← All posts

Platform & Architecture

215 posts on platform & architecture.

SAP Joule Security: Four Boundaries to Test Before Production

SAP Joule security starts with an OAuth user session, continues through application permissions, and relies on TLS plus configured SAP BTP destinations for network communication. Those controls answer different questions. A production review should test the identity on the request, the permissions applied in each connected application, the route used for outbound traffic, and the policy decision made for the prompt before it reaches an LLM.

ai-securityidentity-and-authorizationzero-trustpolicy-enforcementcloud-security
Read post →

SAP Joule Audit Logs: Three Records That Answer Different Questions

SAP Joule audit evidence is split across conversation logs, user-level exports, and security-event records for Joule Studio, classic edition. Conversation logs can preserve the initiating global user ID, timestamps, conversation ID, user input, Joule responses, and feedback. Configuration evidence lives in a different service, and storage depends on tenant choices made during onboarding.

ai-securityforensic-auditauditcomplianceai-governance
Read post →

Salesforce Einstein Audit Logs: Build a Decision Evidence Package

Salesforce says the Einstein Trust Layer securely logs prompts and outputs plus interactions and feedback data, with audit and feedback data stored in Data 360 for reporting and Flow alerts. That is a detailed platform record. A security review should test retrieval and access alongside retention, correlation, and the policy decision behind one interaction instead of treating log presence as proof of complete lineage.

ai-securityauditforensic-auditai-governanceidentity-and-authorization
Read post →

Replit Agent Audit Logs: The 30-Day Evidence Window

Replit Enterprise audit logs cover more than 50 event types, including Agent activity, and support portal exports plus SIEM streaming. Their default retention is 30 days, and a failed audit event never blocks the underlying action. Security teams need to distinguish this administrative activity record from an independent, per-decision record of HTTP model requests.

ai-securityauditforensic-auditagentic-aiidentity-and-authorization
Read post →

Perplexity Enterprise Security: SSO, Sharing Controls, SCIM, and the Request Gap

Perplexity Enterprise gives administrators controls for SSO, SCIM provisioning, public sharing, file downloads, repository changes, attachments, connectors, and incognito retention. These controls govern account access and workspace behavior. A security review should also identify which HTTP AI routes the enterprise controls, because a valid workspace member can still submit sensitive content unless a request-level policy evaluates the principal, payload, and destination before model access.

ai-securitycloud-securityidentity-and-authorizationzero-trustpolicy-enforcementdata-loss-prevention
Read post →

Oracle AI Security: IAM, API Keys, Guardrails, and the Request Boundary

OCI Generative AI separates resource authorization, model credentials, and content guardrails. IAM policies decide which groups can manage or use service resources. Generative AI API keys authenticate calls to hosted models, while guardrails provide content moderation and detection of prompt injection or PII. A production review should preserve those layers and add identity-bound policy to each HTTP inference request.

ai-securitycloud-securityidentity-and-authorizationpolicy-enforcementzero-trustllm-security
Read post →

SAP AI Core Security: Tenant Boundaries Stop Short of Request Authorization

SAP AI Core uses XSUAA service-key credentials, tenant-aware resource groups, namespace isolation, and sandboxed workloads. Those controls establish who can reach the service and where runtime objects belong. An AI request still needs a content-aware authorization decision that binds the originating identity, prompt classification, model route, and policy version before inference.

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

Replit Agent Security: Four Control Boundaries to Test

Replit assigns Agent harness security to its platform while customers own generated-code review, prompt hygiene, sensitive-action approval, and third-party Skill or MCP vetting. Agent security scans add source and static analysis, but Replit calls them incomplete. A credible review tests the Agent, generated application, deployment, and routed model-request boundaries separately.

ai-securityagentic-aidevsecopszero-trustpolicy-enforcement
Read post →

Perplexity Enterprise Audit Logs: Rich Query Evidence Still Needs Policy Context

Perplexity Enterprise Audit Logs stream query, answer, file, login, settings, and Comet agent events to a customer webhook in real time. The documented schema includes a UUID, timestamp, event type, user email, IP address, user agent, session ID, and event metadata. This gives investigators unusually rich activity evidence. A policy review should still test delivery failure handling, retention, content exposure, and the absence of an enterprise authorization decision in the event schema.

ai-securityauditforensic-auditcomplianceagentic-aiidentity-and-authorization
Read post →

OpenAI Agent Builder Security: Constrain the Workflow, Then Authorize Every Model Call

OpenAI documents prompt injection and private-data leakage as central risks in Agent Builder workflows. Its guidance calls for structured outputs, human approval on MCP operations, input guardrails, trace graders, and careful placement of untrusted data. Those controls reduce workflow risk. Enterprise authorization still needs an independent decision on each HTTP model request, tied to the principal, content classification, route, and policy in force.

ai-securityagentic-aiprompt-injectionidentity-and-authorizationinline-enforcementllm-security
Read post →

OpenAI Agent Builder Audit Logs: The Admin API Records the Org, Not the Agent Run

OpenAI exposes an Audit Logs API that lists recent user actions and configuration changes for an organization, reached with an admin credential carrying the Audit Logs read scope. The documented surface is administrative: credential creation, user and role changes, login attempts, project modifications. Agent Builder workflows execute inside that organization, and the runs themselves sit outside the event list the Admin API publishes.

ai-securityaudit-logsagentic-aicomplianceidentity-and-authorization
Read post →

NVIDIA NIM Security: What an NGC API Key Authenticates and What It Does Not

An NGC API credential pulls NIM container images from nvcr.io and authenticates calls to NVIDIA-hosted endpoints. It works at the registry and account level rather than as a per-request authorization mechanism. Once a NIM container is running in your own cluster, access control belongs entirely to the deployment platform, and platforms including NVIDIA Run:ai default to public access with no authentication on the inference endpoint.

ai-securityself-hosted-llmidentity-and-authorizationzero-trustarchitecture
Read post →