Insights
Curated reading for enterprise agentic AI.
A short, executive‑friendly list of high‑signal references we use for architecture, governance, evaluation, and security.
Standards & Governance
- NIST AI RMF Risk management for AI systems
- FDA AI/ML-enabled medical devices Regulatory considerations
- GMLP (FDA + partners) Guiding principles
- OWASP LLM Top 10 Security risks & mitigations
Agent Frameworks & Patterns
- Model Context Protocol (MCP) Standardized tool and context connections
- LangGraph Stateful, multi‑step agent workflows
- Microsoft AutoGen Multi‑agent orchestration
- OpenTelemetry Traces/metrics/logs for observability
Cloud AI Platforms
- AWS Bedrock Agents Managed agents on AWS
- Microsoft Azure AI Enterprise AI services & governance
- Google Vertex AI Models, retrieval, and app tooling
- Databricks Generative AI LLMOps, governance, and deployment
How Eduric uses this
- Architecture: tool‑calling with policy boundaries and verification loops
- Evaluation: gold sets, regression, red‑team, and runtime monitoring
- Governance: identity, approvals, audit, and data minimization
- Adoption: change plan and workflow‑level KPIs