Claims data platform on Microsoft Fabric feeding agents and reports

Well-Architected review Claims data platform on Microsoft Fabric feeding agents and reports · 2026-10-02 · mode full

Coverage audit

• Azure Well-Architected Framework — 5 pillars, 59 recommendations, from the live documentation index, snapshot 2026-10-02 (0 days old).
• Assessed 59 recommendations: 10 with diagram evidence, 49 cannot be determined.
• Evidence sources: architecture diagram (services, boundaries, relationships); cost estimate from the Azure Retail Prices API.
• Corpus read from a committed snapshot of the live documentation index (not re-fetched during this review). Re-read it with `archify-azure wa corpus --refresh`. Statuses reflect what the diagram and spec show. Process, configuration and runtime evidence are not observable here, so those recommendations are 'Cannot Determine' rather than guessed.

Executive summary

This Azure Well-Architected Framework (with the guidance for AI workloads) review of Claims data platform on Microsoft Fabric feeding agents and reports (standard criticality) assessed the architecture diagram only. 10 of 59 framework recommendations have diagram evidence; the rest are Cannot Determine because process, configuration and runtime evidence is not in the diagram. It found 0 critical, 1 high, 1 medium and 0 low risks. Estimated run cost is $508/month (indicative).

10 of 59 recommendations have diagram evidence (17%); among those, 2 implemented, 2 partial, 6 not implemented. Provisional: scores cover evidenced practices only.

Strengths. Data stores are not placed in public subnets; IaC / delivery pipeline shown; Model telemetry destination shown.

Architecture overview

The reviewed architecture is the Diagram tab (15 components, dataflow diagram). Hover a finding to highlight the components involved.

Pillar scorecard

Score = 1 + 4 × (implemented + ½ partial) ÷ evidenced recommendations; shown only when ≥ 3 recommendations are evidenced. It reflects evidenced practices, not the whole pillar.

Recommendation ledger 59 recommendations — nothing truncated

Findings

High risk (1)

Medium risk (1)

To confirm not drawn, so not counted as gaps

• No private endpoints shown for PaaS data services SE:06, SE:04 — Disable public network access on PaaS data services (Storage, SQL, Cosmos DB, Key Vault) and connect through Azure Private Link private endpoints with private DNS zones.
• No Azure Key Vault shown for data at rest SE:07 — Manage encryption keys in Azure Key Vault (customer-managed keys where you need rotation, access policy or audit control) and enforce encryption at rest and TLS in transit on every data store.
• No identity / authentication service shown SE:05 — Authenticate and authorize every request through Microsoft Entra ID with conditional access, MFA and least-privilege RBAC; use managed identities for workload-to-workload access.
• No threat detection or posture management shown SE:10, SE:01 — Enable Microsoft Defender for Cloud and Microsoft Sentinel, assign Azure Policy initiatives for the baseline, and send activity and diagnostic logs to a central, access-restricted Log Analytics workspace.
• No backup or recovery capability shown RE:09 — Protect data with Azure Backup (vault with soft delete and cross-region restore where required) or database point-in-time restore, and test restores against your RPO/RTO.
• No cost visibility shown CO:03, CO:04, CO:01 — Set Microsoft Cost Management budgets with alert thresholds and enforce cost-allocation tags (Azure Policy) so spend maps to this workload.
• Single-region model inference RE:05, RE:06 — Plan for throttling and quota limits (retries, queuing, provisioned throughput units) and consider global or data-zone deployments, a second region or a fallback model.
• Model cost controls CO:07, CO:12 — Select the smallest model that meets quality targets; use prompt caching and batch deployments where possible; track cost per request.
• Agents and excessive agency SE:05, SE:08 — Give agents least-privilege managed identities and scoped tools, enforce policy at the tool boundary and add human approval for high-impact actions.

Eisenhower prioritization

Prioritized remediation plan

Next steps

1. F-001 No content safety around model input/output — Apply Azure AI Content Safety (content filters, prompt shields, groundedness detection) to prompts and responses, and handle PII before it reaches the model. (ML platform team)
2. Re-run the review after changes, and when the architecture or documentation changes.

Impact × Likelihood matrix from the AWS well-architected-review skill, applied to the Azure Well-Architected Framework (Severe+High = Critical; Severe+Medium/Low or Moderate+High = High; Moderate+Medium/Low or Minor+High = Medium; otherwise Low).