What challenges did HSBC face before AI implementation?

Employees were repeatedly contacting internal policy experts for answers, creating tens of thousands of calls each year. Responses could be delayed by time zones and workloads, and the quality or consistency of answers could vary across experts. HSBC needed a scalable way to support a large global workforce with faster access to internal policy information.

What was the impact of the AI solution?

HSBC gained faster and more consistent access to internal policy information for employees. The chatbot reduced the burden on subject-matter experts by handling routine queries. Query analytics provided useful business intelligence for policy simplification, learning and development, and operational resilience decisions.

Source

GCPExpanded

HSBC deploys Dialogflow to reduce policy-expert call burden

Use case typeCustomer service automationUpdated Jun 13, 2026

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

Reported outcomes

Strategic outcomes

Customer experience & trustFaster and more consistent policy accessSpeed & agilityReduced routine expert query burdenBetter decisions & insightImproved policy analytics for decisions

Primary read

Use case focus

Showing 3 of 3

1Internal policy Q&A
2Conversational AI
3Enterprise search

Employees were repeatedly contacting internal policy experts for answers, creating tens of thousands of calls each year.
Responses could be delayed by time zones and workloads, and the quality or consistency of answers could vary across experts.
HSBC needed a scalable way to support a large global workforce with faster access to internal policy information.

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.

Technologies

Google Cloud Dialogflow Cloud Contact Center AI Natural Language Processing Document search

HSBC gained faster and more consistent access to internal policy information for employees.
The chatbot reduced the burden on subject-matter experts by handling routine queries.
Query analytics provided useful business intelligence for policy simplification, learning and development, and operational resilience decisions.

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

KPMG

Sources & evidence1

ExpandedExpanded

The same organization appears in newer AI deployment evidence.