Agent Fabric Context Catalog and the Future of AI Governance
Summary
Salesforce integrates Agent Fabric with Informatica’s Cloud Data Governance & Catalog to create a unified governance control plane that provides end-to-end visibility across AI agents, MCP infrastructure, APIs, execution traces, and enterprise data. This approach addresses the challenge of tracking dynamic runtime API calls and their data lineage, something traditional governance tools struggle with. With capabilities like deterministic lineage from MuleSoft runtime data, confidence scoring for inferred relationships, and human-in-the-loop validation, teams can trust and monitor autonomous AI workflows continuously. Salesforce teams can leverage this framework to ensure compliance, data quality, and governance visibility when building agent-driven automations and integrations.
Takeaways
- Integrate Agent Fabric with Informatica CDGC for end-to-end AI governance visibility.
- Use MuleSoft runtime data to establish deterministic lineage between APIs and datasets.
- Apply confidence scoring and human reviews to validate inferred lineage relationships.
- Monitor AI agent execution paths continuously to detect governance and policy violations.
- Leverage governance metadata early in development to improve agent workflow trustworthiness.
Modern agents no longer execute within predictable application boundaries. They invoke APIs dynamically, retrieve enterprise context through MCP servers, orchestrate workflows across multiple platforms and interact with structured and unstructured data sources in real time. As these systems become more autonomous, organizations lose visibility into what data influenced an outcome, what systems were touched during execution and whether governance policies were enforced consistently. Traditional data governance platforms were designed around deterministic pipelines, scheduled ETL jobs and relatively stable application architectures. But agentic systems behave differently. Runtime execution paths change continuously based on prompts, retrieved context, orchestration logic and tool selection. The result is a growing governance gap between enterprise AI execution and enterprise observability.