Resources
Read before you buy
The material around the product: what the problems actually are, the vocabulary to discuss them, how the proxy fits the stack you already run, and what regulators expect of LLM traffic. Written for engineers deciding what to defend against – not just what to buy.
What are LLM guardrails?
LLM guardrails explained: input, output, and action checks that keep AI apps safe. Types, concrete examples, library vs proxy trade-offs, and how to start.
What is prompt injection?
Prompt injection explained: direct jailbreaks, indirect attacks hidden in emails and tool results, and why agents raise the stakes. Defense in depth, layer by layer.
What are AI hallucinations?
Why LLMs hallucinate, the four failure types that matter in production, and how detection actually works – from deterministic number checks to fact-check judges.
What is MCP security?
The Model Context Protocol gives agents tools – and attackers a surface. Tool poisoning, rug pulls, and result injection explained, plus the gateway defenses.
AI hallucination examples: the incidents that made case law
Documented AI hallucination incidents – Air Canada’s chatbot, fabricated legal citations, a $100B demo error – and the guardrail that would have caught each one.
What is excessive agency?
Excessive agency – OWASP LLM06 – is the gap between what your agent can do and what it should. Permissions, tiers, budgets, and approvals, explained.
The LLM security checklist
A practical pre-launch security checklist for LLM apps and agents: input, output, action, and operational checks – each with what “done” actually means.
The guardrails glossary
Thirty terms in a paragraph each – the attacks, the defenses, and the operating concepts – each linking to the page that treats it in depth.
OWASP LLM Top 10 coverage map
Each of the ten risks mapped to the guardrail that addresses it – including the two we only partially cover and the one a runtime proxy honestly can’t.
Library vs gateway vs proxy
The four ways teams deploy guardrails, what job each is actually good at, and when a proxy on the wire is – and isn’t – the right call.
LangChain
Add guardrails to LangChain and LangGraph agents without middleware sprawl: a base-URL swap for model calls, a callback for tool checkpoints, one audit trail.
n8n
Guard n8n AI workflows without rebuilding them: point AI nodes at the proxy, gate consequential nodes with a checkpoint, and compile your workflow into policy.
MCP
Route MCP clients through a gateway that inspects tools/call before forwarding, scans results for injection, and pins server manifests against rug pulls.
OpenAI
Put guardrails in front of the OpenAI API without changing your code: PII screening, hallucination checks, tool-call policy – via a base-URL swap in any SDK.
Claude (Anthropic)
Run Claude Opus, Sonnet, and Haiku behind a guardrails pipeline: PII screening, hallucination checks, and content safety – without changing your client code.
OpenRouter
One guardrails pipeline across every OpenRouter model – Gemini, Claude, GPT, Llama, DeepSeek, Qwen, Mistral – with per-model cost and quality evidence.
LM Studio & local models
Local models still hallucinate and still obey injections. Run the same guardrail pipeline in front of LM Studio and any OpenAI-compatible local server.
EU AI Act
How runtime guardrails support EU AI Act obligations – logging and traceability, human oversight, accuracy and robustness – ahead of the August 2026 deadline.
GDPR
Sending prompts to model providers is processing personal data. How PII screening, pseudonymization, and screened logs support GDPR-aligned LLM deployments.
HIPAA
Using LLMs with patient data raises PHI disclosure risk. How PII screening and audit trails support HIPAA-aligned healthcare AI deployments.
Done reading? See it run.
We’re running a limited demo – sign up and we’ll get you in as soon as we can.