Purview insider-risk tool that flags messages in email, Teams or Copilot interactions that may be inappropriate or breach regulations so reviewers can respond; DLP policies sit elsewhere.
Also called Microsoft Purview Communication Compliance.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Communication Compliance in context, with comparison tables and the common traps.
Terms in this definition
- Chat message roles
Labels on chat messages: instructions go under system, the person's input under user, the model's previous answers under assistant, and results returned by a called tool under tool (or function).
- Agents (classic) API
First-generation Foundry Agent Service API, based on threads, messages and runs. It is deprecated, replaced by conversations and responses, and retires on 31 March 2027.
- Microsoft Purview Data Loss Prevention
Policies in Purview that look for sensitivity labels or sensitive information types in content held in many places, including Microsoft 365 Copilot, and respond by auditing, warning or blocking. You can simulate a policy before enforcing it.
Related terms
- Adaptive scope
A dynamic way to target Microsoft Purview retention, auto-labelling or communication compliance policies, where a query on attributes such as department selects the users, groups or sites and is re-run every day. A static scope is the fixed alternative.
- FINRA
The Financial Industry Regulatory Authority is an independent American regulator that sets and polices rules for brokers and broker-dealers, such as Rule 4511 on keeping records. Microsoft Purview Communication Compliance can spot messages that may breach its requirements.
- Microsoft Copilot experiences
A location you can pick in retention policies and in Communication Compliance to capture what people ask Microsoft-built Copilots and what those Copilots answer, covering, for example, Copilot Studio, Security Copilot, Copilot in Fabric and Microsoft Copilot. Copilot messages used to fall under the older Teams chats and Copilot interactions location.
- One-click policies
Ready-made policies that Data Security Posture Management sets up from its recommendations, covering DLP, Insider Risk Management, Communication Compliance and collection. Any later changes happen in each policy's own solution.
- Other AI apps
A location in Communication Compliance and retention policies that captures what people do in consumer and third-party AI tools, ChatGPT, Google Gemini and consumer Microsoft Copilot among them. Enterprise AI apps are covered by their own, different location.
- Pseudonymisation
Hiding who someone is by showing a random label, for example ANON2340, in place of their name and other personal details. Microsoft Purview Insider Risk Management and Communication Compliance do this by default for reviewers in their analyst and investigator roles.