Use Case Intelligence RSS Search use cases Search
Snowflake Financial Services New York, London, Montreal, Hong Kong, Singapore, Paris

TS Imagine

Document Processing

turn unstructured financial-data emails and reference content into usable structured workflows while reducing the cost and operational burden of enterprise gen AI adoption.

Read the original story Explore all use cases
30% cost reduction by using Snowflake Cortex AI vs. other top external pretrained LLM APIs
4,000 hours per year saved
Every week, we grow by almost one billion rows

Reported impact

Business outcome

TS Imagine cut gen AI costs by 30%, saved 4,000 employee hours a year on email monitoring, and deployed production AI workflows in under a week once it moved them to Cortex AI.

  • Compliance
  • Cost Reduction
  • Productivity Improvement

Solution

TS Imagine uses Snowflake, Cortex AI, Streamlit in Snowflake, and Secure Data Sharing on Snowflake to turn unstructured financial-data emails and reference content into usable structured workflows while reducing the cost and operational burden of enterprise gen ai adoption. Market data, client-facing financial content, and unstructured operational emails are consolidated in Snowflake so TS Imagine can apply gen AI without moving sensitive data outside the platform. Cortex AI powers the RAG-based email workflow and other gen AI use cases, while Streamlit in Snowflake makes conversational access and internal AI applications easier to operationalize quickly. Operations and data teams use the outputs to categorize emails, create JIRA tasks, answer business questions through chatbot experiences, and share governed data products with clients more easily. Keeping ingestion, storage, transformation, and governed access on one platform reduces copying, simplifies administration, and makes...

Data flow

financial reference data and operational emails flow into Snowflake, Cortex AI, Streamlit in Snowflake, and Secure Data Sharing; curated data, reports, and model outputs are then served to operations teams, internal business users, and client-sharing workflows.

Solution architecture

4 components · 3 layers
  1. Compute
    • Cortex AI Provides in-platform AI functions used for summarization, classification, generation, or model-assisted analysis.
  2. Storage
    • Snowflake Provides the centralized data platform that stores governed datasets and serves analytics or AI workloads.
  3. Serving
    • Streamlit in Snowflake Delivers interactive applications and agent interfaces on top of Snowflake data.
    • Secure Data Sharing Shares governed data with partners or internal consumers without moving copies.

Architecture clues

  • Runs enterprise gen AI inside a secure, controlled Snowflake environment.
  • Uses a RAG-based workflow on Snowflake to categorize incoming emails and create JIRA tickets.
  • Uses a private Snowflake Marketplace listing and secure sharing for client collaboration.

Evidence from the source

30% cost reduction by using Snowflake Cortex AI
4,000 hours per year saved
Doing everything exclusively in Snowflake was game-changing
the AI deletes duplicate or non-relevant emails, and creates, assigns, prioritizes and schedules JIRA tickets
Transparency Evidence & methodology 100/100 reference value · 79% 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 value100/100
  • 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 impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence79%
  • 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
    4 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    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. Snowflake

    TS Imagine customer story

    First-party
    https://www.snowflake.com/en/customers/all-customers/case-study/ts-imagine/
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • First archived Sep 24, 2024 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Jul 9, 2026 · Snowflake · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
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
Snowflake Archived · Jun 8, 2026 Emirates Insurance Financial Services Abu Dhabi, United Arab Emirates Legacy on-premises systems required heavy manual work, limited visibility into broker and customer behavior, and could not support the automation Emirates Insurance needed for profitable growth. 30-40% Faster motor claims registration with AI Document ProcessingRisk Management Dagster · Qlik · Snowflake OpenAI Oct 16, 2026 Benefit Street Partners Financial Services North America Benefit Street Partners needed to answer investment-committee follow-up questions faster, compare lender marks across shared loans, and review 300-page credit agreements for clauses that could shift value away from… 10–12 hours total. Document ProcessingRisk Management BDC mark tracker · Codex · Credit agreement analyzer OpenAI Oct 16, 2026 Itaú Financial Services Latin America Itaú needed to make financial guidance simpler and more personalized for millions of customers while also scaling document-heavy internal workflows, all under the governance, observability, and economic controls… 100% of the customer base is the goal by the end of 2026 Customer Service AutomationDocument Processing Customer DNA · IARA · OpenAI models