Disablement and incident response: AI Agents / MCP

Source: deck slide 17 · WPP Pilot assessment | Risks #9, #14, #20

Legend: Today = Wrike capability | Confirm = setup/evidence | Pilot = proposed control. See the overview for all labels.

#9 Operational Support#

Unclear ownership prolongs incidents.

Wrike AI Agents

• Today: A native agent can be disabled individually.
• Pilot: Name the person who can disable it and the person responsible for recovery.

Wrike MCP

• Confirm: how to stop the assistant or middleware connection and revoke access tokens. Name an operator who can carry out those steps.

#14 Reputation & Client Trust#

AI incidents reduce trust.

Wrike AI Agents

• Pilot: Agree who investigates, escalates, restores service and communicates with WPP if an agent causes an incident.

Wrike MCP

• Pilot: Agree how teams coordinate an incident spanning the assistant, middleware and Wrike, including who updates WPP and any affected stakeholders.

#20 Autonomous Actions#

Damaging actions continue unchecked.

Wrike AI Agents

• Pilot: Taskforce reviews the AI Agents performance and details what/if any further in-product requirements they have for Wrike.

Wrike MCP

• Pilot: Taskforce reviews the actions done via MCP and its performance and details what/if any further in-product requirements they have for Wrike.

Discussion log#