# Certiv

> Probe-verified (tier 2 of 3). Last checked 2026-08-23. 4 of 5 capability checks passed.

- host: certiv.ai
- url: https://certiv.ai/
- category: ai agent security platform
- type: saas
- language: en

## Probe-verified · tier 2 of 3

Probed live on 2026-08-23 against rubric v1. 4 of 5 checks passed.

- PASS — Markdown negotiation
- PASS — Markdown twin at a predictable URL
- PASS — llms.txt
- PASS — API catalog
- fail — MCP server answers

## Unverified actions

Read from the page's own content, with the wording each was drawn from. Inference is kept separate from tested facts; an agent completing the action is tier 3.

- **read** — "Product overview: Complete visibility and control over the agentic workforce" → `https://certiv.ai/product/`
- **read** — "Runtime Assurance explained" → `https://certiv.ai/what-is-runtime-assurance/`
- **read** — "Certiv's approach" → `https://certiv.ai/approach/`
- **read** — "Claude Code security" → `https://certiv.ai/claude-code/`
- **read** — "Codex security" → `https://certiv.ai/codex/`
- **read** — "Pre-execution policy enforcement" → `https://certiv.ai/pre-execution-policy-enforcement/`
- **read** — "The Lethal Trifecta" → `https://certiv.ai/lethal-trifecta/`
- **read** — "Continuous authorization for AI agents" → `https://certiv.ai/continuous-authorization-for-ai-agents/`
- **read** — "AI agent security policies" → `https://certiv.ai/ai-agent-security-policies/`
- **read** — "Certiv vs CASB" → `https://certiv.ai/compare/casb/`

## Summary

Certiv provides an enterprise platform for discovering, understanding, and controlling AI agents on endpoints with runtime authorization and policy enforcement.

## Context

2006 sites in this index share the type "saas"; 1410 are transactional.

## How we grade

- tier 1 — **Declared**: The site says agents are welcome in its robots.txt. A permission, not a capability.
- tier 2 — **Probe-verified** (this site): We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
- tier 3 — **Behaviourally verified**: An agent completed the action end to end — booked, bought, submitted — and it worked.

## About this record

Known-Good probes sites live and publishes what was tested and when.
Method: https://knowngood.sh/about.md · Rubric: https://knowngood.sh/benchmark