Turo connects car owners with renters worldwide. Supporting users across multiple languages and regions is essential to its global peer-to-peer car sharing marketplace.
In two months, Turo built its initial AI agent with Voiceflow. The first deployment focused on new-user education and FAQs on Turo's "How It Works" page, giving the team a focused place to validate accuracy before expanding further.
Benjamin Biancamaria, who leads Turo's product teams in France, described users' disappointment with the existing solution. Combined with the challenge of scaling support while keeping costs down, that led Turo to research AI-based solutions.
The challenge: moving beyond basic chatbots
Turo was using a traditional decision-tree chatbot that had been acquired by Zoom. While their operations team had done an impressive job optimizing the tool, its limitations were becoming increasingly apparent:
- The chatbot could only handle pre-programmed decision trees.
- Users were frustrated by its rigid, mechanical responses.
- It was difficult to measure true contact deflection rates
- The solution couldn't scale with Turo's growing global user base
Finding the right solution: a strategic evaluation
At the beginning of 2023, Benjamin and Eric Comellas, Senior Director of Engineering at Turo, were tasked with analyzing AI opportunities for Turo. Through their evaluation, they identified three distinct categories of potential solutions:
After extensive evaluation, including discussions with major providers like Google, Turo chose Voiceflow for several key reasons:
- Flexibility with speed: They could leverage existing infrastructure while maintaining the ability to customize and expand beyond just chatbot use cases.
- Quick implementation: The visual interface and support enabled rapid development without requiring investment in additional engineering resources while providing high confidence in time to market.
- Strong partnership: The Voiceflow team provided dedicated support, including bi-weekly meetings and a dedicated Slack channel for rapid problem-solving.
- Future-proof: The extensibility of the platform would allow Turo to easily scale to future use cases, such as automating agent emails.
- Cost-effective: Compared to similar solutions, Voiceflow offered competitive pricing with clearer terms.
The vision: a proactive customer support agent
Turo planned three phases, beginning with an accurate FAQ agent before expanding to transactional and proactive support.
The informational phase called for an extremely accurate FAQ agent with low tolerance for hallucination. The transactional phase would connect the agent to user data, while the problem-solving phase would enable it to take actions and proactively assist customers.
Their ultimate north star? An AI agent that could say, "I see your flight was delayed. Let me move your trip back an hour or two," without requiring customer intervention.
Aligning the team around an inspirational vision created the buy-in necessary to implement the first phase and get their AI agent project off the ground.
The solution: rapid implementation of phase one
As a proof of concept, Turo chose to launch their initial agent on their "How It Works" page, which is focused on new user education and support. This approach allowed them to validate their AI capabilities while minimizing risk.
The team moved quickly through seven iterations in two months, following a structured approach:
Start simple. Begin with knowledge-base inquiries and responses. Use a defined response format to enforce step-by-step thinking and ground answers in factual knowledge.
Improve iteratively. Refine prompts and add topic validation as complexity increases.
Test rigorously. Test against 40-50 must-handle questions. An LLM scoring system evaluates accuracy, relevance, clarity, and completeness to detect both improvements and regressions.
Monitor comprehensively. Track 37 different metrics across the agent's performance to support continued improvement.
The team particularly valued Voiceflow's observability features, which provided visibility into the agent's decision-making process. "Being able to see what's happening at every step helps us better understand the agent's behavior," notes Biancamaria. This visibility into agent actions, through features like the debug mode and Prompts CMS, became crucial for maintaining quality and iterating effectively.
Each update built upon lessons from the last, with the team regularly testing with users and refining based on feedback. By the seventh version, they had achieved the reliability and accuracy needed for production deployment.
Technical architecture
Turo designed the agent to process multiple aspects of an interaction simultaneously to keep latency low.
The agent also generates responses and checks their quality:
Response generation
- Distinct style guides for hosts and guests.
- Structured JavaScript format to enforce logical response construction.
- Relevant hyperlinks identified and integrated automatically.
- Self-verification and rewriting capabilities.
- Responses and UI elements, including buttons, in the user's detected language.
Quality control
- Real-time response validation: the agent double-checks its answer and rewrites it if adjustment is needed.
- Dynamic button creation for improved user experience.
- Comprehensive knowledge base integration.
- Multilingual capability verification.
One of the benefits of working with Voiceflow at the enterprise level is access to staff expertise in agent design and prompt engineering.
The results: achieving 99% response rate
The first-phase deployment helped Turo meet its criteria for moving to the next phase. Accuracy and user satisfaction were priorities for the pilot.
The agent was deployed on a prospect-facing page rather than a customer support page. The team described the 2% escalation rate as expected in that context and planned to learn more as they expanded into customer support.
The team noted that a 90% accuracy rate is a realistic goal for an AI Agent because seeking a perfect solution is not the end goal. Achieving similar (or better) results than human agents and focusing on accuracy for blocking points is the objective.
That being said, the agent has proven particularly effective at meeting its first objective of new user education, successfully handling common inquiries about booking processes, protection plans, and getting started with Turo. Through comprehensive monitoring of 37 different metrics, the team maintains visibility into every aspect of the agent's performance, enabling continuous optimization and improvement.
Key learnings and best practices
Turo's quick, successful implementation of a proof-of-concept AI agent shows how important it is for enterprises to start with focused use cases while exploring new AI initiatives.
For others considering the same path, keep these insights in mind:
- Set a North Star: The Turo team knew they eventually wanted an agent that could handle complex, proactive support, and that inspiration fueled them as they started at the ground floor
- Start small, scale smart: Begin with a focused use case and expand based on success
- Iterate rapidly: The team went through seven prototypes before reaching their production version
- Know your metrics: Track multiple metrics beyond just satisfaction rates, ideally keeping a dashboard for team alignment and reporting
- Test thoroughly: Combine automated testing with manual verification of responses
- Focus on accuracy: Prioritize response accuracy before expanding into additional features and functionality
With Voiceflow, the team could use a simple API to create their knowledge base and focus on chatbot design and prompting. Eric described the repeated human and automatic tests as key to the first phase and to moving into the next phase.
Looking ahead
With their initial success, Turo is now positioned to expand their AI capabilities further. Future plans include:
- Replacing their legacy customer support chatbot with the new AI solution
- Expanding the agent's capabilities to handle more complex scenarios
- Integrating deeper transactional capabilities
- Developing proactive problem-solving features
"We knew there was potential, but we weren't exactly sure about the size of it," explains Biancamaria. “We imagined needing some flexibility during the research process. We imagined using Voiceflow for automating agent emails, for example, which would not have been possible with pure chatbot solutions.” Their measured approach and successful implementation with Voiceflow has now given them the confidence to pursue more ambitious AI initiatives.
Want to learn how Voiceflow can help your organization build advanced AI agents? Request a demo today
