Putting AI to work for the public interestHow IFJR gave victims a voice through artificial intelligenceDiscover how Marion Berthaut and the French Institute for Restorative Justice transformed 200 sensitive testimonies into actionable data for research and public policy, while preserving each person's dignity.A unique but unusable knowledge baseSince 2018, IFJR has built a rare corpus of more than 200 testimonies from restorative justice programsExceptional value under heavy constraintsThese narratives, collected from victims and offenders, are exceptionally rich material for understanding restorative justice mechanisms.What is restorative justice?Established in French law for over a decade, it complements criminal justice by creating safe spaces for dialogue between victims and offenders. The goal is to help victims regain agency over their story and encourage offenders to face the concrete consequences of their actions.International studies show these approaches support desistance and reduce reoffending. In France, however, one major barrier remains: the lack of usable data, capable of objectifying these effects and clarifying the psychological mechanisms at play.200+Testimonies collected since 2018Victims & OffendersVulnerable populations100%Sensitive data protectedKey constraintsExtremely sensitive data: Vulnerable populations requiring maximum protectionHeterogeneous formats: Phone interviews, written content, and reportsManual anonymization was impossible at scaleQualitative analysis was too heavy for small teamsNo tools were compatible with the sector's ethical requirements"We should start a project, but it would take me three months full-time. I don’t have three full months to dedicate to it."President of IFJRFacing the temporal and cognitive barrierResult: An underused knowledge asset, even though it could have fed research and public debate. Without a suitable solution, this project would simply never have launched.An expert bridging disconnected silosMarion BerthautNLP R&D Expert - Fractional R&D Lead For the past ten years, Marion Berthaut has been working in natural language processing (NLP). In 2015, she launched her first company to help people with dyslexia read more effectively, already using linguistic analysis technologies. Today, Marion works as a "fractional R&D lead." Her mission: spotting opportunities where others do not see them.“You have an extraordinary body of textual material, of incredible richness. It just so happens that there are tools capable of leveraging this textual matter especially when there’s a lot of it and extracting some really fascinating insights from it.”Marion Berthaut“That’s exactly what happened with the IFJR at the beginning of 2025.”Why Swiftask: Sovereignty FirstMarion needed an “off-the-shelf” solution, quick to deploy, without having to build everything from scratch.Digital SovereigntyData hosted in France • Full control over inferences • No training on third-party modelsInnovation SandboxRapid experimentation • Frictionless trial-and-error • No benchmarking for each new ideaImmediate DeploymentReady to use solution • No development from scratch • Production deployment in a few weeksMulti-modelAccess to Mistral, Anthropic, and others • Cost optimization • Selecting the best model for each use case"For ideological reasons and the values at stake, I wouldn’t use certain models in the context of restorative justice. The idea that testimonies could be stored on servers outside of France was simply inconceivable."Marion BerthautThat’s exactly what happened with IFJR in early 2025.Marion discovered Swiftask at the beginning of 2025 thanks to Olivier La Grandeur. At that time, the AI solutions market was still young. “You have to put yourself in the context—it’s January 2025. There aren’t 36,000 solutions available,” Marion recalls.An excellent sandbox"Swiftask spares me from having to worry about which tool to choose. I can experiment, tinker, and develop relevant use cases. For someone whose job is to imagine innovations, this freedom was invaluable."Edwin: A Game-Changing Proof of ConceptData Exploration for Restorative Justice – Digital IntelligenceA tribute to Edwin Lemert, who theorized the distinction between primary and secondary deviance.TranscriptionPhone interviews are transcribed automatically with high accuracy, preserving nuances and emotions.Full AnonymizationAn agent detects and removes all personal identifiers (names, locations, dates) based on the standards of the Cour de Cassation.AnalysisOnce anonymized, the testimonies can be provided to research laboratories for in-depth analysis.A Pragmatic ApproachMarion released the first version of Edwin in May 2025, working with 50 testimonies. She tested different models (Mistral, Anthropic) and optimized costs by using models that consumed fewer tokens.Results That Transform What’s PossibleAn ROI measured not in hours saved, but in value created"It’s a game changer. It allows us to do things that weren’t accessible before. Edwin saved us time, but more importantly, it made us decide to act. Where the time required was prohibitive, we simply wouldn’t have done it."Marion BerthautThat’s exactly what happened with IFJR in early 2025.Major DiscoveryEdwin detected a particular anger from victims toward the penal system itself, revealing a systemic issue that had not previously been documented through the testimonies.Giving Participants a VoiceIFJR was able to provide the Ministry of Justice with insights that no one else could offer during public policy evaluation: the voices of offenders and victims.Funding Secured€150,000 in funding was secured to develop Edwin 2. The POC served as a proof of concept for private foundations. Before Edwin, IFJR would have simply “not applied for the grant.”Game ChangerEdwin enabled the decision to act. Where the time required had been prohibitive and so nothing was done it became possible. This represents a scale-up opportunity for IFJR.The transformation in numbersBefore Edwin200 dormant testimonialsNo usable outputAbsent from evaluationsAbandoned (too heavy)Blocking cognitive barrierAfter EdwinUsable anonymized testimonialsInsights delivered to the MinistryIntegrated into public policies€150,000 in funding securedProject launched and deployedEdwin 2: Scaling upDemocratize access to testimonials for researchThe next stepNow that Edwin is trained, Marion is waiting for the €150,000 funding to be released to further develop Edwin."An agent will return the intelligence you give it. So if you ask it stupid questions, it will answer stupidly. That’s how it works: it amplifies. If you amplify zero, well, it will still be zero. But if you amplify intelligence, then it’s astonishing."Marion BerthautThat’s exactly what happened with IFJR at the beginning of 2025.Open to a small group of IFJR members for daily useSupported by training to learn how to ask the right questionsAccessible to partner research labs with strong security guarantees10Trained IFJR usersTrainingIntegrated training programResearchSecure access for laboratoriesHarness AI power for the benefit of society"There are tools around language processing. These tools are super powerful. It's incredible. Rather than just using them to analyze online reviews to figure out which second toaster you’re going to buy when you don’t even need one...""What if we put that power to work on something that benefits society?"Marion BerthautThat’s exactly what happened with IFJR at the beginning of 2025.The problem in numbers200+Testimonies collected since 2018Victims & OffendersVulnerable populations100%Sensitive data protectedIndustryRestorative justiceSupport for victims and offendersTraining and research in criminal justiceRestorative dialogue (criminal and extrajudicial)Size12 employeesLocation46 boulevard d'Alsace Lorraine - 64000 PAU (Pyrenees-Atlantiques)Ready to transform your agency?Discover how Swiftaskcan multiply your team's productivityStart my Free trial now!