCA,

so the conversation is redacted.

So if within the conversation

a social security number is mentioned,

you will see, you will hear,

"My social security number is beep, beep, beep, beep."

Because it's redacted and obfuscated.

The information is being consumed,

I already mentioned about QuickSight

and also through the PCA console

that it is gonna be part of the demo.

So this is the the new PCA console.

We created this video relying on real data

so you will be seeing real data.

Of course it's been redacted for this presentation.

Gonna make sure that it is running.

Okay, it's running.

So the PCA console provides details, call details.

I dunno if it's running or not.

Yeah, it's running.

Including call metadata, queue name,

agent name, call duration, agent and sentiment trends.

It also provides transcribed details

and a speaker time for all the stakeholders

involving the voice interaction.

There is a new functionality that was going through

to check tone, loudness and sentiment,

which is very useful to determine

how effective the interaction was.

And now in there you will see that new cool functionality.

PCA now host a live Gen AI query on the call details page,

enabling users to ask questions in real time,

such as how could the agent have done better?

Did the agents show empathy?

And a visual summarization and identification tasks.

This is something that we released

no more than couple months ago,

and it's creating a lot of impact

and good, good feedback from our business stakeholders.

The next video, it's gonna be related

with the topic hierarchy definition.

These functionalities aim to help our business stakeholders

to detect trend topics, drill down,

and get detailed on specifics, allowing proactive actions

to improve the customer experience.

This is extremely important.

As I mentioned before,

this is something that we created in house.

We are relying on PCA data points

and also supported on Bedrock,

specifically on (inaudible) Instant.

Yeah, it's running.

So the report is built on AWS QuickSight

providing NLP functionality supported on QuickSight Queue.

The report allows to filter by a specific data ranges

and engagement center queues,

providing a specific KPIs like number of calls,

average talk time and call duration.

We have defined three levels within the hierarchy

and providing a summary for each one of them.

This has been a very detailed and refined initiative,

partnering with our business stakeholders

to include business relevant topics,

clustering the outcomes provided by Bedrock.

Finally, we created a timeline analysis

considering the number of calls per day

pointing to some specific topic.

Okay, now I'm gonna be moving to one of my favorite slides.

At Principle, as we think about understanding

the customer experience,

our goal is simple.

Ultimately we want to deliver simplified, personalized,

and anticipatory customer experience

that build a feeling of security

when customer interact with us

using their preferred channel.

In this case, either email or voice.

Extremely important because the cornerstone

for our customer experience now,

it's PCA, the voice interaction,

the richness that we may get on all that information,

and we are now combining that with email interaction.

For us it's extremely important to be dealing with the what,

what are the customers talking about?

That's gonna be the topics.

But also extremely important

to be relying on the why.

Why are the customers calling?

Why are the customer emailing us?

Right?

Topics and intents are the way

that we are using to connect different channels.

So now I already explain you that we are relying on Neptune

for this specific purpose,

but we are able to find hidden relationships

and customer experience using

or interacting through multiple channels.

So the omnichannel experience,

it's extremely important for us

and that's exactly where we are moving on.

I'm gonna be detailing some of those activities

within the roadmap that we are gonna be facing next year.

We are looking to continue our partnership with AWS

executing on a very exciting roadmap.

So for phase one, which is already in production,

we're using post call analytics

enabling PII reduction,

topic hierarchy definition and summarization.

To date, we've processed over 1 million calls

from multiple contact center queues

that has provided the insight into the customer

content of calls.

With enhanced VI capabilities,

we are relying on large language models

to gather additional customer insights.

For phase two,

I already mentioned about email interaction.

We are already processing email interaction

and we are looking to get additional integrations

with Google Analytics

because that's the platform that we are using

for a tagging strategy,

and bringing that digital interaction into this equation.

And of course we are looking to improve

our topic hierarchy definition

considering new business domains.

For phase three, this is, I would say

extremely strategic for us right now

because considering the substantial progress

that we have had with PCA

and although the different data points

that we are able to process,

we said we need to enable an intelligent agent,

basically relying on PCA data,

but eventually can be complimented

by additional knowledge bases.

So now we are working with AWS

to deploy intelligent agents supported on AWS, Q&A bot,

infused by AWS Bedrock

and of course using Kendra as a pivotal platform.

Why am I pointing to Kendra?

Because we are gonna be facing,

or we are facing a RAG approach,

it is a retrieval augmented generation

pointing to the PCA data

complemented by additional knowledge bases.

Q&A bot is providing the functionality

to create our own knowledge bases

or to point to a preexisting ones.

The user interface is gonna be a chatbot like interface,

but it is gonna be circumscribed

to customer omni-channel interaction.

So that's the challenge that we're, I would say

it is a challenge, but it is gonna be really,

really exciting roadmap

that we are gonna be facing for next year.

So Aartika.

- Awesome.

- Thank you so much.

- Thanks, Miguel.

(audience applauds)

All right.

Next steps.

If you wanna get in touch with us,

you can ask us for a discovery workshop

or starting a proof of concept.

You can work with the different contact center platform

providers that Chris showed,

with Contact Center Intelligence Solutions

or you can reach out to us

to know more about the Amazon Connect solution.

You can work with our AWS experts, the ProServe team,

our long list of CCI partners, consulting partners,

and ISVs.

Before we let you go, we do wanna leave you

with some resources which will help you understand

more about all the solutions that we just spoke about.

And if you wanna know more about AIML in contact centers,

we do have an interesting list of sessions lined up

for the rest of the week that you can attend,

workshops, chat talks, and other breakout sessions.

This was all of us.

Do remember to fill in the survey, give us your feedback,

that's always very helpful

and we'll open it up for questions.

I'm happy to come to you or you can stand up

and shout at the top of your voice

to ask all your questions.