Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
Capgemini transforms software engineering with a self-hosted AI assistant powered by Mistral
…nity Partners Help center Start building Studio Vibe Vibe for Code Get in touch Capgemini transforms software engineering with a self-hosted AI assistant powered by Mistral. Technology and Software Transforming client delivery through a private software…
Description
Capgemini built 'RAISE for Private Software Engineering', an internal, self-hosted AI coding assistant for regulated clients in aerospace, defense and public sectors who require on-premises AI. After switching the underlying model from an open-source LLM to Mistral's Codestral, without changing IDE or CI/CD integrations, code completion accuracy jumped from 50% to 90% and developer adoption rose from 30% to 100% across all client projects, with more than 50 client projects reporting productivity improvements within six months.
…emini France. Codestral delivers the breakthrough needed for developer adoption Capgemini's transformation came when they transitioned from their previous open-source LLM to Mistral's Codestral in their self-hosted coding assistant solution. The switch required no changes to their existing infrastructure—they simply rep…
…productivity gains while maintaining data sovereignty for regulated industries. 100% developer adoption rate across all client projects 90% code completion accuracy vs. 50% with previous solutions 50+ client project…
Company
Capgemini
…s 50+ client projects reporting productivity improvements in less than 6 months Capgemini, a global system integrator with 350,000 employees across 40+ countries, has revolutionized its software engineering capabilities through “RAISE for Pr…
Industry
Technology & Software
…sforms software engineering with a self-hosted AI assistant powered by Mistral. Technology and Software Transforming client delivery through a private software engineering assistant. Capgemini transforms software engineering with a self-hosted AI assistant power…
Problem
Capgemini's regulated clients in aerospace, defense, and public sectors had strict data-privacy and sovereignty requirements that ruled out cloud-based generative AI. Its earlier open-source coding assistant only reached 30% developer adoption, with ~50% accuracy that developers found insufficient for daily use, and it needed to support legacy applications dating to the 1980s across languages like ADA and C/C++.
…rce coding assistants proved unsuccessful despite promising laboratory results. Adoption rates remained at only 30%, with developers finding the ~50% accuracy insufficient for daily use. The company also faced the complexity of supporting legacy applications dating…
…only 30%, with developers finding the ~50% accuracy insufficient for daily use. The company also faced the complexity of supporting legacy applications dating back to the 1980s, requiring AI assistance across diverse programming languages including ADA, C or C++ and industry-specific languages critical for their regulated clients managing d…
Solution
Capgemini built 'RAISE for Private Software Engineering', a self-hosted internal software engineering assistant, and switched its underlying model from a previous open-source LLM to Mistral's Codestral without changing existing IDE or CI/CD integrations. Capgemini also invested in deployment methodology and developer coaching to drive adoption, and is now expanding to the full Mistral Code solution, including Codestral Embed and Devstral, for enhanced RAG and CI/CD integration.
…emini France. Codestral delivers the breakthrough needed for developer adoption Capgemini's transformation came when they transitioned from their previous open-source LLM to Mistral's Codestral in their self-hosted coding assistant solution. The switch required no changes to their existing infrastructure—they simply rep…
…uld work more efficiently across their entire portfolio of client technologies. Beyond the technical capabilities, Capgemini invested also in deployment methodology and developer coaching to ensure successful adoption after the first impressions were positive. Why Mistral? Capgemini selected Mistral models for their: Self-hosted deploymen…
…prompted Capgemini to expand their AI strategy beyond basic coding assistance. They're now deploying the full Mistral Code solution, including Codestral Embed and Devstral for enhanced RAG capabilities and CI/CD integration. Future applications include business requirements capture, automated test plan…
Business value
Code completion accuracy jumped from 50% to 90%, developer adoption rose from 30% to 100% across all client projects, and more than 50 client projects reported productivity improvements in less than 6 months.
…placed the underlying model while maintaining other IDE and CI/CD integrations. Accuracy jumped from 50% to 90%, which proved to be transformational for the developers experience. "It's the difference you experience, as a developer, when the first answer is g…
…nt value and business transformation The results were immediate and impressive. Developer adoption jumped from 30% to 100%, with all approximately 50 client projects reporting productivity savings. "From one day to another all the projects went green," describes the transforma…
AI capabilities
Generative AI
…ing capabilities through “RAISE for Private Software Engineering” (aka SovBox), an internal software engineering assistant powered by Mistral. Serving regulated clients in aerospace, defense, and public sectors who requir…
Business functions
IT & Software Engineering
…nt value and business transformation The results were immediate and impressive. Developer adoption jumped from 30% to 100%, with all approximately 50 client projects reporting productivity savings. "Fro…
Technology
Mistral Codestral, Mistral Code, Codestral Embed, Devstral
…through needed for developer adoption Capgemini's transformation came when they transitioned from their previous open-source LLM to Mistral's Codestral in their self-hosted coding assistant solution. The switch required no changes…
…prompted Capgemini to expand their AI strategy beyond basic coding assistance. They're now deploying the full Mistral Code solution, including Codestral Embed and Devstral for enhanced RAG capabilities and CI/CD integration. Future applications include business requirements capture, automated test plan…
Deployment model
on-premise
…ssions were positive. Why Mistral? Capgemini selected Mistral models for their: Self-hosted deployment capabilities that satisfy strict data-privacy and compliance mandates for regulated clients. Superior accuracy across both modern and legacy programming languages, driving…
Deployment options
On-premise
…ssions were positive. Why Mistral? Capgemini selected Mistral models for their: Self-hosted deployment capabilities that satisfy strict data-privacy and compliance mandates for regulated clients. Superior accuracy across both modern and legacy programming languages, driving…
Headline outcome
…productivity gains while maintaining data sovereignty for regulated industries. 100% developer adoption rate across all client projects 90% code completion accuracy vs. 50% with previous solutions 50+ client project…
Use case type
Software engineering assistance
…ing capabilities through “RAISE for Private Software Engineering” (aka SovBox), an internal software engineering assistant powered by Mistral. Serving regulated clients in aerospace, defense, and public sectors who requir…
