How Amazon Bedrock powers next-generation account planning at AWS

At AWS, our gross sales groups create customer-focused paperwork referred to as account plans to deeply perceive every AWS buyer’s distinctive targets and challenges, serving to account groups present tailor-made steerage and assist that accelerates buyer success on AWS. As our enterprise has expanded, the account planning course of has develop into extra intricate, requiring detailed evaluation, evaluations, and cross-team alignment to ship significant worth to prospects. This complexity, mixed with the guide evaluation effort concerned, has led to important operational overhead. To deal with this problem, we launched Account Plan Pulse in January 2025, a generative AI software designed to streamline and improve the account planning course of. Implementing Pulse delivered a 37% enchancment in plan high quality year-over-year, whereas lowering the general time to finish, evaluation, and approve plans by 52%.

On this put up, we share how we constructed Pulse utilizing Amazon Bedrock to scale back evaluation 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), companies to deploy and function brokers, and instruments for fine-tuning, safeguarding, and optimizing fashions, together with information bases to attach purposes to your newest knowledge so that you’ve every part you could shortly transfer from experimentation to real-world deployment.

Challenges with rising scale and complexity

As AWS continued to develop and evolve, our account planning processes wanted to adapt to fulfill rising scale and complexity. Earlier than enterprise-ready giant language fashions (LLMs) grew to become obtainable by way of Amazon Bedrock, we explored rule-based doc processing to guage account plans, which proved insufficient for dealing with nuanced content material and rising doc volumes. By 2024, three important 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 important 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 evaluation course of – The standard evaluation course of relied on guide evaluations by gross sales management. Although thorough, these evaluations consumed priceless time that would in any other case be dedicated to strategic buyer engagements. As our enterprise scaled, this strategy created bottlenecks in plan approval and implementation.
• Information silos – We recognized untapped potential for cross-team collaboration. Creating strategies to extract and share information would remodel particular person account plans into collective greatest practices to raised serve our prospects.

Answer 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:

1. Account plan narrative content material is pulled from our CRM system on a scheduled foundation by way of an asynchronous batch processing pipeline.
2. The info flows by way of a collection of processing levels:
   1. Preprocessing to construction and normalize the information and generate metadata.
   2. LLM inference to investigate content material and generate insights.
   3. Validation to verify high quality and compliance.
3. Outcomes are saved securely for reporting and dashboard visualization.

We’ve built-in Pulse instantly with current gross sales workflows to maximise consumer 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 parts of the answer in additional element.

Ingestion

We implement a batch processing pipeline that extracts account plans from our CRM system into Amazon Simple Storage Service (Amazon S3) buckets. A scheduler triggers this pipeline on an everyday cadence, facilitating steady evaluation of probably the most present info.

Preprocessing

Contemplating the dynamic nature of account plans, they’re processed in each day snapshots, with solely up to date plans included in every run. Preprocessing is carried out at two layers: an extract, remodel, and cargo (ETL) circulate layer to arrange required information to be processed, and simply earlier than mannequin calls as a part of enter validation. This strategy, 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 each day scheduled job that reads account plan knowledge saved as Parquet information 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 not too long ago modified plans, considerably decreasing computational overhead and prices. The processed textual content content material and metadata are then reworked right into a standardized format and saved again to Amazon S3 as Parquet information, making a clear dataset prepared for LLM evaluation.

Evaluation with Amazon Bedrock

The core of our answer makes use of Amazon Bedrock, which offers a wide range of mannequin selections and management, knowledge customization, security and guardrails, price optimization, and orchestration. We use the Amazon Bedrock FMs to carry out two key capabilities:

• Account plan analysis – Pulse evaluates plans in opposition to 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 developments that may in any other case stay remoted in particular person paperwork.

We implement these capabilities by way of asynchronous batch processing, the place analysis and summarization workloads function independently. The analysis course of runs every account by way of 27 particular questions with tailor-made management prompts, and the summarization course of generates topical overviews for simple consumption and information sharing.

For this implementation, we use structured output prompting with schema constraints to supply constant formatting that integrates with our reporting instruments.

Validation

Our validation framework contains the next parts:

• Enter and output validations are important as a part of the OWASP Top 10 for Large Language Model Applications. The enter validation is crucial by the introduction of vital 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 in opposition to established enterprise guidelines.
• Extra evaluation 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 parts:

• Amazon S3 offers safe storage for all processed account plans and insights.
• A each day run cadence refreshes perception and allows progress monitoring.
• Interactive dashboards provide each govt summaries and detailed plan views.

Engineering for manufacturing: Constructing dependable AI evaluations

When transitioning Pulse from prototype to manufacturing, we carried out a strong engineering framework to handle three important AI-specific challenges. First, the non-deterministic nature of LLMs meant equivalent inputs may 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 facets 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 handle the information dispersion, which we achieved by calculating the general CoV on the evaluated query degree. With this strategy, we will 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 routinely within the system, and people outdoors established thresholds are flagged for guide evaluation. 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 influence. 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 bear periodic evaluation with gross sales management and adjustment primarily based on suggestions, so our AI evaluations stay related whereas sustaining high quality and saving priceless time.

Conclusion

On this put up, we shared how Pulse, powered by Amazon Bedrock, has reworked 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 information 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.

Trying forward, we’re excited to boost 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 intention to determine and act on new alternatives, creating deeper insights into how strategic planning drives buyer success on AWS.

We intention 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 Agents and Amazon Bedrock AgentCore, we will make a extra dynamic circulate sooner or later.

To be taught extra about Amazon Bedrock, confer with the Amazon Bedrock User Guide, Amazon Bedrock Workshop: AWS Code Samples, AWS Workshops, and Using generative AI on AWS for diverse content types. For the newest information on AWS, see What’s New with AWS?

Concerning the authors

Karnika Sharma is a Senior Product Supervisor within the AWS Gross sales, Advertising and marketing, and World Providers (SMGS) org, the place she works on empowering the worldwide gross sales group to speed up buyer development with AWS. She’s keen about bridging machine studying and AI innovation with real-world influence, 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 Providers (SMGS) Group. He helps each AWS inside groups and exterior prospects reap the benefits of the facility 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 concentrate on delivering measurable enterprise impacts. He has MSc. (Tech) in Communication Engineering. Dayo is keen about advancing generative AI/ML applied sciences to drive real-world influence.

Mihir Gadgil is a Senior Knowledge Engineer within the AWS Gross sales, Advertising and marketing, and World Providers (SMGS) org, specializing in enterprise-scale knowledge options and generative AI purposes. With 9+ years of expertise and a Grasp’s in Data Expertise & Administration, he focuses on constructing strong knowledge pipelines, advanced knowledge modeling, and ETL/ELT processes. His experience drives enterprise transformation by way of modern knowledge engineering options, superior analytics capabilities.

Carlos Chinchilla is a Options Architect at Amazon Internet Providers (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 companies. His work contains growing AI assistants, machine studying pipelines, and serving to organizations use cloud applied sciences for innovation.

Sofian Hamiti is a expertise 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 influence and obtain their profession aspirations.

Sujit Narapareddy, Head of Knowledge & Analytics at AWS World Gross sales, is a expertise chief driving world enterprise transformation. He leads knowledge product and platform groups that energy AWS’s Go-to-Market by way of AI-augmented analytics and clever automation. With a confirmed observe report in enterprise options, he has reworked gross sales productiveness, knowledge governance, and operational excellence. Beforehand at JPMorgan Chase Enterprise Banking, he formed next-generation FinTech capabilities by way of knowledge innovation.