Use Case Intelligence RSS Search use cases Search
IBM Financial Services Sweden

Edger Finance

Document Processing · Enterprise Knowledge Search

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.

Read the original story Explore all use cases
90% improvement in the turnaround time for quarterly report data extracts
Approximately 96% improvement in the time it takes to summarize the main points of a 30+ page report
a matter of seconds
just four hours

Reported impact

Business outcome

Edger sharply reduced turnaround time for report processing, improved platform relevance and personalization for investors, and proved its product could create value for both retail investors and enterprises using financial-report data.

  • Customer Experience
  • Productivity Improvement
  • Speed to Market

Solution

Working with IBM Client Engineering and IBM Innovation Studio through the IBM Fintechx program, Edger Finance piloted three AI-assisted workflows on top of IBM watsonx.ai and IBM watsonx Assistant. The first produces CEO-style summaries from quarterly reports, the second extracts structured data points from each filing, and the third lets investors ask questions about a report through a chat interface. Watsonx.ai provides the secure model-development and process-automation layer for all three assistants, while watsonx Assistant powers the conversational experience for the Q&A flow. The pilot focused on Swedish- and English-language report processing and proved that generative AI could fit directly into Edger's investment-research platform rather than acting as a side experiment. That architecture turns long-form corporate disclosures into searchable, summarized and queryable assets so investors can move from raw filings to relevant decision support much more quickly.

Data flow

Quarterly reports are ingested into watsonx.ai for summarization and data extraction, then the resulting report data is exposed through watsonx Assistant so investors can ask questions and retrieve the information most relevant to their strategy.

Solution architecture

2 components · 2 layers
  1. Compute
    • IBM watsonx.ai Runs the report summarization, data-extraction and investment-analysis workflows in Edger's platform.
  2. Serving
    • IBM watsonx Assistant Enables investors to interact with report data through a question-answer chat flow.

Architecture clues

  • One assistant summarizes reports, one extracts data points and one exposes a Q&A interface.
  • The MVP pilot ran for four weeks and covered Swedish and English workflows.
  • The pilot was designed to fit directly into Edger's investment platform.

Evidence from the source

"90% improvement in the turnaround time for quarterly report data extracts"
"Approximately 96% improvement in the time it takes to summarize the main points of a 30+ page report"
"Each assistant relies on IBM watsonx.ai"
"The collaboration resulted in the creation of three AI-assisted processes"
"The third assistant also utilizes IBM watsonx Assistant"
Transparency Evidence & methodology 95/100 reference value · 89% 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 value95/100
  • 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 scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • 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 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. IBM

    Edger Finance customer story

    First-party
    https://www.ibm.com/case-studies/edger-finance
    Source type
    Vendor-published customer story
    Published
    Apr 22, 2024
    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
MongoDB Oct 8, 2026 Navisio AI Financial Services Europe Rapid adoption of Navisio AI's platform triggered severe latency spikes, elevated CPU and RAM consumption, and costly vertical scaling. As it prepares to scale to 1,000 by the end of the year, and eventually toward 5,000 users, the team is… Document ProcessingEnterprise Knowledge Search MongoDB Atlas · MongoDB Atlas Vector Search Google Cloud Archived · Sep 27, 2026 SIGNAL IDUNA Financial Services Germany SIGNAL IDUNA needed to spread AI safely across a large insurance workforce, make a century of internal policy knowledge searchable, and let teams build their own agents without creating a fragmented, insecure shadow-AI… 80% weekly active adoption rate with a +45 NPS in first five months Document ProcessingEnterprise Knowledge Search Document AI · Gemini · Gemini Enterprise Agent Platform OpenAI Jul 31, 2026 Univé Financial Services Europe & UK Univé needed to build organization-wide AI capability across insurance operations so employees could safely redesign their own work instead of waiting for centralized software projects or isolated AI pilots. 85% of licensed users active every week Document ProcessingEnterprise Knowledge Search ChatGPT Enterprise · Custom GPTs · Workspace Agents