Earlier this yr, we revealed the primary in a collection of posts about how AWS is remodeling our vendor and buyer journeys utilizing generative AI. Along with planning issues when constructing an AI software from the bottom up, it targeted on our Account Summaries use case, which permits account groups to rapidly perceive the state of a buyer account, together with latest traits in service utilization, alternative pipeline, and proposals to assist prospects maximize the worth they obtain from AWS.
In the identical spirit of utilizing generative AI to equip our gross sales groups to most successfully meet buyer wants, this submit evaluations how we’ve delivered an internally-facing conversational gross sales assistant utilizing Amazon Q Enterprise. We talk about how our gross sales groups are utilizing it as we speak, examine the advantages of Amazon Q Enterprise as a managed service to the do-it-yourself choice, evaluate the information sources obtainable and high-level technical design, and speak about a few of our future plans.
Introducing Subject Advisor
In April 2024, we launched our AI gross sales assistant, which we name Subject Advisor, making it obtainable to AWS workers within the Gross sales, Advertising and marketing, and International Providers group, powered by Amazon Q Enterprise. Since that point, 1000’s of energetic customers have requested tons of of 1000’s of questions by way of Subject Advisor, which we have now embedded in our buyer relationship administration (CRM) system, in addition to by way of a Slack software. The next screenshot reveals an instance of an interplay with Subject Advisor.
Subject Advisor serves 4 major use instances:
- AWS-specific data search – With Amazon Q Enterprise, we’ve made inside knowledge sources in addition to public AWS content material obtainable in Subject Advisor’s index. This allows gross sales groups to work together with our inside gross sales enablement collateral, together with gross sales performs and first-call decks, in addition to buyer references, customer- and field-facing incentive applications, and content material on the AWS web site, together with weblog posts and repair documentation.
- Doc add – When customers want to supply context of their very own, the chatbot helps importing a number of paperwork throughout a dialog. We’ve seen our gross sales groups use this functionality to do issues like consolidate assembly notes from a number of group members, analyze enterprise studies, and develop account methods. For instance, an account supervisor can add a doc representing their buyer’s account plan, and use the assistant to assist establish new alternatives with the client.
- Common productiveness – Amazon Q Enterprise makes a speciality of Retrieval Augmented Technology (RAG) over enterprise and domain-specific datasets, and may also carry out common data retrieval and content material technology duties. Our gross sales, advertising, and operations groups use Subject Advisor to brainstorm new concepts, in addition to generate personalised outreach that they will use with their prospects and stakeholders.
- Notifications and proposals – To enrich the conversational capabilities supplied by Amazon Q, we’ve constructed a mechanism that enables us to ship alerts, notifications, and proposals to our area group members. These push-based notifications can be found in our assistant’s Slack software, and we’re planning to make them obtainable in our net expertise as nicely. Instance notifications we ship embody field-wide alerts in help of AWS summits like AWS re:Invent, reminders to generate an account abstract when there’s an upcoming buyer assembly, AI-driven insights round customer support utilization and enterprise knowledge, and cutting-edge use instances like autonomous prospecting, which we’ll discuss extra about in an upcoming submit.
Based mostly on an inside survey, our area groups estimate that roughly a 3rd of their time is spent making ready for his or her buyer conversations, and one other 20% (or extra) is spent on administrative duties. This time provides up individually, but in addition collectively on the group and organizational degree. Utilizing our AI assistant constructed on Amazon Q, group members are saving hours of time every week. Not solely that, however our gross sales groups devise motion plans that they in any other case might need missed with out AI help.
Right here’s a sampling of what a few of our extra energetic customers needed to say about their expertise with Subject Advisor:
“I take advantage of Subject Advisor to evaluate govt briefing paperwork, summarize conferences and description actions, as nicely analyze dense data into key factors with prompts. Subject Advisor continues to allow me to work smarter, not tougher.”– Gross sales Director
“After I put together for onsite buyer conferences, I outline which advisory packages to supply to the client. We work backward from the client’s enterprise targets, so I obtain an annual report from the client web site, add it in Subject Advisor, ask about the important thing enterprise and tech targets, and get a number of worthwhile insights. I then use Subject Advisor to brainstorm concepts on easy methods to finest place AWS providers. Summarizing the enterprise targets alone saves me between 4–8 hours per buyer, and we have now round 5 buyer conferences to organize for per group member per thirty days.” – AWS Skilled Providers, EMEA
“I profit from getting notifications by way of Subject Advisor that I’d in any other case not concentrate on. My buyer’s Financial savings Plans had been expiring, and the notification helped me kick off a dialog with them on the proper time. I requested Subject Advisor to enhance the content material and message of an electronic mail I wanted to ship their govt group, and it solely took me a minute. Thanks!” – Startup Account Supervisor, North America
Amazon Q Enterprise underpins this expertise, decreasing the effort and time it takes for inside groups to have productive conversations with their prospects that drive them towards the very best outcomes on AWS.
The remainder of this submit explores how we’ve constructed our AI assistant for gross sales groups utilizing Amazon Q Enterprise, and highlights a few of our future plans.
Placing Amazon Q Enterprise into motion
We began our journey in constructing this gross sales assistant earlier than Amazon Q Enterprise was obtainable as a totally managed service. AWS supplies the primitives wanted for constructing new generative AI purposes from the bottom up: providers like Amazon Bedrock to supply entry to a number of main basis fashions, a number of managed vector database choices for semantic search, and patterns for utilizing Amazon Easy Storage Service (Amazon S3) as a knowledge lake to host data bases that can be utilized for RAG. This method works nicely for groups like ours with builders skilled in these applied sciences, in addition to for groups who want deep management over each part of the tech stack to satisfy their enterprise targets.
When Amazon Q Enterprise grew to become typically obtainable in April 2024, we rapidly noticed a possibility to simplify our structure, as a result of the service was designed to satisfy the wants of our use case—to supply a conversational assistant that would faucet into our huge (gross sales) domain-specific data bases. By shifting our core infrastructure to Amazon Q, we not wanted to decide on a big language mannequin (LLM) and optimize our use of it, handle Amazon Bedrock brokers, a vector database and semantic search implementation, or customized pipelines for knowledge ingestion and administration. In only a few weeks, we had been in a position to reduce over to Amazon Q and considerably cut back the complexity of our service structure and operations. Not solely that, we anticipated this transfer to pay dividends—and it has—because the Amazon Q Enterprise service group has continued so as to add new options (like automated personalization) and improve efficiency and end result accuracy.
The next diagram illustrates Subject Advisor’s high-level structure:
Answer overview
We constructed Subject Advisor utilizing the built-in capabilities of Amazon Q Enterprise. This consists of how we configured knowledge sources that comprise our data base, indexing paperwork and relevancy tuning, safety (authentication, authorization, and guardrails), and Amazon Q’s APIs for dialog administration and customized plugins. We ship our chatbot expertise by way of a customized net frontend, in addition to by way of a Slack software.
Knowledge administration
As talked about earlier on this submit, our preliminary data base is comprised of all of our inside gross sales enablement supplies, in addition to publicly obtainable content material together with the AWS web site, weblog posts, and repair documentation. Amazon Q Enterprise supplies a variety of out-of-the-box connectors to in style knowledge sources like relational databases, content material administration methods, and collaboration instruments. In our case, the place we have now a number of purposes constructed in-house, in addition to third-party software program backed by Amazon S3, we make heavy use of Amazon Q connector for Amazon S3, and in addition to customized connectors we’ve written. Utilizing the service’s built-in supply connectors standardizes and simplifies the work wanted to take care of knowledge high quality and handle the general knowledge lifecycle. Amazon Q offers us a templatized approach to filter supply paperwork when producing responses on a specific matter, making it easy for the applying to provide a better high quality response. Not solely that, however every time Amazon Q supplies a solution utilizing the data base we’ve related, it robotically cites sources, enabling our sellers to confirm authenticity within the data. Beforehand, we needed to construct and preserve customized logic to deal with these duties.
Safety
Amazon Q Enterprise supplies capabilities for authentication, authorization, and entry management out of the field. For authentication, we use AWS IAM Id Heart for enterprise single sign-on (SSO), utilizing our inside id supplier known as Amazon Federate. After going by way of a one-time setup for id administration that governs entry to our gross sales assistant software, Amazon Q is conscious of the customers and roles throughout our gross sales groups, making it easy for our customers to entry Subject Advisor throughout a number of supply channels, like the net expertise embedded in our CRM, in addition to the Slack software.
Additionally, with our multi-tenant AI software serving 1000’s of customers throughout a number of gross sales groups, it’s crucial that end-users are solely interacting with knowledge and insights that they need to be seeing. Like all massive group, we have now data firewalls between groups that assist us correctly safeguard buyer data and cling to privateness and compliance guidelines. Amazon Q Enterprise supplies the mechanisms for shielding every particular person doc in its data base, simplifying the work required to verify we’re respecting permissions on the underlying content material that’s accessible to a generative AI software. This fashion, when a person asks a query of the software, the reply will probably be generated utilizing solely data that the person is permitted to entry.
Internet expertise
As famous earlier, we constructed a customized net frontend somewhat than utilizing the Amazon Q built-in net expertise. The Amazon Q expertise works nice, with options like dialog historical past, pattern fast prompts, and Amazon Q Apps. Amazon Q Enterprise makes these options obtainable by way of the service API, permitting for a custom-made appear and feel on the frontend. We selected this path to have a extra fluid integration with our different field-facing instruments, management over branding, and sales-specific contextual hints that we’ve constructed into the expertise. For example, we’re planning to make use of Amazon Q Apps as the muse for an built-in immediate library that’s personalised for every person and field-facing position.
A have a look at what’s to return
Subject Advisor has seen early success, but it surely’s nonetheless just the start, or Day 1 as we prefer to say right here at Amazon. We’re persevering with to work on bringing our field-facing groups and area help features extra generative AI throughout the board. With Amazon Q Enterprise, we not must handle every of the infrastructure elements required to ship a safe, scalable conversational assistant—as a substitute, we are able to give attention to the information, insights, and expertise that profit our salesforce and assist them make our prospects profitable on AWS. As Amazon Q Enterprise provides options, capabilities, and enhancements (which we regularly have the privilege of having the ability to take a look at in early entry) we robotically reap the advantages.
The group that constructed this gross sales assistant has been targeted on growing—and will probably be launching quickly—deeper integration with our CRM. It will allow groups throughout all roles to ask detailed questions on their buyer and associate accounts, territories, leads and contacts, and gross sales pipeline. With an Amazon Q customized plugin that makes use of an inside library used for pure language to SQL (NL2SQL), the identical that powers generative SQL capabilities throughout some AWS database providers like Amazon Redshift, we’ll present the power to combination and slice-and-dice the chance pipeline and traits in product consumption conversationally. Lastly, a typical request we get is to make use of the assistant to generate extra hyper-personalized customer-facing collateral—consider a first-call deck about AWS merchandise and options that’s particular to a person buyer, localized of their language, that pulls from the most recent obtainable service choices, aggressive intelligence, and the client’s present utilization within the AWS Cloud.
Conclusion
On this submit, we reviewed how we’ve made a generative AI assistant obtainable to AWS gross sales groups, powered by Amazon Q Enterprise. As new capabilities land and utilization continues to develop, we’re excited to see how our area groups use this, together with different AI options, to assist prospects maximize their worth on the AWS Cloud.
The subsequent submit on this collection will dive deeper into one other latest generative AI use case and the way we utilized this to autonomous gross sales prospecting. Keep tuned for extra, and attain out to us with any questions on how one can drive development with AI at what you are promoting.
In regards to the authors
Joe Travaglini is a Principal Product Supervisor on the AWS Subject Experiences (AFX) group who focuses on serving to the AWS salesforce ship worth to AWS prospects by way of generative AI. Previous to AFX, Joe led the product administration perform for Amazon Elastic File System, Amazon ElastiCache, and Amazon MemoryDB.
Jonathan Garcia is a Sr. Software program Improvement Supervisor primarily based in Seattle with over a decade of expertise at AWS. He has labored on quite a lot of merchandise, together with knowledge visualization instruments and cell purposes. He’s enthusiastic about serverless applied sciences, cell growth, leveraging Generative AI, and architecting modern high-impact options. Exterior of labor, he enjoys {golfing}, biking, and exploring the outside.
Umesh Mohan is a Software program Engineering Supervisor at AWS, the place he has been main a group of proficient engineers for over three years. With greater than 15 years of expertise in constructing knowledge warehousing merchandise and software program purposes, he’s now specializing in using generative AI to drive smarter and extra impactful options. Exterior of labor, he enjoys spending time together with his household and taking part in tennis.
