Tutorials¶
50+ step-by-step guides covering every aspect of AI agent governance.
Where to start?
New here? Start with Tutorial 01: Policy Engine, then work through the Foundations section. For a quick taste, try Tutorial 36: 2-Line Governance.
Foundations¶
| # | Tutorial | What you'll learn |
|---|---|---|
| 01 | Policy Engine | Core policy evaluation, rule authoring |
| 02 | Trust & Identity | Agent identity, trust tiers, verification |
| 03 | Framework Integrations | Connect AGT to LangChain, CrewAI, OpenAI, etc. |
| 04 | Audit & Compliance | Logging, evidence collection, compliance mapping |
| 05 | Agent Reliability | SLOs, monitoring, graceful degradation |
| 36 | 2-Line Governance Quickstart | Fastest path to governed agents |
Security¶
| # | Tutorial | What you'll learn |
|---|---|---|
| 06 | Execution Sandboxing | Privilege rings, runtime isolation |
| 07 | MCP Security Gateway | Per-tool policy enforcement for MCP servers |
| 08 | OPA / Rego / Cedar Policies | Policy engines comparison and integration |
| 09 | Prompt Injection Detection | Detecting and preventing prompt injection |
| 25 | Security Hardening | Production security best practices |
| 26 | SBOM & Signing | Software bill of materials, artifact signing |
| 27 | MCP Scan CLI | Static analysis for MCP server security |
| 39 | DLP with Attribute Ratchets | Data loss prevention, sensitivity escalation |
| 41 | Defense-in-Depth | Advisory classifiers, layered security |
| 45 | Shift-Left Governance | Pre-commit hooks, CI gates, build-time enforcement |
| 46 | Contributor Governance | Contributor reputation, spam detection, cross-project scanning |
| 47 | Red-Team Testing | Adversarial security testing with agt red-team |
Advanced Patterns¶
| # | Tutorial | What you'll learn |
|---|---|---|
| 10 | Plugin Marketplace | Marketplace governance, trust scoring |
| 11 | Saga Orchestration | Multi-step agent workflows with rollback |
| 12 | Liability & Attribution | Decision tracing, blame assignment |
| 13 | Observability & Tracing | Distributed tracing for agent systems |
| 14 | Kill Switch & Rate Limiting | Emergency controls, throttling |
| 15 | RL Training Governance | Governing reinforcement learning agents |
| 16 | Protocol Bridges | Cross-protocol agent communication |
| 17 | Advanced Trust | Behavioral analysis, reputation systems |
| 18 | Compliance Verification | Automated compliance checks |
| 23 | Delegation Chains | Agent-to-agent authorization |
| 24 | Cost & Token Budgets | Resource governance |
| 35 | Policy Composition | Enterprise governance layers, policy merging |
| 37 | Multi-Stage Pipeline | Chained policy evaluation pipelines |
| 38 | Approval Workflows | Human-in-the-loop approval gates |
| 40 | OpenTelemetry Observability | OTel integration for governance events |
| 44 | A2A Conversation Policy | Agent-to-agent conversation governance |
| 48 | Intent-Based Authorization | Authorize actions by declared intent |
| 49 | Multi-Agent Policies | Collective policy enforcement across agent fleets |
| 50 | Decision BOM | Decision bill of materials, audit artifacts |
| 51 | Cost Governance | Budget enforcement, cost attribution |
Language Package Guides¶
| # | Tutorial | What you'll learn |
|---|---|---|
| 19 | .NET package | Agent governance in C# / .NET |
| 42 | C# MCP extension | Govern MCP servers built with the official C# SDK |
| 43 | .NET MAF Hook | Integrate AGT with Microsoft Agent Framework in .NET |
| 20 | TypeScript package | Agent governance in TypeScript |
| 21 | Rust crate | Agent governance in Rust |
| 22 | Go module | Agent governance in Go |
Enterprise & Operations¶
| # | Tutorial | What you'll learn |
|---|---|---|
| 28 | Build Custom Integration | Create your own governance adapter |
| 29 | Agent Discovery | Finding shadow AI in your organization |
| 30 | Agent Lifecycle | Agent lifecycle management, birth to retirement |
| 31 | Entra Agent ID Bridge | Bridging AGT identity with Microsoft Entra |
| 32 | Chaos Testing | Chaos engineering for agent reliability |
| 32b | E2E Encrypted Messaging | End-to-end encrypted agent communication |
| 33 | Offline Verifiable Receipts | Offline-verifiable decision receipts |
| 34 | MAF Integration | Governing agents with Microsoft Agent Framework |
Policy-as-Code Series¶
A focused series on writing, testing, and versioning governance policies.
| # | Tutorial | What you'll learn |
|---|---|---|
| 1 | Your First Policy | Write and evaluate a basic policy |
| 2 | Capability Scoping | Restrict agent tool access |
| 3 | Rate Limiting | Token and request budgets |
| 4 | Conditional Policies | Context-aware policy rules |
| 5 | Approval Workflows | Human approval gates |
| 6 | Policy Testing | Unit testing policies |
| 7 | Policy Versioning | Version control for policies |
| - | MCP Governance | MCP-specific policy patterns |
Guides¶
| Guide | What you'll learn |
|---|---|
| Progressive Governance | Start simple, add governance layers incrementally |
| Retrofit Governance | Add governance to an existing agent |