ENGIE
Autonomous genAI customer agent integrated with the CRM
ENGIE's Agentforce genAI customer agent, integrated into the mobile app in Belgium, resolves 71% of cases on its own and assists 83% of users, deployed in less than a month versus about nine for prior AI projects.
Key points
- Autonomous genAI customer agent in the ENGIE mobile app (billing, meters, EV charging).
- Salesforce Agentforce anchored on the CRM, integrated with Capgemini.
- 71% of cases resolved on its own, 83% of users assisted, go-live in less than a month.
- Evidence level B, confirmed live status.
Objective
Answer customers' common questions instantly in the mobile app, resolve as many cases as possible without an advisor, and drastically shorten the time from idea to production for an agent.
The deployment
ENGIE integrated Agentforce natively into Salesforce for its Belgian customers with a contract or a smart meter. The agent, available in the ENGIE mobile app, gives immediate answers on billing, clean energy, smart meters, and electric vehicle charging, and guides onboarding. It resolves 71% of cases on its own and assists 83% of users. The go-live, carried out with Capgemini, took less than a month, where prior AI projects required about nine months.
Results Proof B
A quantified platform case study (Salesforce) with resolution and assistance rates, repeated in an article from the same source. Concordant sources but both from the publisher, hence level B.
How it works
Documented architectureThe stack in detail
- plateforme Salesforce Agentforce Salesforce-native genAI agent, anchored on the knowledge base and CRM context; resolves 71% of cases on its own in the app.
- plateforme Salesforce (CRM) Account and contract foundation the agent relies on to contextualize its answers.
- integrateur Capgemini Integration partner; go-live in less than a month, versus about nine months for prior AI projects.
- infra Application mobile ENGIE The agent's single channel for Belgian customers with a contract or a smart meter.
How it runs, concretely
For ops teams-
1Question in the app customer
The Belgian customer asks a question in the ENGIE mobile app (billing, meter, EV charging).
-
2Anchored answer AI
Agentforce retrieves the answer from the knowledge base and CRM context, then answers or guides onboarding.
-
3Resolution or escalation AI
The agent closes the case on its own when it can, otherwise it passes to an advisor.
The product knowledge base and the state of the customer account in Salesforce. If the base is incomplete or out of date, the autonomous resolution rate drops and the agent refers to an advisor.
How your customers perceive this type of use
Sourced studiesLes consommateurs n'acceptent pas les chatbots par defaut : 64% prefereraient que les entreprises n'utilisent pas d'IA dans leur service client (Gartner, 2024) et pres d'un utilisateur sur cinq du service client par IA n'en retire aucun benefice (Qualtrics, 2025). L'acceptation se construit sur trois conditions mesurees par Salesforce : savoir qu'on parle a une IA, pouvoir escalader vers un humain, comprendre la logique de l'agent.
Acceptance conditions
- Etre informe qu'on parle a une IA et non a un humain (pres de 75% le demandent, Salesforce 2024)
- Un chemin d'escalade clair vers un agent humain (45% plus enclins a utiliser l'agent IA, Salesforce 2024)
- Une logique de l'agent clairement expliquee (44% plus enclins, Salesforce 2024)
Red lines
- Rendre l'humain injoignable : c'est la premiere inquietude des consommateurs sur l'IA dans le service client (Gartner 2024) et 50% craignent que l'IA les coupe du contact humain (Qualtrics 2025)
- Remplacer le service client par l'IA sans alternative : 53% envisageraient de partir chez un concurrent (Gartner 2024)
Sources: Salesforce 2024 · Gartner 2024 · Qualtrics 2025
How to replicate
Inference, not sourcedData prerequisites
- a structured product knowledge base
- an up-to-date CRM with account status
- a reference of frequent questions
Org prerequisites
- a Salesforce CRM already in place
- a team able to maintain the knowledge base
- an integration partner for the start
Possible stack
- Salesforce Agentforce
- alternative: a genAI agent anchored on a knowledge base and connected to the CRM
The plan, step by step
- Step 1Structure the knowledge base of frequent questions: billing, smart meters, EV charging.Deliverable: A clean, versioned knowledge base
- Step 2Configure the agent on the CRM: anchoring on the base, tone, answer scope.Deliverable: An agent configured in a test environment
- Step 3Test answer accuracy and the escalation rules to an advisor, then wire the app channel.Deliverable: Test suite passed, escalation working
- Step 4Go live in the app and track the autonomous resolution rate.Deliverable: Agent live with a resolution and assistance dashboard
First step: Structure the knowledge base of the most frequent questions and wire a genAI agent anchored on it in a single channel (the app).
The same pattern, proven in other industries
ADT
genAI customer agent
Air India
genAI customer agent (automated customer service)
AT&T
Governed enterprise genAI assistant: an LLM connected to internal knowledge, open to tens of thousands of employees and called at scale by automated systems
Sources
- S1 ENGIE lights the way in energy service with Agentforce's instant answers Interested party archive pending
- S2 How ENGIE and Salesforce Are Redefining Customer Engagement Interested party archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.