AI Pulse is delivered as an Azure Marketplace Managed Application. When you install it, it deploys entirely into your own Azure subscription — a single, self-contained set of resources in one resource group. There is no shared multi-tenant service: each customer runs their own isolated instance.
AI Pulse then reads signals from the AI and security services already in your environment (read-only) to build its governance dashboards. It does not run your AI models, and it does not move your data out of your tenant. Isolation is by deployment boundary — your instance, your subscription, your identity.
Have these ready before installing. Items marked optional only affect specific dashboards, which show an honest "not connected" state until enabled.
A single resource group containing these resources — all standard, all in your subscription:
| Resource | Purpose |
|---|---|
| Container App — portal | The AI Pulse web application itself. |
| Container App — Langfuse | Self-hosted AI-usage tracing. Keeps agent telemetry inside your tenant. |
| Container Apps environment | The managed host both apps run in. |
| PostgreSQL flexible server (2 databases) | Stores the audit log, governance records, and Langfuse data. |
| Key Vault | Holds the deployment's secrets (database password, gateway key, tracing key). |
| Storage account + file share | Persistent working storage for the portal. |
| Managed identity | The read-only identity the portal uses to gather signals (see §5). |
Every connection below is read-only. This is the telemetry AI Pulse gathers and what each signal powers in the product.
| Service | What it reads | What it powers | |
|---|---|---|---|
| Azure Resource Graph | Inventory of AI resources — Azure OpenAI, AI Foundry / ML, Cognitive Services, Search, Bot Service, model deployments. | The AI asset registry — a live map of every AI system you run. | included |
| Azure Cost Management | Month-to-date spend by service, daily AI-model spend, cost anomalies. | Cost & ROI dashboards (FinOps for AI). | included |
| Azure Policy | Compliant / non-compliant resource counts and the named resources. | Compliance posture. | included |
| Microsoft Defender for Cloud | Secure Score, security recommendations, active alerts, regulatory-standard results. | Security posture and attack-surface views. | optional |
| Azure Monitor — Activity Log | Recent administrative changes to AI resources (who changed what). | The admin change trail. | included |
| Azure Monitor — Metrics | Per-service call volume, latency, token counts. | Usage and performance widgets. | included |
| Log Analytics / Microsoft Sentinel | Deep per-agent traces and security-analytics signals. | Advanced telemetry and threat views. | optional |
| Azure AI Foundry / Azure ML | Model evaluation results (groundedness, relevance, safety, etc.). | Model quality and drift tracking. | included |
| Azure AI Content Safety | Prompt-shield and harm-analysis checks against your agents' prompts. | Content-safety posture. | optional |
| Azure Advisor + Logic Apps | Optimization recommendations; automation-workflow run history. | Operational-health widgets. | included |
| Microsoft Entra ID (Graph) | Directory names for access assignment, licence/SKU detection, and unsanctioned ("shadow") AI app discovery. | Identity, licensing, and shadow-AI discovery. | included |
| Microsoft 365 — Copilot audit | Microsoft 365 Copilot usage events. | Copilot adoption & usage. | optional |
| Microsoft Purview | Sensitivity labels and data-security signals. | Data-governance coverage. | optional |
| Power Platform | Copilot Studio agents and Power Automate flows. | Low-code / citizen-developer AI discovery. | optional |
| Self-hosted Langfuse (in your tenant) | Per-agent call / token / cost / latency, plus an in-tenant scan for exposed personal data (counts only — never stores the data itself). | Agent-level observability. | included |
AI Pulse follows least-privilege: it only ever asks for read access, and never gets Contributor, Owner, or user-admin rights. Permissions fall into three groups.
| Role | Scope | Why |
|---|---|---|
| Reader | Subscription | See resources and their configuration to build the AI inventory. |
| Cost Management Reader | Subscription | Read spend figures for the cost dashboards. |
| Key Vault Secrets User | The app's own Key Vault | Read its own deployment secrets at start-up. |
Granted to the app's managed identity after deployment (the identity doesn't exist until then). All read-only:
| Permission | Why |
|---|---|
Organization.Read.All | Detect licences (Copilot, Purview entitlement). |
User.Read.All · Group.Read.All · Directory.Read.All | Let admins assign access by typing a person's email or a group name (not just IDs). |
AuditLog.Read.All | Admin audit trail and Copilot activity. |
Application.Read.All · DelegatedPermissionGrant.Read.All | Discover unsanctioned ("shadow") AI apps consented in your tenant. |
Your data stays in your tenant. Here is exactly how — stated plainly, including the one nuance.
A typical install is five steps. SYLVA can run these with you.
AI asset inventory, cost & ROI, Azure policy compliance, admin change trail, usage & performance, model-quality, identity & shadow-AI discovery, and in-tenant agent observability.
Defender / Sentinel security depth, Content Safety coverage, Microsoft 365 Copilot usage, and Purview data-governance signals — each lights up when you connect the matching service or licence.
This overview is the anchor document. A complete customer pack usually adds the pieces below — we can produce each on request.
| Document | Purpose | |
|---|---|---|
| Azure services, data & security (this document) | The technical anchor — what deploys, what's read, what's needed. | ready |
| Installation & onboarding guide | Step-by-step install with screenshots and the exact scripts. | ready |
| Security & trust white paper | Threat model, data-flow diagram, and control mapping for security reviews. | ready |
| Data processing & privacy statement | What data is processed, where, and for how long — for DPO / legal review. | ready |
| Permissions reference | Every role and Graph permission with its exact identifier, for change-control. | ready |
| Operations & support guide | Backup, updates, monitoring, and how to get help. | ready |
SYLVA Labs Pte Ltd · AI Pulse — AI Assurance Platform. Customer technical overview, pre-release draft.
Prepared for review. Figures and service names reflect the current shipping install package; items marked roadmap are planned, not yet shipped, and are labelled as such deliberately.