Case Study: a Geneva foundation in the financial sector
An audit first, then one workshop per real irritant
Situation
This Geneva foundation in the financial sector works in two languages and produces written analysis whose editorial quality carries its signature. At peak periods, mistakes were slipping past the proofreading stage. Alongside that, teams were working through long, highly standardised public reports by hand, and writing up their meeting minutes afterwards, on time they could not spare.
Objective
Map what people actually do before deciding anything, then equip each team against its own irritants rather than rolling out a single tool for everyone, all within a contractual framework compatible with Swiss data protection law.
Saved per set of minutes
45 min
Fields extracted as JSON
61
Training languages
FR and DE
Framework chosen
Swiss data contract
Process
A shared foundation, in both languages
A half-day of common ground, held twice: in German in Zurich and in French in Geneva, so that both sites started from the same level of understanding.
Quantitative audit, then a day of interviews
A questionnaire to map actual usage, completed by a day of qualitative interviews with all staff. A workshop roadmap came out of it, prioritised team by team.
The workshops, one per irritant
A proofreading assistant for the quality pass at peak periods, structured extraction from public reports, a visual communication workshop, a French-to-German translation workshop built on the in-house glossary, a meeting minutes workshop and a deep research workshop adapted to each role.
Results
Forty-five minutes saved on writing up a two-page set of meeting minutes
61 fields extracted from each public report and returned as usable JSON, then fed into a spreadsheet and into the foundation database
A proofreading assistant that now goes over every text before it is sent out, where the proofreading pass used to be skipped at peak periods
A French-to-German translation assistant that respects the in-house glossary
Adoption of Claude under a contract compliant with Swiss data protection law, rather than a free tool that would send data out of Switzerland
Contact us
- Want to upskill your teams?
Let's schedule a meeting to assess your training needs
- Want to identify high-ROI use cases for generative AI?
Let's schedule a strategic call