HSBC deploys Dialogflow to reduce policy-expert call burden
HSBC, a global banking organization, built ORRA as an intranet-accessible FAQ and document-search chatbot to answer internal policy questions for risk management colleagues across its global operations. The solution was designed to reduce the time employees spent on manually intensive policy queries, improve the consistency and quality of responses, and provide analytics on the type, frequency, and source of questions for operational resilience and policy improvement.
- Organization
- HSBC
- Industry
- Finance
- Location
- United Kingdom
- Published
- March 2021
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- HSBC
- Provider
- GCP
- Maturity
- Production
- Linked source
- Google Cloud Blog
The solution was designed to reduce the time employees spent on manually intensive policy queries, improve the consistency and quality of responses, and provide analytics on the type, frequency, and source of questions for operational resilience and policy improvement
Primary read
Use case focus
Showing 3 of 3
- 1Internal policy Q&A
- 2Conversational AI
- 3Enterprise search
- HSBC selected Google Cloud and worked with Google Cloud customer engineering and KPMG's Innovation Division to deliver Operational Resilience and Risk Application (ORRA).
- ORRA uses Google Cloud Dialogflow, a core component of Cloud Contact Center AI, to power conversational FAQ flows and natural language interactions.
- The team created a knowledge base of intents, utterances, and answers, bulk uploaded content into Dialogflow, and used synonyms, entities, and small talk to improve bot behavior.
- The architecture also includes an in-house document search capability that returns supplementary answers through the same UI in milliseconds.
- ORRA captures conversation analytics and uses machine learning and user feedback to improve response selection over time.
Architecture
ORRA is an intranet-accessible chatbot built on Google Cloud Dialogflow within Cloud Contact Center AI. It combines an intent/utterance/answer knowledge base with bulk upload into Dialogflow, synonyms, entities, small talk, and an in-house document search layer that surfaces supplementary answers through the same UI in milliseconds.
Implementation partners1
Sources & evidence1
- Customer explicitly identified
- Deployment status explicitly supported
- Technical implementation details available
The same organization appears in newer AI deployment evidence.
- Same organization re-documented as recently as 2024.
Measures whether this deployment's public evidence persists — not whether the system is still in production.
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?
Community
Comments
No published comments yet.