Waymo appears to be testing adding Google’s Gemini AI chatbot to its robotaxis in an effort to integrate an AI assistant that will accompany riders and answer their questions, according to its findings researcher Jane Manchun Wong.
“While digging into Waymo’s mobile app code, I discovered the full system message for its unreleased Gemini integration,” Wong wrote in a blog. “The document, internally titled ‘Waymo Ride Assistant Meta-Prompt,’ is a 1,200+ line specification that defines exactly how the AI assistant inside a Waymo vehicle is expected to behave.”
The feature hasn’t shipped in public releases, but Wong says the system prompt makes it clear that this is “more than just a chatbot.” The assistant is said to be able to answer questions, manage certain functions in the cabin such as climate control and, if required, reassure riders.
“While we don’t have specifics to share today, our team is always working on features to make driving with Waymo enjoyable, seamless and useful,” Waymo spokeswoman Julia Ilina told TechCrunch. “Some of that may or may not come across in our rider experience.”
This won’t be the first time Gemini has been integrated into the Alphabet-owned self-driving company’s stack. Waymo says it has used The “cosmic knowledge” of Gemini to train its autonomous vehicles to navigate complex, rare and high scenarios.
Wong writes that the assistant is instructed to have a clear identity and purpose: “a friendly and helpful AI companion embedded in a Waymo autonomous vehicle,” whose primary goal is “to enhance the rider’s experience by providing useful information and assistance in a safe, reassuring, and discreet manner.” The bot is instructed to use clear, simple language and avoid technical jargon, and is instructed to keep its responses concise to one to three sentences.
At the system’s prompts, when a rider activates the assistant through the car’s display, Gemini can choose from a set of pre-approved greetings personalized with the rider’s first name. The system can also access contextual data about the rider, such as how many Waymo trips they’ve taken.
Techcrunch event
San Francisco
|
13-15 October 2026
Prompts currently allow Gemini to access and control car functions such as temperature, lighting and music. Notably absent from the list of functions are volume control, track changes, seat adjustment and window control, Wong pointed out. If a rider requests a feature that Gemini can’t control, the bot must respond with “aspirational phrases,” such as, “It’s not something I can do yet.”
Interestingly, the assistant is intended to maintain a clear distinction between its identity as Gemini the AI bot and its autonomous driving technology (the Waymo Driver). So when answering a question like, “How do you see the road?” Gemini should not say “I’m using a combination of sensors” and should instead respond, “Waymo Driver uses a combination of sensors…”
The system’s prompts include a number of fascinating details, such as how the bot is meant to handle questions about competitors like Tesla or the now-defunct Cruise, or what keywords will make it stop talking.
The assistant also addresses the avoidance of guessing, explaining, confirming, denying or commenting on real-time driving actions or specific driving events. So, if a passenger asks about a video of a Waymo hitting something, the bot is instructed not to answer directly and divert.
“Your role is not to be a spokesperson for the driving system’s performance and you should not adopt a defensive or apologetic tone,” the ad says.
The in-car assistant is allowed to answer general knowledge questions such as the weather, the height of the Eiffel Tower, what time the local Trader Joe’s closes, and who won the last World Series. Actions such as ordering food, making reservations, or handling emergencies are not permitted.
Waymo isn’t the only company incorporating AI assistants into driverless vehicles. Tesla is doing something similar with its xAI Grok. However, the two different car assistants have different functions. Gemini seems programmed to be more realistic and focused on driving, while Grok presents itself more as a friend in the car who can handle long conversations and remember context from previous questions.
