Use Case Intelligence RSS Search use cases Search
Google Cloud Automotive France and Spain Company newsroom

Renault Group

Customer Service Automation · Sales Automation

Renault needed a consistent, reliable, and personalized way to guide online vehicle shoppers from discovery to servicing, especially for electric and hybrid questions, without forcing visitors to manually search across site content before speaking with dealers.

Read the original story Explore all use cases
60% of the questions relate to vehicles and their configuration first. Financing is the third topic of interest.
On mobile, complete configurations are multiplied by 3 between user without askrnlt and user who had a chat with askrnlt.
The open rate of askrnlt has tripled compared with the previous chatbot.
more than 50 000 chats with askrnlt since its launch.

Reported impact

Business outcome

askrnlt improved Renault's digital customer experience by giving shoppers faster, more personalized guidance, increasing engagement with the assistant, boosting completed mobile configurations, and better preparing customers before dealer conversations.

  • Customer Experience
  • Revenue Growth

Solution

Renault Group built askrnlt in-house as a customer-facing agentic AI advisor embedded in renault.fr and renault.es. The front-end conversational experience runs through askrnlt, while an orchestrator agent analyzes each visitor request and routes it to the right capability, such as vehicle configuration or product knowledge. The orchestration layer is powered by Gemini 2.5 Flash for natural interactions. To answer and act, the system draws on multiple connected sources: Renault brand website content for product and journey information, the Renault brand configurator for vehicle selection and prefilled configuration paths, a pricing API for commercial data, and an askrnlt confidential database for internal knowledge, alongside Gemini’s general knowledge. Responses are served back as natural-language guidance enriched with images, videos, deep links, and context-aware redirects, with guardrails and human oversight in place to resist misuse and keep answers reliable.

Data flow

Visitor questions and browsing context on renault.fr or renault.es enter askrnlt, where the orchestrator agent running on Gemini 2.5 Flash classifies the request and invokes the right capability. It retrieves product content from the Renault brand website, configuration data from the Renault brand configurator, prices from the pricing API, and internal knowledge from the askrnlt confidential database, then returns rich answers, links, images, videos, or prefilled configurator journeys to the visitor.

Solution architecture

7 components · 5 layers
  1. Ingest
    • pricing API Provides pricing information used in answers and guidance.
  2. Compute
    • Gemini 2.5 Flash Powers the orchestrator to deliver fluid, natural interactions.
  3. Storage
    • askrnlt confidential database Stores internal data used by the agent alongside public website and pricing sources.
  4. Serving
    • askrnlt Customer-facing conversational agent that supports visitors throughout vehicle discovery and decision-making on Renault brand websites.
    • Renault brand website Provides product and journey content and hosts the customer interaction on renault.fr and renault.es.
    • Renault brand configurator Supplies configuration data and receives users through prefilled links tailored to the conversation.
  5. Orchestration
    • orchestrator agent Analyzes each request and activates the right specialized capability, such as configuration or product knowledge.

Architecture clues

  • Available on renault.fr since November 2025 and on renault.es since April 2026.
  • Guardrails were added to protect against jailbreak attempts and misuse.
  • Human oversight remains in place to ensure correct behavior and source retrieval.
  • Multi-agent architecture with an orchestrator and specialized agents.
  • Renault plans rollout to Italy, Germany, the United Kingdom and Brazil by the end of 2026.
  • The deployment covers the full passenger car range.

Evidence from the source

"Adoption of askrnlt keeps growing, with more than 50 000 chats with askrnlt since its launch."
"Data sources: Renault brand website, Renault brand configurator, pricing API, askrnlt confidential database, and Gemini’s general knowledge."
"Integrated into Renault brand websites, askrnlt is a conversational agent developed in-house by Renault Group’s AI, IS/IT and Renault brand Marketing teams."
"Multi-agent architecture with an orchestrator, powered by Gemini 2.5 Flash to ensure fluid, natural interactions."
"On mobile, complete configurations are multiplied by 3 between user without askrnlt and user who had a chat with askrnlt."
"The goal of askrnlt is to enhance customers’ knowledge upstream, enabling richer conversations with dealers... conversion to purchase is easier."
"The open rate of askrnlt has tripled compared with the previous chatbot."
Transparency Evidence & methodology 90/100 reference value · 94% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence94%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    7 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Renault Group

    Renault Group customer story

    First-party
    https://www.renaultgroup.com/en/magazine/technology/the-era-of-agentic-ai-begins-with-askrnlt-a-new-customer-experience-by-renault/
    Source type
    Customer-published story
    Published
    Jun 4, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Jun 4, 2026 · Renault Group · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Google Cloud Modified · Jun 16, 2026 Allvest Securities Private Limited Financial Services India The evolution of Allvest Securities Private Limited is rooted in a fundamental mission: bridging the gap between sophisticated capital markets and the millions of Indian investors seeking a transparent, ethical entry… Achieved 99.9% uptime during peak trading hours on Google Cloud Customer Service AutomationSales Automation Agent Development Kit (ADK) · Agent Platform · BigQuery Google Cloud Archived · Mar 9, 2026 Metrovacesa Real Estate and Construction Spain Metrovacesa needed to qualify thousands of property leads around the clock because manual call-center processes could not keep up with multilingual demand or high-conversion off-hours interactions. Achieved a 94.8% performance improvement and 38% reduction in customer service time Customer Service AutomationSales Automation Dialogflow CX · Dynamics 365 CRM · Gemini Microsoft Jan 28, 2025 Tekion Automotive United States To streamline vehicle purchasing for consumers and dealerships, Tekion aimed to create a unified, cloud-native platform that uses generative AI. One Tekion customer reports up to $5,000 savings a month. Customer Service AutomationSales Automation Azure · Azure Cosmos DB · Azure Kubernetes Service