ticket_triage · saas · workflow
TomTom's Generative AI Journey: Hub-and-Spoke Innovation for Location Technology
TomTom needed to stay competitive by adapting its location technology for AI use cases externally and streamlining internal operations, while managing GenAI risks such as hallucinations and potential confidentiality breaches—without substantial additional investment or a large influx of new hires.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Spoke team identifies opportunity
Local teams with domain knowledge identify opportunities for GenAI applications within their domain.
Tools used
Azure OpenAIGitHub CopilotChattyMicrosoft 365 CoPilotBentoMLAzure MLChatGPTSalesforceWorkday
Outcome
TomTom launched a ChatGPT location plugin, the Tommy in-car AI assistant, and multiple internal GenAI applications simplifying mapmaking and location technology development—all without significantly increasing budgets or expanding team size.
Results
Time savedfrom quarters to mere weeks
Volume30-60%
Grounding & classification
Source type: technical build writeup
35 fields verified against source quotes.
chatbotcode generationcontent generationconversational aidocument classificationragcode diff prknowledge basesocial media postsupport ticketmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedautomotivesoftwarecycle time reductionemployee productivitytechnical build writeupback office opsquality assuranceticket triage