Use Case Intelligence RSS Search use cases Search
IBM Financial Services North America

Bay Point Advisors

Enterprise Knowledge Search

Bay Point Advisors needed to speed private-market due diligence across secure data rooms full of documents without compromising answer quality, citation grounding, or document-level security controls.

Read the original story Explore all use cases
Hours to minutes
Minutes to seconds
delivered in milliseconds

Reported impact

Business outcome

Bay Point Advisors reduced document-review time, improved responsiveness for clients, and created a secure self-service research experience that supports faster, higher-confidence private-market decisions.

  • Customer Experience
  • Productivity Improvement
  • Risk Reduction

Solution

Bay Point Advisors built Atlas, a conversational due-diligence platform that combines IBM DataStax Astra DB within IBM watsonx.data, Azure Blob Storage, Azure OpenAI, and a SQL metadata layer. Documents stored in secure data rooms are transformed into a retrieval-augmented-generation architecture where Astra DB acts as the vector-backed knowledge layer and Azure Blob Storage holds the underlying files. When advisors or clients ask questions, Atlas retrieves grounded evidence, applies the language model, and returns citation-backed answers in milliseconds instead of forcing users to manually read hundreds of PDFs, spreadsheets, and contracts. IBM's Astra DB team helped Bay Point tune retrieval workflows, parameters, and security, while document-level permissions remain enforced end to end. The result is a secure, self-service interface for private-market research that blends structured and unstructured data for faster investment decisions and more personalized client guidance.

Data flow

PDFs, spreadsheets, and contracts from secure data rooms are stored in Azure Blob Storage, indexed into Astra DB within watsonx.data, retrieved through Atlas's RAG pipeline, and passed to Azure OpenAI so advisors and clients receive citation-backed answers with document-level permissions enforced.

Solution architecture

4 components · 2 layers
  1. Compute
    • Azure OpenAI Generates conversational answers from the retrieved data-room context.
  2. Storage
    • IBM DataStax Astra DB Provides the secure vector-backed database that powers retrieval over private-market data-room content.
    • IBM watsonx.data Supplies the broader data platform that houses Astra DB and supports the RAG knowledge layer.
    • Azure Blob Storage Stores the original documents that Atlas turns into a searchable due-diligence corpus.

Architecture clues

  • Bay Point plans to add agentic AI capabilities for proactive intelligence.
  • Document-level permissions are enforced end to end.
  • The platform uses retrieval-augmented generation across structured and unstructured data.

Evidence from the source

Atlas delivers a secure, personalized experience for every client.
Leveraging IBM DataStax Astra DB within IBM watsonx.data, Azure Blob Storage, Azure OpenAI, and a SQL metadata layer, Atlas uses a Retrieval-Augmented Generation (RAG) architecture
document-level permissions enforced end-to-end, protecting sensitive data.
instant, citation-backed answers delivered in milliseconds
reduced document review and research time from hours to seconds
Transparency Evidence & methodology 75/100 reference value · 87% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value75/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. IBM

    Bay Point Advisors customer story

    First-party
    https://www.ibm.com/case-studies/bay-point
    Source type
    Vendor-published customer story
    Published
    Jan 28, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
IBM Jan 6, 2025 IRCEM Group Financial Services France IRCEM needed to answer growing volumes of customer questions about complex pension, insurance, and social-protection topics without forcing advisors to handle every inquiry manually by email or phone. 4,000 conversations per month Customer Service AutomationEnterprise Knowledge Search IBM Cloud Expert Labs · IBM watsonx Assistant IBM May 14, 2024 Sicredi Financial Services Brazil Sicredi's support representatives had to answer questions across many financial products, and the previous assistant often required escalation to product specialists, which lengthened wait times for members and made… 1% improvement in net promoter score Customer Service AutomationEnterprise Knowledge Search IBM Watson Discovery · IBM watsonx Assistant · IBM watsonx.ai IBM Apr 22, 2024 Edger Finance Financial Services Sweden Edger Finance wanted to help investors collect, summarize and interrogate quarterly-report data much faster so users could make better investment decisions without waiting on manual analyst work. 90% improvement in the turnaround time for quarterly report data extracts Document ProcessingEnterprise Knowledge Search IBM watsonx Assistant · IBM watsonx.ai