Normalized claim
Accuracy: 98% increase
The article reports 98% answer accuracy and a 25% increase in customer satisfaction.
GCPEvidence: Medium50/100
Federal Bank (India) - Feddy AI virtual assistant using Dialogflow Enterprise Edition
Use case typeCustomer service automationUpdated Jun 13, 2026
Federal Bank Limited is a major digital-first Indian commercial bank serving more than 10 million customers across India. The bank built Feddy, an AI personal assistant, to handle conversational customer queries in colloquial language, reduce manual bot training, and support a path toward complex transactional banking without human intervention.
- Organization
- Federal Bank
- Industry
- Finance
- Location
- India
- Published
- January 2020
Reported outcomes
+98%
accuracyQuality & accuracy
+25%accuracy−50%cost
Strategic outcomes
New product / capabilityBuilt a colloquial language customer assistantSpeed & agilityReduced manual bot training effortScale & capacityScaled customer support query handlingCustomer experience & trustImproved customer satisfaction
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Accuracy: 25% increase
The article reports 98% answer accuracy and a 25% increase in customer satisfaction.
Normalized claim
Cost: 50% decrease
The bank expects the assistant to support complex transactional banking and to help migrate 50% of contact center volume, with projected 50% customer relations cost savings by 2025.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Federal Bank
- Provider
- GCP
- Maturity
- Unknown
- Linked source
- Google Cloud Customer Stories
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1Conversational AI
- 2Customer Service Automation
- 3Digital Banking
- Deliver a customer assistant that understands colloquial conversational queries, not just fixed phrasing.
- Scale customer support interactions while reducing dependence on human agents and manual bot training.
- Create trust in the assistant so it can eventually handle transactional banking tasks.
- Federal Bank partnered with Riafy Technologies to build Feddy using Dialogflow Enterprise Edition.
- The solution uses Dialogflow contextual speech understanding and auto-learning so the bot can train itself instead of requiring manual training for each question.
- The rollout included integration with Google Business Messages for asynchronous customer conversations, and the bank planned to add Google Cloud analytics capabilities such as BigQuery ML for personalization.
- The article reports 98% answer accuracy and a 25% increase in customer satisfaction.
- Feddy handles up to 1.4 million queries per year, up from 600,000 in the earlier prototype.
- Dialogflow auto-learning saves the development team up to five hours per day on routine training tasks.
- The bank expects the assistant to support complex transactional banking and to help migrate 50% of contact center volume, with projected 50% customer relations cost savings by 2025.
Architecture
Federal Bank built Feddy on Dialogflow Enterprise Edition with Riafy Technologies. The implementation uses contextual speech understanding and auto-learning in Dialogflow, integrates with Google Business Messages for asynchronous conversations, and is planned to extend into analytics and personalization with Google Cloud tools such as BigQuery ML.
Implementation partners1
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jan 1, 2020Publisher: Google Cloud Customer StoriesEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
Loading comments...