← All posts

Platform & Architecture

338 posts on platform & architecture.

LiteLLM vs an AI Security Gateway: What Each One Does and Where They Compose

LiteLLM is an open-source LLM proxy that normalizes the API surface across more than 100 model providers and handles routing, retries, fallbacks, cost tracking, and basic key management. An AI security gateway sits at the same network position but answers a different question: identity-bound policy on prompt content, data classification at the request boundary, and a per-decision audit record that holds up under EU AI Act Article 12 review. The two products compose in production deployments. This piece walks through what each one does, where they overlap, and where the architectural responsibilities split.

litellmai-gatewaycomparisoninline-enforcementai-architectureaudit
Read post →

AI Security Proxy: What the Pattern Is and How It Differs from Traditional Web Proxies

An AI security proxy intercepts HTTP traffic between authenticated users or agents and LLM APIs, evaluates each request against identity-bound policy, and writes a per-decision audit record before the response returns. The pattern differs from the traditional forward proxy at four architectural points: prompt-level data classification, identity binding at the request layer, fail-closed policy evaluation, and tamper-evident audit independence. I walk through the architecture and where it fits in the 2026 enterprise AI stack.

ai-securityai-gatewayenforcementarchitectureauditai-proxy
Read post →

AI Gateway Latency Benchmarks: Reading the 2026 Numbers Without Getting Fooled by the Mock Upstream

AI gateway latency benchmarks in 2026 report figures from microseconds to tens of milliseconds, but almost all of them measure proxy forwarding against a mock upstream, which deletes the largest real-world variable. This article defines the metrics that matter, reads the LiteLLM, Bifrost, Kong, and Portkey numbers with their methodology caveats, and shows why gateway overhead is a small fraction of provider TTFT and how to keep policy evaluation off the critical path.

ai-gatewayarchitectureinline-enforcementai-securityllmpolicy-enforcement
Read post →

Zoom AI Companion Security: Separate Content, Models, and Controls

Zoom AI Companion security depends on the content source and function in use. The model deployment, administrator setting, and retention configuration also matter. A useful review traces meeting transcripts and chat messages separately from connected-source content and task execution. It also distinguishes Zoom-managed AI processing from any customer-controlled HTTP model route where an independent request-policy decision could operate.

ai-securityllm-securityidentity-and-authorizationpolicy-enforcementcloud-security
Read post →

Windsurf Security: Six Devin Desktop Boundaries to Review

Windsurf security now needs current Cognition terminology. Devin Desktop provides native controls for SSO, SCIM, RBAC, model availability, terminal execution, MCP access, deployment, and sharing. Cognition separately documents encryption and customer-data practices. These preventive controls need distinct owners, and only configurable AI HTTP traffic can pass through an independent request-policy gateway.

ai-securityagentic-aiidentity-and-authorizationzero-trustcloud-security
Read post →

Windsurf Audit Logs: Reading the Current Devin API Evidence

Windsurf audit logs now require a terminology check. Cognition's current documentation exposes enterprise audit events through Devin API v3, while legacy Windsurf Enterprise remains an authentication and billing qualifier. The v3 endpoint supports service-user RBAC and time filters. It also supports action filters and cursor pagination, with actor fields in the response. Investigators still need a separate request-policy record for routed AI HTTP calls.

ai-securityauditforensic-auditidentity-and-authorizationagentic-ai
Read post →

Zapier AI Security: Separate Workflow Controls from Model Routes

Zapier governs AI-enabled automation through publishing controls, app access, managed connections, model restrictions, audit records, AI Guardrails, and scoped MCP tools. Those controls operate inside Zapier. An independent policy gateway covers a narrower path: authenticated LLM inference requests that a supported integration explicitly routes through an external HTTP enforcement point.

ai-securityagentic-aillm-securitypolicy-enforcementidentity-and-authorization
Read post →

WRITER Security: Map Platform Controls to the Model Route

WRITER combines identity validation, permissions, approval flows, activity traces, model controls, and governed access to connected systems inside its enterprise AI platform. A security review should verify those native controls and then inventory every separate LLM route. Independent request authorization applies only where authenticated HTTP model traffic is explicitly routed through an enforcement gateway.

ai-securityllm-securityzero-trustpolicy-enforcementidentity-and-authorization
Read post →

Vertex AI Security: Five Native Controls and the Request Gap

Vertex AI security now sits under Google''s Gemini Enterprise Agent Platform name. Google documents separate controls for residency and customer-managed encryption keys, plus service perimeters and provider access visibility. It also documents retention. Their availability varies by model and operation. A routed AI request still needs caller-aware policy before inference when project IAM represents a shared application rather than the originating person or agent.

ai-securitycloud-securityidentity-and-authorizationzero-trustpolicy-enforcement
Read post →

Snowflake Cortex Security: A Preventive Hardening Review

Snowflake Cortex security requires explicit control over AI function privileges, model RBAC, inference geography, runtime guardrail scope, and Trust Center scanner coverage. A preventive review assigns owners and tests denied paths before production. External policy enforcement applies only to customer-controlled authenticated HTTP LLM traffic routed through a separate proxy.

ai-securitycloud-securityidentity-and-authorizationzero-trustpolicy-enforcement
Read post →

ServiceNow AI Security: Separate Guardian, Roles, and Request Policy

ServiceNow AI security combines in-platform AI Guardian checks, administrative roles, application configuration, and the Generative AI Controller connection to third-party models. A useful review tests each boundary separately, confirms the guardrail scope for every skill, and adds an external request-policy decision only where customer-controlled authenticated HTTP traffic can be routed through it.

ai-securityprompt-injectionidentity-and-authorizationpolicy-enforcementcloud-security
Read post →

Snowflake Cortex Audit Logs: Build the Evidence Chain Across Views

Snowflake Cortex audit evidence is distributed across function usage, agent usage, query history, and access history. Investigators need explicit joins, latency notes, historical-coverage qualifications, and a preserved correlation value. A separate policy-decision record adds request authorization only for customer-controlled authenticated HTTP LLM calls routed through an external gateway.

forensic-auditauditai-securityai-governancecompliance
Read post →