Catalogue › Data Governance

CopilotForge - Data Governance

Use it in Copilot Cowork: download the Data Governance plugin for Copilot Cowork and upload it under Customize > Plugins > Upload plugin. How to install.

Ensure the data used by AI is appropriately owned, classified, accessible, lawful and of sufficient quality.

Layer: assurance
Lead role: Data Governance Lead
Plugin name: copilotforge-data-governance

Skill Status Lifecycle Description

ai-data-access-model draft Mobilise, Enable, Deliver, Scale Defines the organisation-wide model for how AI reaches data - when access must be user-delegated, when an agent or service identity may act, which identity patterns each data class allows, who approves access, and how it is reviewed - so every solution starts from approved patterns. Use when agents need data beyond the user's own access, when makers keep inventing access patterns, or when data owners ask what AI may reach.

ai-data-inventory draft Discover, Mobilise, Deliver, Scale, Improve Builds and maintains an inventory of the data assets AI solutions use and create - databases, Dataverse tables, Fabric items, lists, files, connector data and AI-generated records - with owner, purpose, sensitivity, location and the solutions that depend on each. Use when nobody can say which data feeds which agent, before a data source changes or is retired, or when an audit or rights request needs to know where data flows.

ai-data-lineage draft Deliver, Assure, Improve Traces how data travels from systems of record into AI outputs - copies, indexes, embeddings, prompts, tool calls and generated records - so the organisation can say where an answer came from, which solutions a source change affects, and where personal data has spread. Use when a tier 3 or 4 solution needs explainable provenance, when a source changes or is withdrawn, or when a rights request or incident needs the full path.

ai-data-quality draft Envision, Deliver, Assure, Improve Sets data quality requirements for structured and operational data used by AI - accuracy, completeness, currency, consistency, uniqueness and meaning - with thresholds by use and risk tier, ways to measure them, owners and remediation, so agents and analytics do not confidently repeat bad data. Use when an agent reads business records, when Copilot analyses tables or semantic models, or when AI answers trace back to wrong data.

ai-data-retention-rules draft Mobilise, Enable, Deliver, Scale, Improve Sets the organisation's retention rules for data AI creates or depends on - prompts and responses, transcripts, traces, generated documents, write-backs, indexes and embeddings, agent memory and evaluation sets - aligned to the records schedule, with owners and deletion that reaches every copy. Use when no rule covers AI interactions, when records or legal teams ask how long AI data is kept, or before switching on transcripts or memory at scale.

data-classification-for-ai draft Mobilise, Enable, Deliver, Scale Defines how the organisation's classification scheme and sensitivity labels govern AI - which classes may ground AI, be typed into prompts, reach which models or external services, or train and tune models - plus how labels carry into AI outputs and how unlabelled data is treated. Use when there is no rule for which data AI may use, when labels exist but ignore AI, or before broad Copilot or agent rollout.

data-product-readiness draft Envision, Deliver, Assure Assesses whether a data product - a curated, owned dataset, table set or semantic model - is ready for AI to consume, checking ownership, descriptions and business meaning, quality, classification, access, lineage, refresh and change commitments, and records a ready, ready-with-conditions or not-ready verdict. Use when an agent, Copilot analysis or Foundry solution will read structured business data, or when a data team must make data AI-ready.

Skill	Status	Lifecycle	Description
`ai-data-access-model`	draft	Mobilise, Enable, Deliver, Scale	Defines the organisation-wide model for how AI reaches data - when access must be user-delegated, when an agent or service identity may act, which identity patterns each data class allows, who approves access, and how it is reviewed - so every solution starts from approved patterns. Use when agents need data beyond the user's own access, when makers keep inventing access patterns, or when data owners ask what AI may reach.
`ai-data-inventory`	draft	Discover, Mobilise, Deliver, Scale, Improve	Builds and maintains an inventory of the data assets AI solutions use and create - databases, Dataverse tables, Fabric items, lists, files, connector data and AI-generated records - with owner, purpose, sensitivity, location and the solutions that depend on each. Use when nobody can say which data feeds which agent, before a data source changes or is retired, or when an audit or rights request needs to know where data flows.
`ai-data-lineage`	draft	Deliver, Assure, Improve	Traces how data travels from systems of record into AI outputs - copies, indexes, embeddings, prompts, tool calls and generated records - so the organisation can say where an answer came from, which solutions a source change affects, and where personal data has spread. Use when a tier 3 or 4 solution needs explainable provenance, when a source changes or is withdrawn, or when a rights request or incident needs the full path.
`ai-data-quality`	draft	Envision, Deliver, Assure, Improve	Sets data quality requirements for structured and operational data used by AI - accuracy, completeness, currency, consistency, uniqueness and meaning - with thresholds by use and risk tier, ways to measure them, owners and remediation, so agents and analytics do not confidently repeat bad data. Use when an agent reads business records, when Copilot analyses tables or semantic models, or when AI answers trace back to wrong data.
`ai-data-retention-rules`	draft	Mobilise, Enable, Deliver, Scale, Improve	Sets the organisation's retention rules for data AI creates or depends on - prompts and responses, transcripts, traces, generated documents, write-backs, indexes and embeddings, agent memory and evaluation sets - aligned to the records schedule, with owners and deletion that reaches every copy. Use when no rule covers AI interactions, when records or legal teams ask how long AI data is kept, or before switching on transcripts or memory at scale.
`data-classification-for-ai`	draft	Mobilise, Enable, Deliver, Scale	Defines how the organisation's classification scheme and sensitivity labels govern AI - which classes may ground AI, be typed into prompts, reach which models or external services, or train and tune models - plus how labels carry into AI outputs and how unlabelled data is treated. Use when there is no rule for which data AI may use, when labels exist but ignore AI, or before broad Copilot or agent rollout.
`data-product-readiness`	draft	Envision, Deliver, Assure	Assesses whether a data product - a curated, owned dataset, table set or semantic model - is ready for AI to consume, checking ownership, descriptions and business meaning, quality, classification, access, lineage, refresh and change commitments, and records a ready, ready-with-conditions or not-ready verdict. Use when an agent, Copilot analysis or Foundry solution will read structured business data, or when a data team must make data AI-ready.

Credit

Created by Simon Foote as part of CopilotForge. Content is licensed under CC BY 4.0; keep the credit in each skill's license and authors fields when you share or adapt it. See NOTICE.md in the repository.