Gemini · Google
Draft chargeback responses from dispute emails and transaction records
Dojo, a UK card payments provider, built a Chargeback Agent on Google's Gemini platform that reads dispute emails and transaction records and prepares responses and reports in the format card networks require.
What they did
After rolling Gemini out company-wide, with a partner setting up the first connectors, Dojo used the Gemini platform for more complex agents that handle unstructured data. The Chargeback Agent analyzes the emails in a dispute together with the matching transaction records, builds a structured response, and generates the report card networks expect. A separate agent classifies and extracts data from onboarding and compliance documents.
How it went
The company says the Chargeback Agent cut processing time for complex dispute cases by 70%, and the document agent brought onboarding from hours to minutes.
Worth knowing
This is a vendor case study with no accuracy or win-rate figures for disputes. It does not describe how staff review the agent's responses before they go to card networks.
Try it with Gemini
Here is a chargeback case: the customer and bank emails in <dispute email file> and our records in <transaction export>. Summarize the reason code and the customer's claim, list the evidence we have that supports or weakens our position, and draft a response in <the card network or acquirer template>. Flag any missing evidence, and do not send anything.
We wrote this prompt from the case. Replace the parts in angle brackets with your own details.
What this label means: Vendor says
The maker describes it on its own site or launch post. It shows what the product is meant to do, with no independent result.
Real cases of AI agents at work, from every major agent, each linked to where it was first reported. Rewritten in our own words, most with a prompt you can try. These are not Wize customers.