Microsoft Financial Services Türkiye

Akbank

Enterprise Knowledge Search

If needed, they would reach out to the central support management,” explains Yalçın.

Akbank, now serving over 10.8 million active customers, extends its services through a vast network, with more than 700 branches and 12,000 employees.
Founded in 1948 in Adana, Türkiye, Akbank started as a local bank focused on providing funding to local cotton producers.
Generating correct answers 90 percent of the time, chatbot allows customer representatives to easily save up time, in time of need.
Previously searching through answers in a 10,000-article knowledge base, Akbank staff now conversates with an AI chatbot.

Reported impact

Business outcome

“And with every minute saved, our productivity increases.” Unsurprisingly, Akbank employees received the chatbot very positively.

  • Cost Reduction
  • Customer Experience
  • Productivity Improvement

Solution

Akbank, one of Türkiye's largest banks, has transformed its customer support operations using Azure OpenAI Service to improve employee and customer experience. If needed, they would reach out to the central support management,” explains Yalçın. "When needed, branch employees save time in every customer interaction using the Azure OpenAI-based chatbot," notes Yalçın. “When needed, branch employees save time in every customer interaction using the Azure OpenAI-based chatbot.” Gizem Yalçın, Smart Digital Assistant Applications Technical Product Owner, Akbank Its growth continued with the establishment subsidiaries in subsequent years, including AKSecurities, AKInvestment Trust, and AKAsset Management. “And with every minute saved, our productivity increases.” Unsurprisingly, Akbank employees received the chatbot very positively.

Solution architecture

3 components · 1 layer
  1. Compute
    • Azure OpenAI Service Runs the generative AI experience that answers questions, summarizes content, or drafts outputs for users.
    • Azure Provides the secure, scalable cloud foundation for the solution.
    • Azure Machine Learning Trains and operationalizes machine learning models used by the solution.

Architecture clues

  • "When needed, branch employees save time in every customer interaction using the Azure OpenAI-based chatbot," notes Yalçın.
  • Akbank, one of Türkiye's largest banks, has transformed its customer support operations using Azure OpenAI Service to improve employee and customer experience.
  • Its growth continued with the establishment subsidiaries in subsequent years, including AKSecurities, AKInvestment Trust, and AKAsset Management.
  • “When needed, branch employees save time in every customer interaction using the Azure OpenAI-based chatbot.” Gizem Yalçın, Smart Digital Assistant Applications Technical Product Owner, Akbank

Evidence from the source

"When needed, branch employees save time in every customer interaction using the Azure OpenAI-based chatbot," notes Yalçın.
Akbank, one of Türkiye's largest banks, has transformed its customer support operations using Azure OpenAI Service to improve employee and customer experience.
If needed, they would reach out to the central support management,” explains Yalçın.
“And with every minute saved, our productivity increases.” Unsurprisingly, Akbank employees received the chatbot very positively.
Transparency Evidence & methodology 72/100 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 value72/100
  • Problem clarity12/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth15/25
    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 impact15/25
    1 metric 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
    4 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. Microsoft

    Akbank customer story

    First-party
    https://www.microsoft.com/en/customers/story/1731060947842679292-akbank-azure-open-ai-service-banking-en-turkiye
    Source type
    Vendor-published customer story
    Published
    Jan 30, 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

  • Published on source page Jan 30, 2024 · Microsoft · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.