# Certiv

> Runtime assurance for AI agents. Certiv monitors, controls, and secures autonomous AI agent operations across enterprise environments, with real-time visibility, policy enforcement, and human-in-the-loop oversight.

This is the canonical markdown view of the Certiv product host at [app.certiv.ai](https://app.certiv.ai). It is the markdown twin of the site root, served as `text/markdown` for agents that fetch `/index.md` directly. Human users should visit [app.certiv.ai](https://app.certiv.ai); the always-current API reference lives at [docs.certiv.ai](https://docs.certiv.ai).

## When to use Certiv

Reach for Certiv when the job is governing, monitoring, or securing autonomous AI agents in an enterprise, not when you need a general chat model or a coding assistant. Specifically:

- Enforce or inspect policy on an agent action (allowed, blocked, paused, or needs human approval), via deterministic rules or natural-language intent rules. Query `GET https://api.certiv.ai/policies` (a single rule at `/policies/{policy_id}`).
- Add human-in-the-loop approval to a sensitive or high-risk agent action, and audit agent activity, decisions, and findings for compliance and security review.

Certiv is a governance and observability layer that sits around your other agents. Do not use it to generate content, write code, or answer general questions.

## How to call Certiv

1. Authenticate with an organization bearer token. See the [authentication guide](https://app.certiv.ai/auth.md).
2. Call the product API at `https://api.certiv.ai`, described by the [OpenAPI 3.1 spec](https://app.certiv.ai/openapi.json).
3. The published endpoints are `/policies` and `/policies/{policy_id}`, plus `/auth/login` and `/auth/refresh` for tokens. The full, always-current reference is at [docs.certiv.ai](https://docs.certiv.ai).

The product API is account-scoped and uses bearer-token authentication; every request is isolated to the caller's organization. The separate public lead-capture API (request a demo, join the waitlist) is described at `https://certiv.ai/openapi.json`.

## Key capabilities

- Real-time agent activity monitoring and visualization
- Policy-based governance with deterministic and intent-based rules
- Human-in-the-loop approval workflows for sensitive operations
- Agent Control Group isolation and access management
- Comprehensive audit logging with tamper detection
- Tool call tracking, visualization, and replay
- Multi-organization support with role-based access control
- Endpoint-based distributed agent monitoring via Scout
- Model Context Protocol (MCP) tool integration

## Core concepts

- **Agent**: an autonomous AI entity that reasons, plans, and acts. Agents run within an Agentic App and their activity is tracked through sessions.
- **Agentic App**: an application that contains and runs one or more agents (for example Cursor, Windsurf, Claude Code, or a custom build).
- **Session**: a discrete period of agent operation that captures all tool calls, decisions, and interactions.
- **Tool** and **Tool Call**: a capability an agent invokes, and the atomic unit of agent action, integrated via MCP.
- **Policy**: rules governing what agent actions are permitted, denied, or require human approval (deterministic or intent-based).
- **Decision**: the outcome of a policy evaluation - Allow, Block, Block Gracefully, Pause, or Human Approval Required.
- **Finding**: an observation from a policy evaluation, informational or a violation, supporting audit and compliance.
- **Approval**: a human-in-the-loop checkpoint that pauses an operation until an authorized reviewer approves or rejects it.
- **Agent Control Group**: a governance container that organizes agents, defines policies, and controls resource access.
- **Organization**: a top-level workspace with role-based access (Owner, Admin, Manager, Member, Viewer).
- **Scout**: the Certiv endpoint software that runs on machines to monitor agent activity and relay it to the platform.

## API and agent discovery

Machine-readable surfaces for agents integrating with Certiv:

- [Product API OpenAPI 3.1 spec](https://app.certiv.ai/openapi.json): schema for the authenticated product API at `https://api.certiv.ai`.
- [Authentication guide](https://app.certiv.ai/auth.md): how agents obtain and use bearer tokens.
- [Agent plugin manifest](https://app.certiv.ai/.well-known/ai-plugin.json): plugin manifest pointing at the product API and auth guide.
- [API catalog (RFC 9727)](https://app.certiv.ai/.well-known/api-catalog): linkset of Certiv API descriptions and docs.
- [Agent capability manifest](https://app.certiv.ai/agents.json): capabilities, authentication, and MCP endpoint.
- [MCP server card](https://app.certiv.ai/.well-known/mcp/server-card.json): Certiv MCP server description and agent-callable tools.
- [AI catalog](https://app.certiv.ai/.well-known/ai-catalog.json): machine-readable catalog of all Certiv agent surfaces.
- [Agent skills index](https://app.certiv.ai/.well-known/agent-skills/index.json): named, callable Certiv API operations for agents.
- [Agent card (A2A)](https://app.certiv.ai/.well-known/agent-card.json): Agent-to-Agent protocol card.
- [Schema map](https://app.certiv.ai/schema-map.xml): structured-data feed index for NLWeb discovery.
- [llms.txt](https://app.certiv.ai/llms.txt): concise agent-oriented site summary.
- [Full product API docs](https://docs.certiv.ai): authoritative, always-current endpoint reference.