← All posts

AI Security Solutions

97 posts on ai security solutions.

AI usage quota enforcement: the four counters production deployments actually need

AI usage quota enforcement is the mechanism that keeps AI spend, provider rate limits, and cross-tenant fairness under control. Production deployments need four counters at the gateway: per-caller request rate, per-tenant token throughput, per-workload cost, and per-model concurrency. Each counter answers a different failure mode. This piece walks through the four counters, where each one sits in the request flow, the fail-closed behavior each one demands, and the audit fields the enforcement decisions produce.

ai-quotarate-limitingai-gatewaycost-controlai-policy-enforcement
Read post →

LLM Response Content Filter: The Transform Patterns That Convert an Unsafe Answer Into a Safe One Without Blocking the Request

Blocking every unsafe response is the wrong default for many production deployments. A well-scoped response filter transforms the unsafe portion (redacts PII, rewrites competitor mentions, strips prompt-injection payloads intended for downstream systems) and passes the safe remainder through. This covers the transform patterns, where they sit in the streaming response path, and how the audit record differentiates a transform from a block.

llm-response-filterai-securitycontent-filterllm-dlpai-gatewayoutput-filtering
Read post →

AI Gateway for Regulated Industries: The Control Requirements

A general AI gateway routes traffic and manages keys. A regulated deployment needs more from the same layer: identity bound to every request, prompt-level classification of PHI, NPI, and PII, data-residency control over which endpoints a prompt may reach, a fail-closed posture, and a per-decision audit record that survives a regulator's questions. This walks through the control requirements and maps them to healthcare, finance, government, and legal regimes.

ai-gatewayai-securityinline-enforcementcompliancearchitecture
Read post →

Open Source AI Gateway: What It Covers and Where the Gap Is

Open source AI gateways solved the operational problem of talking to many model providers through one interface: unified APIs, routing, rate limiting, caching, key management, and observability. They are strong at the operational layer and mostly leave the control layer, identity-bound authorization, prompt classification, and a tamper-evident per-decision audit record, as a build-it-yourself exercise. This walks through what the open source category covers, where the regulated-deployment gap sits, and how to evaluate the difference.

ai-gatewayai-securityinline-enforcementarchitecturellm-security
Read post →

Secure AI Gateway: The Seven Properties That Decide Whether It Is a Control

Most products described as a secure AI gateway are routing layers with a content filter attached. A gateway becomes a security control when it holds seven properties: identity binding, per-request authorization, fail-closed behavior, prompt-level data classification, model-agnostic reach, write-path independence for its audit records, and a bounded latency budget. I walk each property, the failure mode it removes, and the question to ask a vendor that claims it.

ai-securityinline-enforcementpolicy-enforcementarchitecturezero-trustaudit
Read post →

AI Agent Guardrails: Constraining a Loop That Chooses Its Own Next Call

Guardrails written for a single chat completion assume one request, one response, one human reading the output. An agent runs a loop: it calls a model, reads the result, picks a tool, calls the model again, and repeats without a human between the steps. That changes what a guardrail has to constrain. This covers the four controls an agent loop needs, why per-call classification is not enough, and how identity-bound authorization limits blast radius when an injected instruction succeeds.

ai-agent-securityai-guardrailsagentic-aiidentity-and-authorizationpolicy-enforcementai-security
Read post →

AI Security Policy: The Eleven Clauses That Have to Be Enforceable

An AI security policy fails at the same place every time: it states what employees and services may send to a model, and nothing in the environment can observe whether that happened. This walks eleven clauses a working policy needs, marks which of them are enforceable at the AI request layer versus which stay administrative, and gives the evidence question to ask of every clause before it ships.

ai-securityai-governancepolicy-enforcementcomplianceshadow-aiaudit
Read post →

LLM Data Security: Five Places Enterprise Data Moves and Which Ones You Can Control

Enterprise data reaches a model through five distinct paths: a user pasting into a prompt, an application assembling context programmatically, a retrieval system injecting documents, a tool call returning results mid-loop, and training or fine-tuning. Each path has a different owner and a different control point. This walks all five, marks which are governable at the HTTP request layer, and explains why prompt-time classification is the one that cannot be substituted.

ai-dlpllm-securityai-securityshadow-aipolicy-enforcementdata-protection
Read post →

Windsurf DLP: The AI Request Paths That Move Source Code

Windsurf DLP is an AI traffic problem with several source-code egress paths: indexed repositories, inline suggestions, chat context, and agent actions. Each path can carry code, fixtures, configuration, or terminal output to an LLM endpoint. This article separates those paths, defines the policy decisions a deployment needs, and locates DeepInspect at the HTTP boundary while naming the endpoint, repository, and credential controls that remain adjacent.

ai-securityllm-securitydata-loss-preventiondlpdevsecopsinline-enforcement
Read post →

Snowflake Cortex DLP Needs Policy at the AI Request Boundary

Snowflake Cortex can carry enterprise context into an LLM workflow. DLP needs a decision point that evaluates the prompt, response, originating identity, data classification, and selected route before content reaches the model. This article sets out the request-path evidence a security review should require.

data-loss-preventiondlpai-securitypolicy-enforcementinline-enforcement
Read post →

SAP Joule DLP Needs Policy at the AI Request Boundary

SAP Joule can carry enterprise context into an LLM workflow. DLP needs a decision point that evaluates the prompt, response, originating identity, data classification, and selected route before content reaches the model. This article sets out the request-path evidence a security review should require.

data-loss-preventiondlpai-securitypolicy-enforcementinline-enforcement
Read post →

Salesforce Einstein DLP Needs Request-Level Policy

Salesforce Einstein can carry enterprise context into an LLM workflow. DLP needs a decision point that evaluates the prompt, response, originating identity, data classification, and selected route before content reaches the model. This article sets out the request-path evidence a security review should require.

data-loss-preventiondlpai-securitypolicy-enforcementinline-enforcement
Read post →