Blog

Analysis on enterprise AI governance, inline policy enforcement, agentic AI security, and regulatory compliance.

Semantic Caching at the LLM Gateway: What It Saves and the Four Ways It Leaks

Semantic caching answers a new prompt with a stored response when the embeddings are close enough. It cuts cost and latency, and it introduces a shared read path across whatever tenants and identities share the cache namespace. This covers the architecture, the similarity threshold problem, four concrete leak paths including cross-tenant hits and stale policy decisions, and the partitioning rules that make a cache safe to run.

Platform & Architectureai-gatewayllm-securityengineeringpolicy-enforcementai-securityarchitecture
Read post →

Pydantic AI Behind a Gateway: Routing, Identity, and What the Type System Does Not Cover

Pydantic AI gives an agent a typed output contract, typed dependencies, and validated tool signatures, which removes a real class of parsing and argument bugs. Schema validation runs after the model call and inside the process, so it covers structure rather than authorization, egress, or evidence. This walks what the type system enforces, the four gaps that remain, and how to route a Pydantic AI agent through a gateway without changing agent code.

Platform & Architectureai-agent-securityengineeringai-gatewayllm-securitypolicy-enforcementpython
Read post →

LLM Tool Integration Security: The Trust Boundary Between a Model and the Functions It Calls

Giving a model tools converts text generation into action. The model emits a structured call, your code executes it, and the result goes back into the context window. Three trust boundaries sit inside that loop: the tool description the model reads, the arguments it emits, and the output that returns as trusted context. This walks the failure at each boundary, the validation each one needs, and where credential scoping does work no HTTP control can substitute for.

Platform & Architecturellm-securityai-agent-securityprompt-injectionpolicy-enforcementengineeringai-security
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 Security Solutionsai-dlpllm-securityai-securityshadow-aipolicy-enforcementdata-protection
Read post →

UK GDPR and AI: The Six Obligations That Bite When a Prompt Leaves Your Network

The UK has no AI Act. AI use is governed under the UK GDPR and the Data Protection Act 2018, enforced by the ICO, with sector regulators layering their own expectations on top. Six obligations do the work: lawful basis, purpose limitation, data minimisation in the prompt, Article 22 automated decisions, international transfers when a prompt crosses a border, and Article 30 records. This walks each and marks where the evidence has to come from.

Compliance & Regulationcomplianceai-governanceregulationauditai-securitydata-protection
Read post →

AI Governance Regulations in 2026: The Dates That Bind and What Each One Asks You to Show

Eleven binding AI instruments carry 2026 or 2027 dates across the EU, the US states, and financial and healthcare regulators. They differ in scope and penalty, and they converge on three demands: know which AI systems you run, control who may use them and how, and produce records showing both held. This lists the instruments with their operative dates and sorts what each one actually asks you to produce.

Compliance & Regulationai-governanceeu-ai-actcomplianceregulationauditai-security
Read post →

AI Governance Standards: Which One Is Certifiable, Which Is Guidance, and What Each Expects in Production

Six documents get called AI governance standards: ISO/IEC 42001, ISO/IEC 23894, the NIST AI RMF, ISO/IEC 27001 with AI extensions, the EU AI Act harmonized standards work, and OWASP AISVS. Only one of them is certifiable, two are law-adjacent, and they differ sharply in how much production evidence they expect. This sorts them by what they are, how they overlap, and which clauses require runtime records rather than documents.

Compliance & Regulationai-governanceiso-42001nist-ai-rmfcomplianceeu-ai-actaudit
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 Security Solutionsai-securityai-governancepolicy-enforcementcomplianceshadow-aiaudit
Read post →

ISO/IEC 23894: What the AI Risk Management Standard Asks You to Produce

ISO/IEC 23894:2023 adapts the ISO 31000 risk management process to AI systems. It is guidance rather than a certifiable standard, which changes how it gets used: teams reach for it to structure risk identification and to feed the risk clauses of ISO/IEC 42001, which is certifiable. This walks the standard structure, the AI-specific risk sources it names, how it relates to 42001 and the NIST AI RMF, and which of its monitoring and record requirements a runtime control produces evidence for.

Compliance & Regulationiso-42001ai-governancecompliancerisk-managementauditregulation
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 Security Solutionsai-agent-securityai-guardrailsagentic-aiidentity-and-authorizationpolicy-enforcementai-security
Read post →

AI Guardrails: The Four Layers, What Each One Enforces, and Where the Evidence Comes From

AI guardrails get used as one word for four different control layers: training-time alignment inside the model, provider safety filters at the inference endpoint, application-side validation in the prompt template, and policy enforcement on the HTTP call itself. Each layer sits at a different point in the request path, fails in a different way, and produces a different quality of evidence. This walks all four, shows where each one breaks, and explains which layer an auditor can actually inspect.

AI Security Solutionsai-guardrailsai-securitypolicy-enforcementai-governancellm-securityaudit
Read post →

The Commission adopted its Article 50 guidelines on July 20: who discloses, who marks, and what you have to be able to prove

The European Commission adopted its final guidelines on the Article 50 transparency obligations on July 20, 2026, thirteen days before those obligations start to apply on August 2. The guidelines set out scope, definitions, and exceptions, and they split the duties actor by actor: providers carry the interaction notice and the machine-readable marking of synthetic content, deployers carry emotion-recognition notice and deepfake disclosure. Generative systems already on the market get until December 2, 2026 for machine-readable marking. This walks the split obligation by obligation and separates the parts an AI policy gateway produces evidence for from the parts it never touches.

Compliance & Regulationeu-ai-actcomplianceregulationai-governanceai-complianceaudit
Read post →