Agent tool call through AgentCore Gateway and Policy

Well-Architected review Agent tool call through AgentCore Gateway and Policy · 2026-10-02 · mode full

Coverage audit

• AWS Well-Architected Framework — 6 pillars, 57 questions, 307 best practices, from the live documentation index, snapshot 2026-10-01 (0 days old).
• Generative AI Lens — 29 questions, 51 best practices, snapshot 2026-10-01.
• Assessed 307 framework BPs and 51 lens BPs: 10 + 7 with diagram evidence, 295 + 44 cannot be determined.
• Evidence sources: architecture diagram (services, boundaries, relationships); cost estimate from the AWS Price List.
• Corpus read from a committed snapshot of the live documentation index (not re-fetched during this review). Re-read it with `archify-aws wa corpus --refresh`. Statuses reflect what the diagram and spec show. Process, configuration and runtime evidence are not observable here, so those BPs are 'Cannot Determine' rather than guessed.

Executive summary

This Well-Architected Framework and Generative AI Lens review of Agent tool call through AgentCore Gateway and Policy (standard criticality) assessed the architecture diagram only. 10 of 307 framework best practices and 7 of 51 lens best practices have diagram evidence; the rest are Cannot Determine because process, configuration and runtime evidence is not in the diagram. It found 0 critical, 0 high, 3 medium and 1 low risks. Estimated run cost is $135/month (indicative).

10 of 307 framework best practices have diagram evidence (3%); among those, 0 implemented, 3 partial, 7 not implemented. Provisional: scores cover evidenced practices only.

Strengths. Guardrails shown; Governed agent tool access and evaluation.

Architecture overview

The reviewed architecture is the Diagram tab (8 components, sequence diagram). Hover a finding to highlight the components involved.

Pillar scorecard

Generative AI Lens scorecard

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

Framework questions

Generative AI Lens questions

Framework best-practice ledger 307 best practices — nothing truncated

Generative AI Lens best-practice ledger 51 best practices — nothing truncated

Findings

Medium risk (3)

Low risk (1)

To confirm not drawn, so not counted as gaps

• No identity / authentication service shown SEC02-BP04 — Authenticate and authorize every request through a centralized identity provider (Amazon Cognito, IAM Identity Center) with MFA and temporary credentials.
• No detection or audit services shown SEC04-BP01, SEC04-BP02 — Enable CloudTrail (organization trail), GuardDuty and Security Hub, and send logs and findings to a central, access-restricted account.
• No infrastructure-as-code or CI/CD shown OPS05-BP04, OPS05-BP10, REL08-BP05, SEC11-BP06 — Define infrastructure as code and deploy through a pipeline with small, reversible changes and automated rollback.
• No CDN / edge acceleration shown for end users PERF04-BP02, PERF04-BP06 — Serve content close to users with Amazon CloudFront or AWS Global Accelerator to reduce latency.
• No cost visibility shown COST01-BP03, COST01-BP06, COST03-BP05 — Set AWS Budgets with alert thresholds, enable Cost Anomaly Detection and cost allocation tags so spend maps to this workload.
• No retrieval / grounding data source shown GENPERF04-BP01 — Ground responses in enterprise data (RAG) and test embeddings for retrieval latency and relevance.
• Single-Region model inference GENREL05-BP01 — Plan for throttling and quota limits (retries, queues, provisioned throughput) and consider cross-Region inference profiles or a fallback model.
• Model cost controls GENCOST01-BP01 — Select the smallest model that meets quality targets; use prompt caching and batch inference where possible; track cost per request.
• Agents and excessive agency GENSEC05-BP01 — Limit agent tool permissions (least privilege, deterministic policy at the tool boundary) and add human approval for high-impact actions.
• Model and hosting efficiency GENSUS03-BP01 — Prefer right-sized or distilled models and serverless inference; avoid always-on endpoints for spiky traffic.

Cross-pillar trade-offs

• Guardrails on model traffic Security ↔ Cost optimization ↔ Performance efficiency
  Guardrails cost $50.00/month (38% of AI spend) and add a synchronous screening step to each model call. Resolution: Apply the strictest policies where harm is highest (final responses, PII) and measure per-policy value before enabling every policy on every call.

Eisenhower prioritization

Prioritized remediation plan

Next steps

1. Add the missing process, configuration and runtime evidence to turn Cannot Determine practices into assessed ones.
2. Re-run the review after changes, and when the architecture or documentation changes.

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