Skip to content

Industrial company · Machinery & Manufacturing · Customer portal

A customer portal that answers before the customer calls

For an industrial company with customers all over the world we verified the needs of customers and the service team, designed a portal with an AI assistant and delivered the code in production.

Challenge
Customers all over the world and a service team flooded with repetitive questions.
What we did
Needs verified with customers and the service team, a portal with an AI assistant on the documentation, code handed over to the internal team.
Result
A single point of access for orders, spare parts and documentation, and a service team free to focus on the cases that matter.

The context

An industrial company with an international installed base and a customer service under pressure: repetitive requests, scattered documentation, long response times.

Customers looked for information on orders, spare parts and manuals by email and phone, without a single point of access.

The problem

The service team spent most of its time on questions the documentation already answered.

A previous portal had been abandoned: it was designed around functions, not around customers’ needs.

The NiEW method

Before writing a line of code

01. Real needs

Interviews with customers and the service team, analysis of real requests, a map of the most frequent questions and their cost.

02. Defined requirements

The questions that matter, organised into clear requirements: what the portal must solve on its own and what goes to the service team.

03. AI-enabled iterations

A portal organised around customers’ questions, with an AI assistant trained on manuals and technical documentation, tested with real users.

04. Market-ready

Integration with ERP and CRM, gradual release and documented code handed over to the internal team.

The solution

A single point of access for orders, spare parts and documentation, with an AI assistant that answers technical questions from the company’s own manuals.

  • Research with customers and the service team and a map of verified needs.
  • Portal concept and prototype validated with real users.
  • Portal in production with an AI assistant on the technical documentation.
  • Documented code and handover to the internal team.

The results

Self-service answers

Recurring questions on orders, spare parts and manuals are answered in the portal, at any time and in any country.

More effective service

The service team spends its time on complex cases instead of questions the documentation already answers.

Designed to be used

Built around customers’ real questions and tested with them before release, unlike the previous portal.

Client autonomy

Documented code handed over to the internal team, which can evolve the portal on its own.

More case studies

  • Events and energy

    The right news, amid the noise of a trade fair

    Challenge
    Hundreds of news stories a day during ADIPEC and guests with only a few minutes to follow them.
    What we did
    A web app and an editorial back office: three bulletins a day on each person’s topics, verified news, readings approved by the editorial team.
    Result
    App and back office online before the fair opened, with the flow tested on real data from the 2025 edition.
  • Machinery & Manufacturing

    An AI-enabled IoT platform for thousands of installations

    Challenge
    Connected installations growing 30% a year and a control room that could not grow at the same pace.
    What we did
    Operator shadowing, machine-learning alarm prioritisation and an AI assistant to resolve cases.
    Result
    Growth without a proportional increase in staff, onboarding from 3–6 months to 4–6 weeks.
  • Machinery & Manufacturing

    An after-sales platform for a group of 50 companies

    Challenge
    Fifty companies in an industrial group, each with its own after-sales tools.
    What we did
    Mapping of 50 tools, 840 insights from interviews, 68 user stories and a structured RFI for vendors.
    Result
    A platform choice free from vendor bias and shared requirements for a global customer portal.

Your project could be the next case study

Tell us about your challenge: in a first call we work out together how we can help.

Book a call