Skip to main content
MeshAI’s governance engine lets you define, enforce, and audit rules across every AI agent in your organization. It covers five areas:

Policies

Eight policy types, with enforcement that varies by type - some block inline at the proxy, others are recorded as evidence. Block models, cap budgets, require approval, and more.

HITL Approvals

Human-in-the-loop workflow. The proxy blocks requests that require approval and queues them for your team to review.

Risk Classification

EU AI Act risk levels (minimal, limited, high, unacceptable) assigned to each agent. AI-assisted suggestions available.

Audit Trail

Immutable log of every governance action. Filter, search, and export for compliance audits.

​
How It Works

Governance enforcement happens at two layers:
  1. Proxy layer - model_allowlist, block_provider, and require_approval policies are evaluated inline on every LLM request and can block it with a 403. budget_limit and rate_limit are enforced separately at the proxy-key/team level (429). Prompt injection scanning is always-on, independent of policies. See Enforcement model for the full picture, including policy types that are evidence-only today.
  2. API layer - registration, classification, and administrative actions go through the API directly; they are not policy-gated by the proxy.

​
Quick Start

1

Register your agents

Use the SDK or API to register agents with framework, model, and environment metadata.
2

Classify risk

Assign an EU AI Act risk level to each agent. Use the AI-assisted suggestion endpoint for guidance.
3

Create policies

Define policies - model allowlists, budget limits, approval requirements - scoped globally or per-agent.
4

Monitor the audit trail

Every action is recorded in the audit trail. Export events for compliance reporting.
5

Check readiness

Use the readiness score to measure your organization’s EU AI Act compliance posture.

​
EU AI Act Compliance

MeshAI maps directly to EU AI Act requirements. See the dedicated pages:

EU AI Act Coverage

Article-by-article mapping of what MeshAI covers.

FRIA

Fundamental Rights Impact Assessments (Article 27).

Incident Reporting

Serious incident reporting per Article 73.

Readiness Score

7-component compliance score (0–120).