← All posts

Platform & Architecture

338 posts on platform & architecture.

Document-Level Security in RAG Must Filter Before Retrieval

Document-level security in RAG belongs in the retrieval query, before chunks enter an LLM prompt. Index each document with tenant and access metadata, derive the caller identity from a trusted source, apply the filter server-side, preserve source permissions during updates, and record the retrieved document IDs for each model request.

ai-securityidentity-and-authorizationllm-securitypolicy-enforcementarchitecture
Read post →

LLM Caching Creates a Second Data Store with Its Own Access Rules

LLM caching can reduce latency and repeated token spend, but semantic and prefix caches create another store for prompts, responses, embeddings, or provider-side context. Security design needs cache scope, tenant isolation, key construction, encryption, expiry, invalidation, and a rule for which data classes may be cached.

ai-securityllm-securitycloud-securitypolicy-enforcementarchitecture
Read post →

Secrets Detection in Prompts Needs a Block Before the Provider Call

Secrets detection in prompts should identify provider keys, cloud credentials, private keys, database strings, and organization-specific tokens before an HTTP LLM request leaves the application boundary. Pattern matching needs entropy checks, custom signatures, decoding tests, allowlists, and a response plan for any credential already exposed.

ai-securitydata-loss-preventionllm-securitypolicy-enforcementdevsecops
Read post →

OPA for AI Policy Separates Decision Logic from the LLM Call

Open Policy Agent can evaluate structured facts about an AI request, including caller role, model route, data classification, region, and requested tool. OPA returns a decision; the gateway still has to enforce it, fail closed, protect policy inputs, version bundles, and write evidence for each request.

ai-securitypolicy-enforcementidentity-and-authorizationllm-securityarchitecture
Read post →

Tokenization vs Redaction for LLM Prompts: Reversibility Changes the Risk

Redaction removes or masks sensitive values before an LLM call. Tokenization replaces them with references that an authorized service may later resolve. The reversible path preserves workflow utility and creates a token vault, access-control, and re-identification obligation. Choose per data field and output requirement.

ai-securitydata-loss-preventionllm-securitypolicy-enforcementarchitecture
Read post →

AI Logs in a SIEM Need Decisions, Identity, and Content Minimization

AI logs sent to a SIEM should record caller identity, model route, policy version, data classification, decision, latency, and correlation IDs. Raw prompts and responses require a separate content decision. OpenTelemetry can standardize model events, while an independent gateway record proves what policy allowed before the call.

ai-securityauditforensic-auditllm-securityarchitecture
Read post →

Glean Permissions Depend on Connector Mode, Sync State, and Sharing

Glean permissions come from several control planes: source-system access lists, indexed snapshots, live authorization checks, Glean administrator roles, and agent-sharing rights. Connector mode determines when source permission changes take effect. Buyers should test revocation, domain-shared documents, and published agents as separate cases.

ai-securityidentity-and-authorizationai-governanceauditarchitecture
Read post →

BYOK for LLM Gateways: Storage, Fallback, Billing, and Attribution

BYOK for an LLM gateway can mean a team-level stored provider credential, a request-scoped credential, or a customer credential used before platform fallback. Those modes change the bill payer, rate limit, approved provider account, and audit trail. A sound design records which credential path served every request without exposing the secret.

ai-securityllm-securityidentity-and-authorizationpolicy-enforcementarchitecture
Read post →

Gong AI Security: SOC 2, ISO 42001, and Retention

Gong holds SOC 2 Type II certification and ISO/IEC 42001:2023 certification for AI management, states that customer conversation data is never used to train its generative models, and lets each customer configure retention themselves. This covers what Gong's Trust Center answers and what it does not: which authenticated identity triggered a specific AI request, what conversation content it carried, and whether a policy decision on that request is provable independent of Gong's own systems.

ai-securityllm-securityauditpolicy-enforcementidentity-and-authorizationarchitecture
Read post →

LLM Load Balancing Needs Policy-Aware Routing

LLM load balancing distributes eligible requests across deployments according to health, capacity, latency, and rate-limit state. The eligibility step comes first: identity, data classification, residency, and model authorization must remove forbidden destinations before an operational algorithm chooses among the remaining endpoints.

llmarchitecturecloud-securityinline-enforcementpolicy-enforcement
Read post →

Model Scanning Catches Dangerous Artifacts Before They Load

Model scanning inspects serialized ML artifacts before a runtime loads them. A useful gate identifies executable payloads, unsafe deserialization paths, suspicious imports, and format-specific risk, then preserves the scan result beside the artifact digest. It covers the model supply chain. Runtime authorization still needs a separate control on live LLM traffic.

ai-securityllm-securityarchitecturedevsecopspolicy-enforcement
Read post →

Loom CVE-2026-103956: An IdP-Less Deployment Granted Super-Admin Access

CVE-2026-103956 gave unauthenticated requests a fixed super-admin identity when Loom for AWS had no Cognito user pool or active external identity provider. This article explains the precise vulnerable state, the 1.6.1 fix, and the deployment gate that should keep an agent management plane unreachable until identity is working.

ai-securityagentic-aiidentity-and-authorizationmcp-securityarchitecture
Read post →