🎧 Customer serviceFrom a real public post
MOM contact centre halves after-call work with GenAI
AgentAWS Bedrock + ins8.ai
IndustryGovernment
CountrySG
DifficultyHard
Tool costEnterprise build
Saved (RM/SGD)After-call work down >50%
Source typeVendor case study (public sector)
1 · The problem
Agents spent a lot of time on note-taking and looking up answers.
2 · Agent setup
Calls are transcribed live in Singapore-accented English, an assistant answers policy questions, and summaries are auto-drafted.
3 · Result
NCS reports after-call work down by more than 50%, average handling time down 12% and productivity up 6%.
4 · Copy-paste prompt
Summarise this customer call transcript: issue, what was promised, next step, deadline. Under 80 words, in our CRM note format.
Related
AI agent answers 2,000+ support chats a month
The consultancy says the agent now handles over 2,000 conversations monthly and three support staff moved into sales without anyone being let go.
NTU's GenAI student bot saves 14.5 days of work a month
NTU's CIO says it saves about 14.5 days of work a month.
Hong Leong Bank chatbot handles 67% of queries
Google Cloud reports the chatbot handles 67% of support queries at 99% accuracy (up from 75%), and coding assistance cut development time by 10-25%.