At AWS, our gross sales groups create customer-focused paperwork known as account plans to deeply perceive every AWS buyer’s distinctive targets and challenges, serving to account groups present tailor-made steerage and help that accelerates buyer success on AWS. As our enterprise has expanded, the account planning course of has grow to be extra intricate, requiring detailed evaluation, evaluations, and cross-team alignment to ship significant worth to prospects. This complexity, mixed with the guide assessment effort concerned, has led to important operational overhead. To deal with this problem, we launched Account Plan Pulse in January 2025, a generative AI device designed to streamline and improve the account planning course of. Implementing Pulse delivered a 37% enchancment in plan high quality year-over-year, whereas reducing the general time to finish, assessment, and approve plans by 52%.
On this publish, we share how we constructed Pulse utilizing Amazon Bedrock to scale back assessment time and supply actionable account plan summaries for ease of collaboration and consumption, serving to AWS gross sales groups higher serve our prospects. Amazon Bedrock is a complete, safe, and versatile service for constructing generative AI purposes and brokers. It connects you to main basis fashions (FMs), providers to deploy and function brokers, and instruments for fine-tuning, safeguarding, and optimizing fashions, together with data bases to attach purposes to your newest knowledge so that you’ve got all the things it’s essential rapidly transfer from experimentation to real-world deployment.
Challenges with growing scale and complexity
As AWS continued to develop and evolve, our account planning processes wanted to adapt to fulfill growing scale and complexity. Earlier than enterprise-ready massive language fashions (LLMs) grew to become out there via Amazon Bedrock, we explored rule-based doc processing to judge account plans, which proved insufficient for dealing with nuanced content material and rising doc volumes. By 2024, three vital challenges had emerged:
- Disparate plan high quality and format – With groups working throughout quite a few AWS Areas and serving prospects in various industries, account plans naturally developed variations in construction, element, and format. This inconsistency made it tough to ensure vital buyer wants had been described successfully and constantly. Moreover, the analysis of account plan high quality was inherently subjective, relying closely on human judgment to evaluate every plan’s depth, strategic alignment, and buyer focus.
- Useful resource-intensive assessment course of – The standard evaluation course of relied on guide evaluations by gross sales management. Although thorough, these evaluations consumed precious time that might in any other case be dedicated to strategic buyer engagements. As our enterprise scaled, this method created bottlenecks in plan approval and implementation.
- Information silos – We recognized untapped potential for cross-team collaboration. Growing strategies to extract and share data would rework particular person account plans into collective finest practices to higher serve our prospects.
Resolution overview
To deal with these challenges, we designed Pulse, a generative AI answer that makes use of Amazon Bedrock to investigate and enhance account plans. The next diagram illustrates the answer workflow.
The workflow consists of the next steps:
- Account plan narrative content material is pulled from our CRM system on a scheduled foundation via an asynchronous batch processing pipeline.
- The info flows via a sequence of processing levels:
- Preprocessing to construction and normalize the info and generate metadata.
- LLM inference to investigate content material and generate insights.
- Validation to substantiate high quality and compliance.
- Outcomes are saved securely for reporting and dashboard visualization.
We’ve built-in Pulse straight with present gross sales workflows to maximise person adoption and have established suggestions loops that repeatedly refine efficiency. The next diagram reveals the answer structure.
Within the following sections, we discover the important thing elements of the answer in additional element.
Ingestion
We implement a batch processing pipeline that extracts account plans from our CRM system into Amazon Easy Storage Service (Amazon S3) buckets. A scheduler triggers this pipeline on a daily cadence, facilitating steady evaluation of probably the most present info.
Preprocessing
Contemplating the dynamic nature of account plans, they’re processed in every day snapshots, with solely up to date plans included in every run. Preprocessing is performed at two layers: an extract, rework, and cargo (ETL) circulate layer to arrange required recordsdata to be processed, and simply earlier than mannequin calls as a part of enter validation. This method, utilizing the plan’s final modified date, is essential for avoiding a number of runs on the identical content material. The preprocessing pipeline handles the every day scheduled job that reads account plan knowledge saved as Parquet recordsdata in Amazon S3, extracts textual content content material from HTML fields, and generates structured metadata for every doc. To optimize processing effectivity, the system compares doc timestamps to course of solely just lately modified plans, considerably lowering computational overhead and prices. The processed textual content content material and metadata are then remodeled right into a standardized format and saved again to Amazon S3 as Parquet recordsdata, making a clear dataset prepared for LLM evaluation.
Evaluation with Amazon Bedrock
The core of our answer makes use of Amazon Bedrock, which gives a wide range of mannequin decisions and management, knowledge customization, security and guardrails, price optimization, and orchestration. We use the Amazon Bedrock FMs to carry out two key features:
- Account plan analysis – Pulse evaluates plans towards 10 business-critical classes, making a standardized Account Plan Readiness Index. This automated analysis identifies enchancment areas with particular enchancment suggestions.
- Actionable insights – Amazon Bedrock extracts and synthesizes patterns throughout plans, figuring out buyer strategic focus and market traits that may in any other case stay remoted in particular person paperwork.
We implement these capabilities via asynchronous batch processing, the place analysis and summarization workloads function independently. The analysis course of runs every account via 27 particular questions with tailor-made management prompts, and the summarization course of generates topical overviews for simple consumption and data sharing.
For this implementation, we use structured output prompting with schema constraints to offer constant formatting that integrates with our reporting instruments.
Validation
Our validation framework contains the next elements:
- Enter and output validations are vital as a part of the OWASP Prime 10 for Giant Language Mannequin Functions. The enter validation is crucial by the introduction of crucial guardrails and immediate validation, and the output validation makes positive the outcomes are structured and constrained to anticipated responses.
- Automated high quality and compliance checks towards established enterprise guidelines.
- Extra assessment for outputs that don’t meet high quality thresholds.
- A suggestions mechanism that improves system accuracy over time.
Storage and visualization
The answer contains the next storage and visualization elements:
- Amazon S3 gives safe storage for all processed account plans and insights.
- A every day run cadence refreshes perception and allows progress monitoring.
- Interactive dashboards provide each government summaries and detailed plan views.
Engineering for manufacturing: Constructing dependable AI evaluations
When transitioning Pulse from prototype to manufacturing, we carried out a sturdy engineering framework to deal with three vital AI-specific challenges. First, the non-deterministic nature of LLMs meant an identical inputs might produce various outputs, probably compromising analysis consistency. Second, account plans naturally evolve all year long with buyer relationships, making static analysis strategies inadequate. Third, totally different AWS groups prioritize totally different features of account plans primarily based on particular buyer {industry} and enterprise wants, requiring versatile analysis standards. To keep up analysis reliability, we developed a statistical framework utilizing Coefficient of Variation (CoV) evaluation throughout a number of mannequin runs on account plan inputs. The purpose is to make use of the CoV as a correction issue to deal with the info dispersion, which we achieved by calculating the general CoV on the evaluated query degree. With this method, we are able to scientifically measure and stabilize output variability, set up clear thresholds for selective guide evaluations, and detect efficiency shifts requiring recalibration. Account plans falling inside confidence thresholds proceed mechanically within the system, and people outdoors established thresholds are flagged for guide assessment. We complemented this with a dynamic threshold weighting system that aligns evaluations with organizational priorities by assigning totally different weights to standards primarily based on enterprise affect. This customizes thresholds throughout totally different account sorts—for instance, making use of totally different analysis parameters to enterprise accounts versus mid-market accounts. These enterprise thresholds endure periodic assessment with gross sales management and adjustment primarily based on suggestions, so our AI evaluations stay related whereas sustaining high quality and saving precious time.
Conclusion
On this publish, we shared how Pulse, powered by Amazon Bedrock, has remodeled the account planning course of for AWS gross sales groups. By way of automated evaluations and structured validation, Pulse streamlines high quality assessments and breaks down data silos by surfacing actionable buyer intelligence throughout our world group. This helps our gross sales groups spend much less time on evaluations and extra time making data-driven choices for strategic buyer engagements.
Wanting forward, we’re excited to reinforce Pulse’s capabilities to measure account plan execution by connecting strategic planning with gross sales actions and buyer outcomes. By analyzing account plan narratives, we goal to establish and act on new alternatives, creating deeper insights into how strategic planning drives buyer success on AWS.
We goal to proceed to make use of the brand new capabilities of Amazon Bedrock for enhanced and strong enhancements to our processes. By constructing flows for orchestrating our workflows, use of Amazon Bedrock Guardrails, introduction of agentic frameworks, and use of Strands Brokers and Amazon Bedrock AgentCore, we are able to make a extra dynamic circulate sooner or later.
To be taught extra about Amazon Bedrock, check with the Amazon Bedrock Person Information, Amazon Bedrock Workshop: AWS Code Samples, AWS Workshops, and Utilizing generative AI on AWS for various content material sorts. For the newest information on AWS, see What’s New with AWS?
In regards to the authors
Karnika Sharma is a Senior Product Supervisor within the AWS Gross sales, Advertising and marketing, and World Companies (SMGS) org, the place she works on empowering the worldwide gross sales group to speed up buyer development with AWS. She’s obsessed with bridging machine studying and AI innovation with real-world affect, constructing options that serve each enterprise targets and broader societal wants. Exterior of labor, she finds pleasure in plein air sketching, biking, board video games, and touring.
Dayo Oguntoyinbo is a Sr. Knowledge Scientist with the AWS Gross sales, Advertising and marketing, and World Companies (SMGS) Group. He helps each AWS inside groups and exterior prospects benefit from the ability of AI/ML applied sciences and options. Dayo brings over 12 years of cross-industry expertise. He makes a speciality of reproducible and full-lifecycle AI/ML, together with generative AI options, with a give attention to delivering measurable enterprise impacts. He has MSc. (Tech) in Communication Engineering. Dayo is obsessed with advancing generative AI/ML applied sciences to drive real-world affect.
Mihir Gadgil is a Senior Knowledge Engineer within the AWS Gross sales, Advertising and marketing, and World Companies (SMGS) org, specializing in enterprise-scale knowledge options and generative AI purposes. With 9+ years of expertise and a Grasp’s in Data Know-how & Administration, he focuses on constructing strong knowledge pipelines, advanced knowledge modeling, and ETL/ELT processes. His experience drives enterprise transformation via progressive knowledge engineering options, superior analytics capabilities.
Carlos Chinchilla is a Options Architect at Amazon Net Companies (AWS), the place he works with prospects throughout EMEA to implement AI and machine studying options. With a background in telecommunications engineering from the Technical College of Madrid, he focuses on constructing AI-powered purposes utilizing each open supply frameworks and AWS providers. His work contains growing AI assistants, machine studying pipelines, and serving to organizations use cloud applied sciences for innovation.
Sofian Hamiti is a know-how chief with over 10 years of expertise constructing AI options, and main high-performing groups to maximise buyer outcomes. He’s passionate in empowering various expertise to drive world affect and obtain their profession aspirations.
Sujit Narapareddy, Head of Knowledge & Analytics at AWS World Gross sales, is a know-how chief driving world enterprise transformation. He leads knowledge product and platform groups that energy AWS’s Go-to-Market via AI-augmented analytics and clever automation. With a confirmed monitor document in enterprise options, he has remodeled gross sales productiveness, knowledge governance, and operational excellence. Beforehand at JPMorgan Chase Enterprise Banking, he formed next-generation FinTech capabilities via knowledge innovation.
