Mistral Builds Autonomous Rails Test-Writing Agent Using Vibe Coding Assistant
Mistral's Applied AI Proto team built an autonomous agent that reads Ruby on Rails source files and generates or improves RSpec tests with no human intervention, running in parallel across large codebases inside CI/CD pipelines. The agent is built on Vibe, Mistral's open-source coding assistant, and uses context engineering via AGENTS.md files, per-file-type skill files, and custom tools for linting and coverage validation. Key techniques include forced self-review prompts, specialized skill files per Rails file category, and careful handling of shared RSpec factories. The approach improved a quality score from 0.68 to 0.74 through structured prompt engineering alone.
Related guides (3)
Related events (8)
Mistral Vibe 2.0: Terminal-Native Coding Agent with Custom Subagents and Devstral 2
Mistral AI has released Mistral Vibe 2.0, a major upgrade to its terminal-native coding agent, powered by the new Devstral 2 model family. Key additions include custom subagents for specialized tasks, multi-choice clarifications before execution, slash-command skills for preconfigured workflows, and unified agent modes. The product is available on Le Chat Pro and Team plans with pay-as-you-go credits, while Devstral 2 moves to paid API access at $0.40/M input and $2.00/M output tokens. Enterprise add-ons include fine-tuning on internal DSLs, reinforcement learning with custom environments, and end-to-end codebase modernization.
Mistral AI Launches Agents API with Built-in Connectors, MCP Tools, and Persistent Memory
Mistral AI has released a dedicated Agents API that extends beyond chat completion by providing built-in connectors for code execution, web search, image generation, and document retrieval, alongside support for Model Context Protocol (MCP) tools. The API features stateful conversation management with branching, streaming output, and multi-agent orchestration capabilities. Benchmark results show substantial web search augmentation gains: Mistral Large jumps from 23% to 75% on SimpleQA, and Mistral Medium from 22% to 82% with search enabled. The release targets enterprise-grade agentic workflows and is accompanied by cookbooks covering GitHub coding assistants, financial analysis, and travel planning use cases.
Mistral AI Launches Mistral Code: Enterprise AI Coding Assistant with On-Prem Deployment
Mistral AI has announced Mistral Code, an enterprise-grade AI coding assistant currently in private beta for JetBrains IDEs and VSCode. The product bundles four specialized models (Codestral, Codestral Embed, Devstral, Mistral Medium) with an IDE plugin, admin controls, and deployment options ranging from serverless to air-gapped on-premises GPUs. It is built on a fork of the open-source Continue project with enterprise additions including RBAC, audit logging, and fine-tuning on private repositories. Early enterprise adopters include Abanca, SNCF (4,000 developers), and Capgemini (1,500+ developers).
Mistral Rebrands Le Chat as Vibe: Unified Agentic Platform for Work and Code
Mistral AI has rebranded its Le Chat product as Vibe, repositioning it as a unified agentic platform covering long-running work tasks and autonomous coding. Work Mode supports multi-step enterprise workflows with integrations across Google Workspace, Outlook, Slack, GitHub, and custom connectors, while Code Mode launches remote coding agents that can open pull requests and run in isolated sandboxes. A new VS Code extension and CLI updates extend the coding agent into developer environments. Pricing tiers range from free to $24.99/user/month for teams, with enterprise options available.
Mistral AI Releases Devstral: Apache 2.0 Agentic Coding Model with SWE-Bench SOTA
Mistral AI, in collaboration with All Hands AI, releases Devstral, an agentic LLM specialized for software engineering tasks under the Apache 2.0 license. The model achieves 46.8% on SWE-Bench Verified, surpassing prior open-source state-of-the-art by over 6 percentage points and outperforming larger models like DeepSeek-V3-0324 (671B) and Qwen3 232B-A22B under the same OpenHands scaffold. Devstral is small enough to run on a single RTX 4090 or a Mac with 32GB RAM, and is available via Mistral's API at $0.1/M input tokens, as well as on HuggingFace, Ollama, and other platforms. Mistral indicates a larger agentic coding model is in development.
Mistral Launches Medium 3.5 (128B Open Weights), Remote Cloud Coding Agents in Vibe, and Work Mode in Le Chat
Mistral AI has released Mistral Medium 3.5, a 128B dense open-weights model with a 256k context window, configurable reasoning effort, and a vision encoder trained from scratch, scoring 77.6% on SWE-Bench Verified. Alongside the model, Mistral is launching remote cloud-based coding agents in its Vibe CLI and Le Chat interface, enabling async parallel coding sessions that run independently and notify users on completion. A new Work mode in Le Chat provides a multi-step agentic interface for cross-tool workflows including email, calendar, research, and issue tracking. Mistral Medium 3.5 replaces Devstral 2 as the default model in both Le Chat and the Vibe CLI, and is available for self-hosting on as few as four GPUs under a modified MIT license.
Mistral Releases Devstral 2 (123B) and Devstral Small 2 (24B) Coding Models Plus Vibe CLI Agent
Mistral AI has released Devstral 2, a 123B-parameter open-weight coding model scoring 72.2% on SWE-bench Verified, and Devstral Small 2, a 24B model scoring 68.0% on the same benchmark and deployable on consumer hardware. Both models support a 256K context window and are permissively licensed (modified MIT and Apache 2.0 respectively). Mistral also launched Vibe CLI, an open-source terminal-based coding agent powered by Devstral that supports multi-file orchestration, natural language code editing, and IDE integration via Agent Communication Protocol. Devstral 2 is currently free via API with post-free pricing of $0.40/$2.00 per million tokens input/output.
Mistral AI Demonstrates Agentic Workflow for Meeting-to-Dev-Ticket Automation
Mistral AI has published a solution blog describing a multi-agent workflow called TranscriptToPRDTicket that converts meeting transcripts into Product Requirements Documents and engineering tickets using two specialized agents (PRDAgent and TicketCreationAgent) both powered by Mistral Large 2. The pipeline integrates with project management tools such as Linear and Jira, and a full implementation is provided via a Google Colab notebook. The post is primarily a deployment-pattern showcase rather than a new model or capability announcement.