01
Identify the equipment context
Connect the request to the relevant inverter, battery, installation, or energy-use situation.
Independent, source-backed renewable-energy case study · AI customer support
Deye: AI support in more than 30 languages.
Deye built a multilingual AI customer-service system for renewable-energy equipment deployed across more than 110 countries and regions. AWS reports 24/7 service, automated resolution, and higher agent efficiency.
Starting point
Deye needed to support customers and distributors in more than 110 countries and regions despite language differences, time zones, and limited access to specialist knowledge.
Solution implemented
Deye and Goclouds built an omnichannel AI service system using ConnectNow and Amazon Bedrock, connected to approved knowledge and available through web, app, email, WhatsApp, and Facebook.
Reported result
AWS reports support in more than 30 languages, 24/7 availability, automatic resolution of 60% of common issues, and more than 30% higher customer-service efficiency.
How it worked
Deye built one multilingual service layer across its global channels.
Customers and distributors could contact the service through their existing channels. The AI assistant used specified knowledge bases to answer common questions and supported human agents on the remaining tickets.
Headline result
60%
of common issues automatically resolved, reported by AWS
02
Retrieve approved guidance
Ground the answer in maintained product and service knowledge rather than an open-ended response.
03
Respond in the right language
Use multilingual assistance while preserving technical meaning and escalation rules.
04
Escalate the exception
Route unusual, safety-sensitive, or unresolved cases to a qualified person with the useful context attached.
Reported business impact
The reported result was a broader and faster support operation.
AWS's customer story reports measurable changes in language coverage, routine resolution, and service-team efficiency after the system was introduced.
01
More than 30 languages
The AI service supports customers and distributors in more than 30 languages.
02
60% of common issues resolved
AWS reports that the chatbot automatically resolves 60% of common issues using specified knowledge bases.
03
More than 30% higher efficiency
AWS reports that AI assistance increased customer-service efficiency by more than 30%.
What this case shows
The evidence is specific.
These lessons come from the implementation and reported results above. The source and attribution are provided below.
- 01 Connect the assistant to equipment and energy context, not only a document library.
- 02 Define which answers can be automated and which require technical escalation.
- 03 Measure automated resolution, agent efficiency, escalation, and repeat contact together.
- 04 Keep unresolved and safety-sensitive equipment issues on a qualified human path.
Source and attribution
Where these claims come from.
Independent industry case study summarised by Remova Tech from AWS's published Deye customer story. Remova Tech did not deliver this project; all performance figures are attributed to AWS and the companies named in the original source.
Verify the reported results in the original sourceHave a similar challenge?
Let’s discuss the actual project.
Show us the current process, systems, data, and target result. We will help you determine what can be built and how success should be measured.