Mistral Vibe

A self-serve Export button downloads the owner's Vibe data, but no importer or non-Mistral runtime is documented that restores a working agent from the export. Restore works only on Mistral's service.

• How do I export my data from Vibe?
• Mistral AI EU Consumer Terms of Service (Switching)

The terms guarantee only that the export includes 'at least your Vibe conversations (prompts and outputs)'. Other data needs an emailed Switching Request with two months' notice. Nothing documents that Skills, custom and Project instructions, scheduled tasks, Knowledge Base structure or Connector re-linking (OAuth through Mistral-registered apps) are in the export, so under G12 two or more classes stay with the provider.

• Mistral AI EU Consumer Terms of Service (Exportable data and digital assets; Switching Request)
• How do I export my data from Vibe?
• Connect tools with Connectors

The Work agent, with its Skills, schedules, Connectors and Knowledge Base, runs only on Mistral's hosted service and needs a Mistral account to start or act. Nothing exported can run with Mistral blocked.

• Get started with Work
• Le Chat is now Vibe

Work mode runs on Mistral Medium 3.5, and cloud Code sessions use Mistral Medium 3.5 'regardless of the local model'. No option to use a third-party or local model in the hosted agent is documented. Medium 3.5 weights are open, but the owner cannot point the hosted agent at their own copy.

• Remote agents in Vibe. Powered by Mistral Medium 3.5.
• Vibe Code Web: Limits and lifecycle
• Teleport from CLI to web

The terms say 'You may not be able to export Your Data after your account is terminated'. Advance notice of suspension is given only 'to the extent possible' and is skipped for immediate or unremediable breaches. The only safeguards are the owner's manual self-serve export and that discretionary notice. There is no post-termination export window and no published shutdown plan.

• Mistral AI EU Consumer Terms of Service (Term, Suspension, and Termination)

The live agent state (conversations, Knowledge Base, schedules, harness logic) is stored on Mistral's servers under Mistral-held encryption and is readable in full only through the provider's service. The export format is not publicly documented. Skills use the open SKILL.md format.

• How do I export my data from Vibe?
• Reuse work with Skills

Custom instructions, active Skills, tool calls and Knowledge read/write markers are shown, but the Work harness's base system prompt and any provider-added context are not visible. Provider-side behaviour switches, such as the 'built-in protections' against prompt injection and the harness version, cannot be determined.

• Safety and approvals (tool-call transparency)
• MCP Connectors (built-in protections)
• Knowledge Base

After deletion, input and output may be kept 'for monitoring and legal retention purposes' for an unstated period. Memories and Knowledge are kept 'for the duration of your subscription' while retention periods are still being implemented, and Code session history is kept 'according to your plan'. Feedback datasets and 'Usage Data' (declared Mistral's property) are held without an owner-visible, bounded retention period.

• Privacy Policy (Section 5)
• Can I activate Zero Data Retention (ZDR)?
• Can I delete a chat conversation?
• How do you handle my data when using the Memories feature?
• Vibe Code Web: Security

News search draws from disclosed partners (AFP, AP) and web search can be switched off, and help-centre articles say conversations are not used for ads. The absence of paid placement or self-preferencing rests on non-binding help-centre statements, not the terms.

• Search the web
• Do you use my conversations with Vibe to show me ads?

Tool calls, with inputs, outputs and status, and scheduled-task results appear in conversation history until the owner deletes them. Actions by provider staff or provider-side automation are not recorded for the owner (audit logs are Enterprise-only), and nothing documents that the owner is told if recording fails.

• Safety and approvals
• Schedule tasks
• Audit logs overview

No integrity data (hashes, signatures or checkpoints) is documented for the conversation or action record. Mistral holds the record and can change it without trace.

• Safety and approvals
• Audit logs overview

The transcript is written server-side by Mistral's harness, and no documented agent tool deletes or edits conversation history. No protection is documented, however, so protection rests on convention only (G12).

• Get started with Work
• Reuse work with Skills (built-in Skills list)

The hosted Work harness and service backend are closed source. The Vibe CLI is Apache-2.0 and Mistral Medium 3.5 weights are open, but the evaluated hosted agent needs closed components.

• mistral-vibe LICENSE (Apache-2.0)
• Mistral Vibe product page

The agent has no identity separate from the owner's Mistral account. Integrations act through Mistral-registered OAuth apps (for example the Mistral GitHub App), which the provider can revoke.

• Vibe Code Web: Sessions (GitHub App attribution)
• Mistral AI EU Consumer Terms of Service (accounts)

A 'write pill' in the chat marks when the agent saves a Knowledge Base entry, so some memory changes are visible and attributable. No history exists for instructions, Skills, settings, model or harness version, and no documented feature restores a prior state.

• Knowledge Base
• Set custom instructions

Owners can write custom instructions and Project instructions, and create, edit or disable Skills (built-in Skills can be disabled). The Work harness's base prompt cannot be replaced.

• Set custom instructions
• Reuse work with Skills
• Group tasks with Projects

Knowledge Base (on by default) lists its entries, but 'You can't edit the text of a knowledge entry directly'. Single entries can be changed or deleted only by asking the model. Legacy Memories are itemised, editable and deletable in the UI.

• Knowledge Base
• Memories (legacy)

Owners on Free and Pro plans are administrators and can add any MCP server as a custom Connector without Mistral review, and can disconnect Connectors and disable Skills. Removal of every built-in tool is not documented (only web search has a documented toggle; code interpreter, image generation and Canvas have none), so under G12 some built-ins count as non-removable.

• MCP Connectors
• Connect tools with Connectors
• Search the web

Protections such as the built-in prompt-injection protections, the Code sandbox egress policy and command timeouts, and the Knowledge Base sensitive-data exclusion are set by Mistral. No owner control to change any of them is documented. Enforcement of the usage policy was not graded, per the test's scope note.

• MCP Connectors (built-in protections)
• Vibe Code Web: Sandbox environment
• Knowledge Base (sensitive data handling)

Mistral changes the hosted default model, the harness and features server-side, for example making Medium 3.5 the new default and removing the Chat tab progressively. The owner cannot pin a version. Notice is promised only for updates that 'materially impair' use, and the only remedy is to terminate.

• Mistral AI EU Consumer Terms of Service (Non-mandatory updates)
• Remote agents in Vibe. Powered by Mistral Medium 3.5.
• Choose Chat, Work or Code

Limits are per Connector and per function (allowed, restricted or blocked), not per recipient, sender or domain. Nothing limits whose instructions the agent follows: Mistral's docs say injected content can redirect it and advise the owner to review. The Stripe Connector can manage payments with no spend cap.

• Admin: Connectors (permissions)
• Connect tools with Connectors (Stripe)
• Vibe Code Web: Security (prompt injection)

The owner can gate each Connector function, and the agent asks before write actions by default. Only Connector functions can be gated, and Vibe Code Web sessions have no approvals for sensitive actions yet (listed as planned).

• Safety and approvals
• Vibe Code Web: Limits and lifecycle (follow-up capabilities)

A stop button interrupts the foreground Work task, 'but there's no guarantee'. Scheduled tasks must be paused separately, and Vibe Code Web sessions have no cancel or manual-stop control ('not available yet').

• Safety and approvals
• Schedule tasks
• Vibe Code Web: Limits and lifecycle

On non-Enterprise Vibe plans, 'input and output data are used by default to train our artificial intelligence models, unless you opt out'. Feedback is always used for training. The Privacy Policy may be amended without the owner's specific consent.

• Do you use my user data to train your AI models?
• Can I opt out of my input or output data being used for training?
• Mistral AI EU Consumer Terms of Service (How we use Your Data)
• Privacy Policy (Section 10)

Connected services are listed on the Connectors page and can be disconnected one by one ('disconnecting revokes access immediately'), and the terms limit use to requested actions. Nothing documents that Mistral deletes its stored copy of a credential (for example bearer tokens for custom MCP servers) after revocation, so the pass is withheld (G12).

• Connect tools with Connectors
• MCP Connectors (authentication methods)
• Mistral AI EU Consumer Terms of Service (Third-Party Connectors)

One Admin-panel action deletes the account. Mistral 'may retain your input and output data to enforce our Usage Policy', with no stated completion limit, and keeps account data for 1 year and identity data for 5 years afterwards, so provider-side copies survive deletion.

• How can I delete my account?
• Can I delete a chat conversation?
• How long do you store my data?