Blog

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

LlamaIndex Audit Logs: What the Instrumentation Module Records and What LlamaCloud Adds

LlamaIndex ships two different record-keeping systems and neither one is an audit log in the sense a compliance team means. The open-source instrumentation module emits Spans and Events through a dispatcher for developer observability. LlamaCloud adds organization-level audit logs and SSO on Enterprise plans, covering administrative actions. Between those two sits the retrieval request itself, which carries no authenticated identity in either record.

Platform & Architectureai-securityaudit-logsragllm-securityobservability
Read post →

Vertex AI Gateway Patterns: Governing Gemini Traffic on Google Cloud

Teams front Vertex AI with a gateway for three jobs: token quotas and cost attribution, regional routing for data residency, and content screening on prompts through Model Armor. This article walks the patterns engineers run on Apigee in front of Gemini, shows where Model Armor sits, and marks the line between screening scoped to Google Cloud and the identity-bound payload governance a mixed model estate needs.

Platform & Architectureai-securityarchitecturezero-trustllm-securityinline-enforcementidentity-and-authorization
Read post →

Llama Security: What Llama Guard, IAM Scoping, and the License Actually Cover

Securing a Llama deployment layers three separate mechanisms: Llama Guard and Prompt Guard filtering content, cloud-native IAM or RBAC scoping which identity can call the model, and Meta'"'"'s Acceptable Use Policy setting legal boundaries on use. None of the three evaluates a specific request against an enterprise'"'"'s own policy at the moment it is made. Two 2026 CVEs in the serving layer underneath Llama show what that gap costs.

Platform & Architectureai-securityllm-securityidentity-and-authorizationzero-trustarchitecture
Read post →

Llama Audit Logs Depend Entirely on Which Hosting Layer You Picked

Llama is an open-weight model with no logging of its own, so audit logging for a Llama deployment depends entirely on the hosting layer. AWS Bedrock offers detailed model invocation logging that ships disabled by default. Azure AI Foundry routes similar detail through diagnostic settings that must be explicitly configured. Self-hosted deployments on vLLM or TGI have no audit logging at all until a team builds it. This article separates the three paths.

Platform & Architectureai-securityllm-securityauditcloud-securityarchitecture
Read post →

LangChain and LangSmith Audit Logs: Why the User ID Field Is Not an Identity Check

LangSmith traces every LangChain LLM call in detail: messages, tool calls, token counts, and custom metadata. The user_id and session_id fields that group those traces into threads are optional strings a developer chooses to attach, not values LangSmith verifies against an identity provider. This article separates trace completeness from identity verification and lists what a security review should check before relying on either.

Platform & Architecturellm-securityai-securityauditidentity-and-authorizationinline-enforcement
Read post →

Jasper AI Security: What SSO, Role Permissions, and the Audit Log Cover

Jasper secures workspace access through SAML SSO, role-based permissions, and a 90-day Audit Log tracking membership and role changes. Content and API access are gated separately through workspace roles and scoped API keys. None of these controls inspects the content of a specific generation request against the sensitivity of the brand or customer data feeding it. This piece maps where each control ends.

Platform & Architectureai-securityllm-securityidentity-and-authorizationauditzero-trust
Read post →

Intercom Fin Security: What Teammate Roles, API Tokens, and Regional Hosting Cover

Intercom secures Fin and the broader workspace through three separate mechanisms: teammate seat types and custom roles, API access tokens and OAuth scopes, and Regional Data Hosting across the US, EU, and Australia. Each answers a different question about who can reach the workspace and where data sits. None evaluates the content of a specific customer conversation Fin resolves on its own. This piece maps where each control ends.

Platform & Architectureai-securityllm-securityidentity-and-authorizationzero-trustarchitecture
Read post →

Intercom Fin Audit Logs: What Gets Recorded When an AI Agent Handles a Conversation

Intercom logs Fin AI Agent activity in two separate places: conversation-level metadata showing whether an AI Agent or a teammate handled a case, and Teammate Activity Logs recording admin configuration changes. Neither was built to capture what a specific Fin reply pulled from, or what policy should have governed a specific customer conversation. This article separates the two and lists what a review should retrieve.

Platform & Architectureai-securityllm-securityauditinline-enforcementpolicy-enforcement
Read post →

IBM watsonx.ai Security: What IAM Roles, Service IDs, and Private Endpoints Cover

IBM watsonx.ai secures access through three separate mechanisms: an IAM role hierarchy across platform, service, and workspace levels, Service ID credentials for programmatic access, and an optional private-network-only endpoint for the Runtime API. Each answers a different question about who can reach the platform. None evaluates the content of a specific prompt a permitted caller sends on a given request. This piece maps where each control ends.

Platform & Architectureai-securityllm-securityidentity-and-authorizationarchitecturecloud-security
Read post →

IBM watsonx.ai Audit Logs and the Service ID Gap at the Foundation Model Boundary

IBM watsonx.ai routes foundation model calls through Activity Tracker Event Routing, which records the caller IAM identity, the action, and the outcome in CADF format. Most production callers authenticate as a Service ID rather than a named person, so the event records which credential made the call, not which employee or agent was behind it. This article separates the two and lists what a security review should check.

Platform & Architectureai-securityllm-securityauditcloud-securityidentity-and-authorization
Read post →