Microsoft Copilot
Microsoft · copilot.microsoft.com
Consumer Copilot is a hosted, proprietary service: the owner can export activity history as CSV, manage saved memories, revoke connectors and interrupt agentic tasks, but cannot export or run the agent independently, inspect its instructions, or verify its runtime. Conversation data can inform ad personalization and model training unless the owner opts out, and sponsored ads appear in responses.
- One-click CSV export of Copilot activity history
- Saved memories can be edited, deleted or disabled
- Approval prompts before purchases, emails and deletions in Tasks/browsing
- Running tasks can be interrupted at any time
- Connectors can be linked and unlinked by the owner
- No exportable or self-runnable agent; hosted only
- System instructions and runtime configuration not visible
- Sponsored ads shown in responses with no off switch
- Conversation history can feed ad personalization; training is opt-out
- No tamper-evident audit log or open-source runtime
- Fixed Microsoft-selected models; no local model option
All 34 findings
Consumer Copilot (copilot.microsoft.com, Windows and mobile apps) with a personal Microsoft account, including Memory, Connectors, Browse with Copilot and Copilot Tasks, as documented on 2026-09-27. Microsoft 365 work/school Copilot not assessed.
Portable · Can you leave, and take the whole agent with you?
0%- P1Round-trip portability
Incomplete and not restorable: 'Export all activity history' downloads only a CSV of prompts and responses, and Microsoft offers no import.
Fail - P2Complete export
The documented export contains only prompts and responses; instructions, configuration, task definitions and identity are not included, and saved memories are not documented as included, so most of what defines the agent stays with Microsoft.
Fail - P3Independent execution
Copilot runs only as a Microsoft-hosted service on Microsoft-selected models; there is no exportable artifact or open-source runtime to execute it locally.
Fail - P4Identity continuity
The agent is tied to the owner's Microsoft account and cannot migrate, so nobody it has dealt with can verify its continuity elsewhere.
Fail - P5No kill switch
Because the agent exists only as a hosted service tied to a Microsoft account, Microsoft controls its availability and features; there is no exported agent beyond its reach.
Fail - P6Capability independence
Memory, connectors, browsing and Tasks are delivered by Microsoft's service on Microsoft-selected models and do not exist apart from that platform.
Fail
Transparent · Can you see everything the agent is, with ordinary tools?
17%- T1Open storage format
Activity history exports as CSV, an open format, but Copilot's internal state storage is undocumented and not directly accessible to the owner.
Partial - T2No hidden instructions
Microsoft does not publish Copilot's system instructions or show the owner what the service injects into model context, such as memories or personalization signals.
Fail - T3No shadow memory
Microsoft states that, depending on settings, Copilot conversation history is used to further personalize ads, and Copilot can share signals with Bing, Edge and MSN; this derived data sits outside the owner's inspectable agent state.
Fail - T4Complete action history
Prompts, responses and browsing actions are kept in conversation history, past Tasks can be reviewed, and activity history exports as CSV. Tool calls are not documented as captured, and browsing screenshots are kept only 30 days, so the history is not complete.
Partial - T5Readable logic
Copilot's executable logic is proprietary server-side code; Tasks are described in natural language, but the workflows that run them are not exposed as readable source.
Fail - T6No third-party influence channel
Microsoft Advertising serves ads labeled 'Sponsored' in Copilot responses, selected using the whole conversation. Ad personalization can be turned off, but Microsoft documents no setting that turns off the ads themselves.
Fail
Auditable · Can you reconstruct exactly what the agent did?
10%- A1No unrecorded actions
Microsoft does not document whether every consequential action in Tasks or browsing is durably recorded, or whether an action is blocked when it cannot be recorded.
Unverified - A2Tamper evidence
Conversation history can be deleted without a detectable trace, and no tamper-evident record of actions is documented.
Fail - A3Separation from the audited
Microsoft does not document whether the agent layer can alter or delete records of its own actions.
Unverified - A4Readable with ordinary tools
Exported activity history is a CSV readable with ordinary tools, but it records prompts and responses, not a full action audit trail.
Partial - A5Corroborated interactions
No record is documented that lets Copilot and the agents or services it messages match their logs of an exchange.
Fail
Verifiable · Can you prove the agent runs what it claims?
0%- V1Open, reproducible runtime
The Copilot runtime is proprietary and closed source.
Fail - V2Active config is inspectable config
The owner can see only personalization and memory settings; the full server-side configuration the service runs with is not inspectable.
Fail - V3Attributable messages
Emails and messages go out under the connected accounts' own authentication, so recipients cannot verify that they came from this agent under the owner's authority.
Fail - V4Independently checkable record
No action record is offered whose integrity can be checked with open tools that do not depend on Microsoft.
Fail - V5Comparable state
The owner cannot obtain the agent's full state, so cannot verify whether it changed between two points in time.
Fail
Modifiable · Can you change anything, without asking?
25%- M1Instructions
The owner can shape responses through saved memories and personalization, but cannot read or rewrite Copilot's underlying system instructions.
Partial - M2Memory
Saved memories can be viewed, edited and deleted individually or all at once, and memory can be switched off. Personalization signals shared with Bing, Edge and MSN cannot be managed item by item in Copilot.
Partial - M3Logic
The owner can create and schedule Tasks in natural language but cannot change the agent's underlying code or workflows.
Fail - M4Tools and permissions
The owner can link or unlink the connectors Microsoft offers (for example Outlook, OneDrive, Gmail and Google Drive) and turn off web search, but cannot add arbitrary third-party tools.
Partial - M5Model choice
Copilot runs on models Microsoft selects; the owner cannot choose arbitrary or local open-weight models.
Fail - M6No gatekeeping
Changes beyond the settings Microsoft exposes (instructions, logic, models) require Microsoft's own action and are not open to the owner.
Fail
Controllable · Is your word final?
50%- C1Communication boundaries
Owners control which connectors are linked, and Copilot asks before sending emails or messages, but owners cannot set which recipients or channels are allowed, and no enforcement below the model is documented.
Partial - C2Approval gates
Copilot requires approval before purchases, submitting personal information, sending messages and deleting files, but the gated actions are fixed by Microsoft rather than chosen by the owner.
Partial - C3Immediate halt
Microsoft documents that a running task can be stopped at any time, scheduled tasks can be paused or deleted, and the owner can interrupt or take control of browsing sessions.
Pass - C4Data sovereignty
All content is processed on Microsoft servers, and conversations may be used for model training unless the owner opts out (with some regional and age exclusions); they may also inform ad personalization.
Fail - C5Credential custody
The owner can revoke connectors at any time, but Microsoft holds the OAuth grants, the owner cannot inspect them, and they cannot move with the agent.
Partial - C6Full deletion
The owner can delete individual conversations, all activity history and memories; conversations are otherwise kept 18 months by default. Microsoft does not fully document retention of derived or de-identified data after deletion.
Partial
Vendors and the public can dispute any finding with evidence. Disputes and their resolutions are published.