The complete AI security platform. Firewall your AI agents, secure your API keys, observe every decision in real-time. One platform — total protection.
The AI firewall that tests every AI agent before it touches your systems. Riddle-based authentication, real-time observability, zero blind trust.
Ultra-secure API key storage with zero-trust architecture. AES-256 encryption, jumpbox isolation, and unified billing across all AI providers.
Request is encrypted with AES-256-GCM before it leaves your app. Even if intercepted — unreadable.
Platform LayerDoes this AI already hold a cached Capability Certificate? If yes — skip straight to forwarding. Under 400ms.
Speed PassNo cert? The Looking Glass builds a contextual riddle from your real system data — database tables, service endpoints, team structures. Only an AI that truly knows your systems can solve it.
Riddle MatrixThe AI receives messy, real-world data (logs, config, metadata) and must extract the correct answers. A competent AI solves it instantly. An outsider can't even begin.
Every field checked. 100% correct = pass. Anything less = denied. No partial credit. A temporary key (5 min TTL) and Capability Certificate are issued.
Gate LayerThe request is sent to the real LLM (OpenAI, Claude, Groq, Bedrock — any provider). Your app receives the normal response. Zero code changes.
Every action — riddle generated, score computed, cert issued or denied — is streamed live to The Looking Glass Dashboard via SSE. Full observability in real time.
ObservableA person onboards the AI with system knowledge — like onboarding a new employee. That knowledge becomes the riddle clues.
An AI Brain auto-scans your infrastructure and builds riddles automatically. No human intervention needed — the Brain keeps riddles fresh and evolving.
Keys encrypted at rest with your master key. Even we can't see them — only your authorized services can decrypt.
Keys never leave the vault. Requests proxy through isolated containers with no persistent storage or network egress.
Bring your own OpenAI, Anthropic, or Groq keys. Use our unified billing or your existing provider accounts.
Unified billing with volume discounts across providers. One invoice, predictable costs, transparent pricing.
Riddle tests: "What's the main branch? What's the staging URL? Which service owns /api/users?"
Riddle tests: "Who is the CFO? What's the payroll DB table? What's the quarterly tax deadline?"
Riddle tests: "What EHR system is active? What's the patient ID format? What department owns this data?"
Riddle tests: "What VPC is production? What's the CIDR block? Which IAM role has deploy access?"
Riddle tests: "What's the price table? What currency format? What's the max discount policy?"
Riddle tests: "What jurisdiction? What case management system? What document classification level?"
Works with any app that talks to OpenAI, Claude, Groq, or Bedrock. Change one URL — that's it.
End-to-end encryption. Data is encrypted before it leaves your app — even we can't read it in transit.
When pass rates climb above 90%, riddles automatically evolve to stay ahead. Security improves without human intervention.
Trusted AI skips the riddle with a cached Capability Certificate. Repeat access in under 400ms.
Locked sandbox with no internet access, auto-destroyed when the task completes. Applied on top of either module.
The Looking Glass Dashboard streams every verdict, every score, every decision — live via SSE. Nothing hidden.
Firewall your AI agents with Looking Glass. Secure your keys with Key Vault. No blind trust.