Sales ops · Production

How AWS Sales uses generative AI to streamline account planning

The problem

AWS account managers spent up to 40 hours per customer drafting account plans, creating significant organizational overhead when combined with similar time spent by support roles, and the process required hours of research across the internet and disparate internal tools.

Workflow diagram · grounded in source

User initiates in CRM

trigger

“When a user of the AWS internal CRM system initiates the workflow in Field Advisor, it triggers the account plan draft assistant capability through a pre-signed URL”

Multi-source data collection

integration

“orchestrates a multi-source data collection process, performing web searches while also pulling account metadata from OpenSearch, Amazon DynamoDB, and Amazon Simple Storage Service (Amazon S3) storage”

Bedrock AP draft generation

ai_action

“After analyzing and combining this data with user-uploaded documents, the assistant uses Amazon Bedrock to generate the AP”

Quality assurance check

validation

“Built-in quality assurance capabilities help ensure that APs meet internal standards for comprehensiveness, accuracy, and strategic alignment with our customers and business”

AM review and customization

human_review

“the product allows AMs to customize and refine the content by uploading proprietary documents to match their unique customer knowledge and strategic approach”

Notification and record storage

output

“a notification chain using Amazon Simple Queue Service (Amazon SQS) and our internal notifications service API gateway begins delivering updates using Slack direct messaging and storing searchable records in OpenSearch for future reference”

Reported outcome

Since launch in October 2024, thousands of AWS sales teams have used the assistant saving time on each account plan created, with one enterprise account manager reporting at least 15 hours saved on a single plan, and AMs shifting focus to higher-value customer engagement activities.

Reported metrics

AP drafting time per customer (before)up to 40 hours per customer

Hours saved per enterprise account planat least 15 hours

Sales team adoptionthousands of sales teams

AP creation timesaving time on each AP created

Show all 5 reported metrics

AP drafting time per customer (before)up to 40 hours per customer

hours saved per enterprise account planat least 15 hours

sales team adoptionthousands of sales teams

AP creation timesaving time on each AP created

organizational overhead (before)significant organization overhead

Reported stack

Amazon BedrockField AdvisorAmazon QAWS LambdaAmazon DynamoDBAmazon S3Amazon SQSAWS GlueOpenSearchAWS IAM Identity CenterReactJSSlack

Source

https://aws.amazon.com/blogs/machine-learning/how-aws-sales-uses-generative-ai-to-streamline-account-planning?tag=soumet-20

Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Since launch in October 2024, thousands of AWS sales teams have used the assistant saving time on each account plan created, with one enterprise account manager reporting at least 15 hours saved on a single plan, and…

What tools did this team use?

Amazon Bedrock, Field Advisor, Amazon Q, AWS Lambda, Amazon DynamoDB, Amazon S3, Amazon SQS, AWS Glue, OpenSearch, AWS IAM Identity Center.

What results were reported?

AP drafting time per customer (before): up to 40 hours per customer; Hours saved per enterprise account plan: at least 15 hours; Sales team adoption: thousands of sales teams; AP creation time: saving time on each AP created (source-reported, not independently verified).

How is this sales ops AI workflow structured?

User initiates in CRM → Multi-source data collection → Bedrock AP draft generation → Quality assurance check → AM review and customization → Notification and record storage.