[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-bedrock-adoption-readiness":3,"mdc-9dir4x-key":55,"related-repo-aws-bedrock-adoption-readiness":2105,"related-org-aws-bedrock-adoption-readiness":2210},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":27,"repoUrl":28,"updatedAt":29,"license":30,"forks":31,"topics":32,"repo":50,"sourceUrl":53,"mdContent":54},"bedrock-adoption-readiness","assess Amazon Bedrock production readiness","Amazon Bedrock production readiness assessment covering IAM governance, data retention (ZDR), quota and capacity headroom, and operational observability across Standard Bedrock and Mantle surfaces. Use this skill when a user asks to review Bedrock readiness, assess Bedrock security posture, evaluate quota headroom, check ZDR configuration, validate Bedrock operational setup, or prepare for Bedrock production deployment. Triggers on \"Bedrock readiness review\", \"am I ready for Bedrock production\", \"Bedrock security assessment\", \"check my Bedrock quotas\", \"Bedrock adoption audit\", \"Bedrock operational review\", or \"assess my Bedrock environment\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"Compliance","compliance",{"name":20,"slug":21,"type":15},"LLM","llm",{"name":23,"slug":24,"type":15},"Governance","governance",{"name":26,"slug":8,"type":15},"AWS",35,"https:\u002F\u002Fgithub.com\u002Faws\u002Ftools-for-devops-agent","2026-08-27T13:31:49.236601",null,30,[33,34,35,36,37,8,38,39,40,41,42,43,44,45,46,47,48,49],"agent-skills","agentic-ai","agents","ai-agents","aiops","aws-devops-agent","cloud-operations","custom-agents","devops","devops-agent-skills","frontier-agent","incident-response","operational-excellence","root-cause-analysis","skills","sre","support",{"repoUrl":28,"stars":27,"forks":31,"topics":51,"description":52},[33,34,35,36,37,8,38,39,40,41,42,43,44,45,46,47,48,49],"Open-source tools for AWS DevOps Agent - extend DevOps Agent with ready-to-use skills, custom agents, and other tools, for incident response, root cause analysis, and operational troubleshooting","https:\u002F\u002Fgithub.com\u002Faws\u002Ftools-for-devops-agent\u002Ftree\u002FHEAD\u002Fskills\u002Fbedrock-adoption-readiness","---\nname: bedrock-adoption-readiness\ndescription: >\n  Amazon Bedrock production readiness assessment covering IAM governance, data retention\n  (ZDR), quota and capacity headroom, and operational observability across Standard Bedrock\n  and Mantle surfaces. Use this skill when a user asks to review Bedrock readiness, assess\n  Bedrock security posture, evaluate quota headroom, check ZDR configuration, validate\n  Bedrock operational setup, or prepare for Bedrock production deployment. Triggers on\n  \"Bedrock readiness review\", \"am I ready for Bedrock production\", \"Bedrock security\n  assessment\", \"check my Bedrock quotas\", \"Bedrock adoption audit\", \"Bedrock operational\n  review\", or \"assess my Bedrock environment\".\nmetadata:\n  version: \"1.0.0\"\n  author: sruved\n  aws-devops-agent-skills.agent-types: \"Chat tasks, Evaluation\"\n  aws-devops-agent-skills.aws-services: \"Amazon Bedrock\"\n  aws-devops-agent-skills.technical-domains: \"AI\u002FML\"\n---\n\n# Bedrock Adoption Readiness Assessment\n\nAssess an AWS account's readiness to run Amazon Bedrock at production scale. Covers four dimensions: IAM governance, data retention (ZDR), quota and capacity headroom, and operational observability. Operates across both Standard Bedrock and Mantle (OpenAI models) surfaces.\n\n## Important: Two Surfaces\n\nBedrock operates across two control planes. Both must be assessed.\n\n| | Standard Bedrock | Mantle (OpenAI models) |\n|---|---|---|\n| CloudWatch namespace | `AWS\u002FBedrock` | `AWS\u002FBedrockMantle` |\n| Metric names | `Invocations`, `InputTokenCount`, `OutputTokenCount` | `Inferences`, `TotalInputTokens`, `TotalOutputTokens` |\n| CW dimensions | `ModelId` | `Model`, `Project` |\n| IAM prefix | `bedrock:`, `bedrock-runtime:` | `bedrock-mantle:` |\n| Cost discriminator | No marker in USAGE_TYPE | `-mantle-` substring in USAGE_TYPE |\n| Cross-region inference | Yes - Geographic (`us.`, `eu.`, `apac.` prefixes) and Global (`global.` prefix) | No (in-region only) |\n\n## When to Use\n\nActivate this skill when the user asks to:\n- Review or assess Bedrock production readiness\n- Audit Bedrock IAM permissions or access governance\n- Check Bedrock quota utilization or capacity planning\n- Evaluate Zero Data Retention (ZDR) configuration\n- Validate Bedrock operational monitoring setup\n- Prepare for scaling Bedrock usage in production\n\n## Dimension States\n\nEvery dimension reports one of three states:\n- **ASSESSED**: Data collected, rules applied, findings produced\n- **NOT_ASSESSED**: Collection failed or data unreachable (state the reason)\n- **INSUFFICIENT_DATA**: Data returned but volume too low for meaningful analysis\n\nA dimension producing zero findings after successful collection = GOOD. A dimension producing zero findings because collection failed = NOT_ASSESSED. These must render differently.\n\n## Step 1: Identify Scope\n\nAsk the user:\n- Which AWS account to assess\n- Which regions to review (if unknown, discover by listing metrics in us-east-1, us-east-2, us-west-2)\n- Whether they have specific concerns or want a full assessment\n\n## Step 2: Discover Active Regions and Models\n\nFor each candidate region, check both namespaces:\n- List metrics in `AWS\u002FBedrock` namespace\n- List metrics in `AWS\u002FBedrockMantle` namespace\n\nAny region returning metrics on either namespace is in scope. Record which ModelId\u002FModel values appear - these identify active models for D2, D3, and later dimensions.\n\n## Step 3: Collect Data\n\n### 3.1 Standard Bedrock Metrics (7 days, per active region)\n\nQuery without dimensions for aggregates:\n- `Invocations` (Sum)\n- `InvocationThrottles` (Sum)\n- `InvocationLatency` (Average)\n- `InputTokenCount` (Sum)\n- `OutputTokenCount` (Sum)\n- `CacheReadInputTokenCount` (Sum) - NOTE: correct metric name, NOT `CacheReadInputTokens`\n- `CacheWriteInputTokenCount` (Sum)\n- `InvocationServerErrors` (Sum)\n- `InvocationClientErrors` (Sum)\n\nThen query WITH `ModelId` dimension for per-model quota utilization:\n- `EstimatedTPMQuotaUsage` (Maximum) per ModelId discovered in Step 2\n\n### 3.2 Mantle Metrics (7 days, per active region)\n\nQuery at zero-dimension for aggregates:\n- `Inferences` (Sum)\n- `TotalInputTokens` (Sum)\n- `TotalOutputTokens` (Sum)\n- `InferenceClientErrors` (Sum)\n\nThen per-Model for attribution (TotalInputTokens supports Model dimension):\n- `TotalInputTokens` with `Model` dimension per model discovered in Step 2\n- `TotalOutputTokens` with `Model` dimension\n\nFor non-GPT-5.x models that emit `BurnDownConsumed`, query with `(Model, Project)` pair.\n\n### 3.3 Service Quotas\n\nList all quotas under `serviceCode: bedrock`. Paginate fully (can be 1,001+).\n\nSeparate:\n- Standard Bedrock quotas: names NOT prefixed with `[bedrock-mantle endpoint]`\n- Mantle quotas: names prefixed with `[bedrock-mantle endpoint]`\n\n### 3.4 IAM (full depth)\n\n**Step A**: List all roles in the account.\n\n**Step B**: For each role, get attached managed policies AND inline policies.\n\n**Step C**: For inline policies, get the policy document directly.\n\n**Step D**: For managed policies, get the policy version document using the DefaultVersionId.\n\nSearch all policy documents for: `bedrock:`, `bedrock-runtime:`, `bedrock-mantle:`, `bedrock-agentcore:`, and bare `*` in Action fields.\n\nNote: CDK\u002FCloudFormation execution roles with `*` are expected. Flag as INFO, not CRITICAL.\n\nIf policy documents cannot be retrieved (only metadata returned), mark D1 as NOT_ASSESSED: \"IAM policy documents not retrieved.\"\n\n### 3.5 Alarms and Observability\n\nList all CloudWatch alarms in each active region. Identify which reference Bedrock metrics.\n\nCheck model invocation logging configuration. If the API returns empty response, logging is DISABLED.\n\nCheck CloudTrail event selectors for `bedrock-runtime.amazonaws.com` data events (management events alone do not capture model invocations).\n\n### 3.6 Guardrails\n\nList Bedrock guardrails. Zero guardrails on a production deployment using Standard Bedrock (`bedrock-runtime`) is a finding. Note: Guardrails are NOT available on the Mantle endpoint (`bedrock-mantle`). Do not flag missing guardrails for Mantle-only workloads.\n\n### 3.7 VPC Endpoints\n\nCheck for VPC endpoints for all Bedrock services:\n- `com.amazonaws.\u003Cregion>.bedrock` (Control Plane)\n- `com.amazonaws.\u003Cregion>.bedrock-runtime` (Runtime)\n- `com.amazonaws.\u003Cregion>.bedrock-mantle` (Mantle\u002FOpenAI)\n- `com.amazonaws.\u003Cregion>.bedrock-agent` (Agents Build-time)\n- `com.amazonaws.\u003Cregion>.bedrock-agent-runtime` (Agents Runtime)\n\nRef: https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fvpc-interface-endpoints.html\n\n### 3.8 SCPs (if accessible)\n\nList service control policies at the organization level. If access denied (member account), mark SCP check as NOT_ASSESSED: \"organization-level access required.\"\n\n### 3.9 Data Retention (classic plane)\n\nAttempt to read account-level data retention configuration via `GetAccountDataRetention`. \n\nIf the call succeeds, record the mode per region. If it fails (permission not in DA policy), use fallback: check if any Covered Model (Fable 5, Mythos 5) appears in the invoked ModelId list from Step 3.1. Covered Models cannot be invoked without provider data sharing being active - their presence in metrics IS retention evidence.\n\n## Step 4: Analyze - Four Dimensions\n\n### Dimension 1: IAM & Access Governance\n\nAnalyze policy documents from Step 3.4:\n\n| Finding | Severity |\n|---|---|\n| Bare `*` Action on non-deployment role | CRITICAL |\n| Any bedrock prefix with `*` resource on non-deployment role | HIGH |\n| No SCP referencing Bedrock (regulated customer) | HIGH (or NOT_ASSESSED if org access unavailable) |\n| Zero guardrails configured (Standard Bedrock workloads) | HIGH |\n| No VPC endpoints for bedrock-runtime | MEDIUM |\n| Broad permissions on CDK\u002Fdeployment roles | INFO |\n\n### Dimension 2: Retention & Zero Data Retention (ZDR)\n\nThree retention regimes exist:\n\n| | Claude (standard) | Claude Covered Models (Fable 5, Mythos 5) | OpenAI GPT-5.x |\n|---|---|---|---|\n| ZDR obtainable? | Yes, self-service | NO - mandatory 30-day retention | Yes, must be granted |\n| Scope | Set the mode | Cannot be changed | Per account, per model, per region |\n\nAssessment:\n\n1. If `GetAccountDataRetention` succeeded, report the mode per region\n2. If Covered Model detected in invocation metrics, flag: provider data sharing is active\n3. If GPT-5.x models present in Mantle metrics, note: ZDR must be explicitly granted per account\u002Fmodel\u002Fregion\n4. Check SCP results for retention enforcement policies\n\n| Finding | Severity |\n|---|---|\n| Covered Model invoked without documented awareness | CRITICAL (regulated) \u002F HIGH (general) |\n| GPT-5.x in use, ZDR status unknown | HIGH (regulated) \u002F MEDIUM (general) |\n| No SCP enforcing retention policy (regulated customer) | HIGH |\n| Model invocation logging disabled | HIGH |\n| Retention state unreadable | UNRESOLVED - flag for customer confirmation |\n\n### Dimension 3: Quota & Capacity Headroom\n\nCompare PER-MODEL utilization against PER-MODEL quotas. Never compare an account aggregate against a per-model limit.\n\nFor Standard Bedrock:\n- Use per-ModelId `EstimatedTPMQuotaUsage` from Step 3.1\n- Compare each model's 7-day peak against its specific quota from Step 3.3\n- Cache awareness: cache reads do NOT consume quota, cache writes DO\n\nFor Mantle GPT-5.x (where `BurnDownConsumed` does not emit):\n- Compute utilization from per-Model `TotalInputTokens + TotalOutputTokens`\n- Compare against `[bedrock-mantle endpoint]` quota for that model\n- Note: output tokens burn at 5:1 rate for Claude Opus\u002FSonnet 4.5+ (real consumption = InputTokenCount + CacheWriteInputTokenCount + OutputTokenCount x 5)\n\n| Finding | Severity |\n|---|---|\n| Any model's peak utilization >90% of its quota | CRITICAL |\n| Any `InvocationThrottles` > 0 in 7 days | HIGH |\n| Any model's peak >70% with growth trend | HIGH |\n| No CRIS enabled + >50% utilization (Standard only, N\u002FA Mantle) | MEDIUM |\n\nNote: CRIS is detectable via inference profile prefixes in ModelId - `us.`, `eu.`, `apac.` (geographic) or `global.` (global). Absence of any prefix means single-region only.\n\nIf per-model quota data cannot be joined to metrics (naming mismatch), mark as INSUFFICIENT_DATA with available numbers shown.\n\n### Dimension 6: Operational Observability\n\nCheck which monitoring is in place. Reference: CWR checklist `bedrock` v2.0 defines alarm checks with thresholds. Key checks:\n\n- Throttle alarm (InvocationThrottles > 0)\n- Server error alarm (InvocationServerErrors as % of Invocations)\n- Client error alarm (InvocationClientErrors as % of Invocations)\n- Quota utilization alarm (EstimatedTPMQuotaUsage approaching limit)\n- Latency alarm (InvocationLatency p90 by model family)\n- Cost alarm\n\nAlso check measured values against thresholds:\n- If `InvocationServerErrors \u002F Invocations > 1%` = active breach, HIGH\n- If `InvocationClientErrors \u002F Invocations > 5%` = active breach, HIGH\n\n| Finding | Severity |\n|---|---|\n| Measured metric actively breaching a threshold | HIGH |\n| Zero Bedrock-related alarms configured | HIGH |\n| No throttle monitoring | HIGH |\n| Model invocation logging disabled | HIGH |\n| CloudTrail data events not enabled for bedrock-runtime | MEDIUM |\n| Missing cost alarm | MEDIUM |\n\nNote on metric names: The correct CloudWatch names are `InvocationThrottles` (not `ThrottledEvents`) and `EstimatedTPMQuotaUsage` (not `QuotaUtilization`). Some documentation uses alternate names that return zero datapoints.\n\n## Step 5: Generate Report\n\nOutput format:\n\n```\n# Bedrock Adoption Readiness Assessment\nAccount: \u003Caccount-id> | Regions: \u003Clist> | Date: \u003Ctoday>\nSurfaces: Standard Bedrock [Y\u002FN] | Mantle [Y\u002FN]\n7-Day Volume: \u003CN> invocations | 30-Day Spend: $\u003Camount>\nAssessment: READY \u002F READY WITH ACTIONS \u002F NOT READY\n\n## Dimension Status\n- D1 IAM: [ASSESSED \u002F NOT_ASSESSED: reason]\n- D2 Retention: [ASSESSED \u002F UNRESOLVED: needs confirmation]\n- D3 Quota: [ASSESSED \u002F INSUFFICIENT_DATA]\n- D6 Observability: [ASSESSED]\n\n## Findings\n[Sorted by severity, then dimension]\n\n| # | Finding | Severity | Dimension | Recommendation |\n|---|---------|----------|-----------|----------------|\n\n## Model Inventory\n| Model | Surface | Region | 7-Day Invocations | TPM Peak | Quota | % Used |\n|-------|---------|--------|-------------------|----------|-------|--------|\n\n## Priority Actions\n1. [Highest severity + remediation]\n2. [Next]\n3. [Next]\n\n## Next Steps\n- Immediate (CRITICAL)\n- This week (HIGH)\n- This month (MEDIUM)\n```\n\nVerdict thresholds:\n- **READY**: 0 critical, \u003C=2 high, 0 unresolved, 0 NOT_ASSESSED\n- **READY WITH ACTIONS**: 0 critical, (>2 high OR any unresolved OR any NOT_ASSESSED)\n- **NOT READY**: Any critical finding\n\n## Severity Definitions\n\n| Severity | Definition | SLA |\n|----------|-----------|-----|\n| CRITICAL | Immediate risk to security, data exposure, or unbounded cost | Fix before production use |\n| HIGH | Significant gap that will cause issues at scale | Fix within 1 week |\n| MEDIUM | Notable improvement opportunity | Plan within 30 days |\n| LOW | Minor optimization | Address when convenient |\n| INFO | Observation, no action required | N\u002FA |\n\n## References\n\n- Bedrock Security: https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fsecurity.html\n- Bedrock Quotas: https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fquotas.html\n- Cross-Region Inference: https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fcross-region-inference.html\n- Model Invocation Logging: https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fmodel-invocation-logging.html\n- Inference Profiles: https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Finference-profiles.html\n- Data Retention: https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fdata-retention.html\n- Enforce ZDR with SCPs: https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fsecurity\u002Fenforce-zero-data-retention-on-amazon-bedrock-with-bedrock-projects-and-service-control-policies\u002F\n- CloudWatch Metrics TTFT & EstimatedTPMQuotaUsage: https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fimprove-operational-visibility-for-inference-workloads-on-amazon-bedrock-with-new-cloudwatch-metrics-for-ttft-and-estimated-quota-consumption\u002F\n",{"data":56,"body":64},{"name":4,"description":6,"metadata":57},{"version":58,"author":59,"aws-devops-agent-skills":60},"1.0.0","sruved",{"agent-types":61,"aws-services":62,"technical-domains":63},"Chat tasks, Evaluation","Amazon Bedrock","AI\u002FML",{"type":65,"children":66},"root",[67,76,82,89,94,345,351,356,391,397,402,436,441,447,452,470,476,481,506,511,517,524,529,628,640,654,660,665,705,710,746,767,773,786,791,815,821,831,841,851,861,900,912,917,923,928,933,946,952,973,979,984,1042,1055,1061,1066,1072,1085,1090,1096,1102,1107,1220,1226,1231,1307,1312,1343,1426,1432,1437,1442,1467,1479,1510,1585,1616,1621,1627,1640,1673,1678,1704,1795,1829,1835,1840,1852,1857,1890,1896,2008,2014],{"type":68,"tag":69,"props":70,"children":72},"element","h1",{"id":71},"bedrock-adoption-readiness-assessment",[73],{"type":74,"value":75},"text","Bedrock Adoption Readiness Assessment",{"type":68,"tag":77,"props":78,"children":79},"p",{},[80],{"type":74,"value":81},"Assess an AWS account's readiness to run Amazon Bedrock at production scale. Covers four dimensions: IAM governance, data retention (ZDR), quota and capacity headroom, and operational observability. Operates across both Standard Bedrock and Mantle (OpenAI models) surfaces.",{"type":68,"tag":83,"props":84,"children":86},"h2",{"id":85},"important-two-surfaces",[87],{"type":74,"value":88},"Important: Two Surfaces",{"type":68,"tag":77,"props":90,"children":91},{},[92],{"type":74,"value":93},"Bedrock operates across two control planes. Both must be assessed.",{"type":68,"tag":95,"props":96,"children":97},"table",{},[98,120],{"type":68,"tag":99,"props":100,"children":101},"thead",{},[102],{"type":68,"tag":103,"props":104,"children":105},"tr",{},[106,110,115],{"type":68,"tag":107,"props":108,"children":109},"th",{},[],{"type":68,"tag":107,"props":111,"children":112},{},[113],{"type":74,"value":114},"Standard Bedrock",{"type":68,"tag":107,"props":116,"children":117},{},[118],{"type":74,"value":119},"Mantle (OpenAI models)",{"type":68,"tag":121,"props":122,"children":123},"tbody",{},[124,152,207,240,273,297],{"type":68,"tag":103,"props":125,"children":126},{},[127,133,143],{"type":68,"tag":128,"props":129,"children":130},"td",{},[131],{"type":74,"value":132},"CloudWatch namespace",{"type":68,"tag":128,"props":134,"children":135},{},[136],{"type":68,"tag":137,"props":138,"children":140},"code",{"className":139},[],[141],{"type":74,"value":142},"AWS\u002FBedrock",{"type":68,"tag":128,"props":144,"children":145},{},[146],{"type":68,"tag":137,"props":147,"children":149},{"className":148},[],[150],{"type":74,"value":151},"AWS\u002FBedrockMantle",{"type":68,"tag":103,"props":153,"children":154},{},[155,160,184],{"type":68,"tag":128,"props":156,"children":157},{},[158],{"type":74,"value":159},"Metric names",{"type":68,"tag":128,"props":161,"children":162},{},[163,169,171,177,178],{"type":68,"tag":137,"props":164,"children":166},{"className":165},[],[167],{"type":74,"value":168},"Invocations",{"type":74,"value":170},", ",{"type":68,"tag":137,"props":172,"children":174},{"className":173},[],[175],{"type":74,"value":176},"InputTokenCount",{"type":74,"value":170},{"type":68,"tag":137,"props":179,"children":181},{"className":180},[],[182],{"type":74,"value":183},"OutputTokenCount",{"type":68,"tag":128,"props":185,"children":186},{},[187,193,194,200,201],{"type":68,"tag":137,"props":188,"children":190},{"className":189},[],[191],{"type":74,"value":192},"Inferences",{"type":74,"value":170},{"type":68,"tag":137,"props":195,"children":197},{"className":196},[],[198],{"type":74,"value":199},"TotalInputTokens",{"type":74,"value":170},{"type":68,"tag":137,"props":202,"children":204},{"className":203},[],[205],{"type":74,"value":206},"TotalOutputTokens",{"type":68,"tag":103,"props":208,"children":209},{},[210,215,224],{"type":68,"tag":128,"props":211,"children":212},{},[213],{"type":74,"value":214},"CW dimensions",{"type":68,"tag":128,"props":216,"children":217},{},[218],{"type":68,"tag":137,"props":219,"children":221},{"className":220},[],[222],{"type":74,"value":223},"ModelId",{"type":68,"tag":128,"props":225,"children":226},{},[227,233,234],{"type":68,"tag":137,"props":228,"children":230},{"className":229},[],[231],{"type":74,"value":232},"Model",{"type":74,"value":170},{"type":68,"tag":137,"props":235,"children":237},{"className":236},[],[238],{"type":74,"value":239},"Project",{"type":68,"tag":103,"props":241,"children":242},{},[243,248,264],{"type":68,"tag":128,"props":244,"children":245},{},[246],{"type":74,"value":247},"IAM prefix",{"type":68,"tag":128,"props":249,"children":250},{},[251,257,258],{"type":68,"tag":137,"props":252,"children":254},{"className":253},[],[255],{"type":74,"value":256},"bedrock:",{"type":74,"value":170},{"type":68,"tag":137,"props":259,"children":261},{"className":260},[],[262],{"type":74,"value":263},"bedrock-runtime:",{"type":68,"tag":128,"props":265,"children":266},{},[267],{"type":68,"tag":137,"props":268,"children":270},{"className":269},[],[271],{"type":74,"value":272},"bedrock-mantle:",{"type":68,"tag":103,"props":274,"children":275},{},[276,281,286],{"type":68,"tag":128,"props":277,"children":278},{},[279],{"type":74,"value":280},"Cost discriminator",{"type":68,"tag":128,"props":282,"children":283},{},[284],{"type":74,"value":285},"No marker in USAGE_TYPE",{"type":68,"tag":128,"props":287,"children":288},{},[289,295],{"type":68,"tag":137,"props":290,"children":292},{"className":291},[],[293],{"type":74,"value":294},"-mantle-",{"type":74,"value":296}," substring in USAGE_TYPE",{"type":68,"tag":103,"props":298,"children":299},{},[300,305,340],{"type":68,"tag":128,"props":301,"children":302},{},[303],{"type":74,"value":304},"Cross-region inference",{"type":68,"tag":128,"props":306,"children":307},{},[308,310,316,317,323,324,330,332,338],{"type":74,"value":309},"Yes - Geographic (",{"type":68,"tag":137,"props":311,"children":313},{"className":312},[],[314],{"type":74,"value":315},"us.",{"type":74,"value":170},{"type":68,"tag":137,"props":318,"children":320},{"className":319},[],[321],{"type":74,"value":322},"eu.",{"type":74,"value":170},{"type":68,"tag":137,"props":325,"children":327},{"className":326},[],[328],{"type":74,"value":329},"apac.",{"type":74,"value":331}," prefixes) and Global (",{"type":68,"tag":137,"props":333,"children":335},{"className":334},[],[336],{"type":74,"value":337},"global.",{"type":74,"value":339}," prefix)",{"type":68,"tag":128,"props":341,"children":342},{},[343],{"type":74,"value":344},"No (in-region only)",{"type":68,"tag":83,"props":346,"children":348},{"id":347},"when-to-use",[349],{"type":74,"value":350},"When to Use",{"type":68,"tag":77,"props":352,"children":353},{},[354],{"type":74,"value":355},"Activate this skill when the user asks to:",{"type":68,"tag":357,"props":358,"children":359},"ul",{},[360,366,371,376,381,386],{"type":68,"tag":361,"props":362,"children":363},"li",{},[364],{"type":74,"value":365},"Review or assess Bedrock production readiness",{"type":68,"tag":361,"props":367,"children":368},{},[369],{"type":74,"value":370},"Audit Bedrock IAM permissions or access governance",{"type":68,"tag":361,"props":372,"children":373},{},[374],{"type":74,"value":375},"Check Bedrock quota utilization or capacity planning",{"type":68,"tag":361,"props":377,"children":378},{},[379],{"type":74,"value":380},"Evaluate Zero Data Retention (ZDR) configuration",{"type":68,"tag":361,"props":382,"children":383},{},[384],{"type":74,"value":385},"Validate Bedrock operational monitoring setup",{"type":68,"tag":361,"props":387,"children":388},{},[389],{"type":74,"value":390},"Prepare for scaling Bedrock usage in production",{"type":68,"tag":83,"props":392,"children":394},{"id":393},"dimension-states",[395],{"type":74,"value":396},"Dimension States",{"type":68,"tag":77,"props":398,"children":399},{},[400],{"type":74,"value":401},"Every dimension reports one of three states:",{"type":68,"tag":357,"props":403,"children":404},{},[405,416,426],{"type":68,"tag":361,"props":406,"children":407},{},[408,414],{"type":68,"tag":409,"props":410,"children":411},"strong",{},[412],{"type":74,"value":413},"ASSESSED",{"type":74,"value":415},": Data collected, rules applied, findings produced",{"type":68,"tag":361,"props":417,"children":418},{},[419,424],{"type":68,"tag":409,"props":420,"children":421},{},[422],{"type":74,"value":423},"NOT_ASSESSED",{"type":74,"value":425},": Collection failed or data unreachable (state the reason)",{"type":68,"tag":361,"props":427,"children":428},{},[429,434],{"type":68,"tag":409,"props":430,"children":431},{},[432],{"type":74,"value":433},"INSUFFICIENT_DATA",{"type":74,"value":435},": Data returned but volume too low for meaningful analysis",{"type":68,"tag":77,"props":437,"children":438},{},[439],{"type":74,"value":440},"A dimension producing zero findings after successful collection = GOOD. A dimension producing zero findings because collection failed = NOT_ASSESSED. These must render differently.",{"type":68,"tag":83,"props":442,"children":444},{"id":443},"step-1-identify-scope",[445],{"type":74,"value":446},"Step 1: Identify Scope",{"type":68,"tag":77,"props":448,"children":449},{},[450],{"type":74,"value":451},"Ask the user:",{"type":68,"tag":357,"props":453,"children":454},{},[455,460,465],{"type":68,"tag":361,"props":456,"children":457},{},[458],{"type":74,"value":459},"Which AWS account to assess",{"type":68,"tag":361,"props":461,"children":462},{},[463],{"type":74,"value":464},"Which regions to review (if unknown, discover by listing metrics in us-east-1, us-east-2, us-west-2)",{"type":68,"tag":361,"props":466,"children":467},{},[468],{"type":74,"value":469},"Whether they have specific concerns or want a full assessment",{"type":68,"tag":83,"props":471,"children":473},{"id":472},"step-2-discover-active-regions-and-models",[474],{"type":74,"value":475},"Step 2: Discover Active Regions and Models",{"type":68,"tag":77,"props":477,"children":478},{},[479],{"type":74,"value":480},"For each candidate region, check both namespaces:",{"type":68,"tag":357,"props":482,"children":483},{},[484,496],{"type":68,"tag":361,"props":485,"children":486},{},[487,489,494],{"type":74,"value":488},"List metrics in ",{"type":68,"tag":137,"props":490,"children":492},{"className":491},[],[493],{"type":74,"value":142},{"type":74,"value":495}," namespace",{"type":68,"tag":361,"props":497,"children":498},{},[499,500,505],{"type":74,"value":488},{"type":68,"tag":137,"props":501,"children":503},{"className":502},[],[504],{"type":74,"value":151},{"type":74,"value":495},{"type":68,"tag":77,"props":507,"children":508},{},[509],{"type":74,"value":510},"Any region returning metrics on either namespace is in scope. Record which ModelId\u002FModel values appear - these identify active models for D2, D3, and later dimensions.",{"type":68,"tag":83,"props":512,"children":514},{"id":513},"step-3-collect-data",[515],{"type":74,"value":516},"Step 3: Collect Data",{"type":68,"tag":518,"props":519,"children":521},"h3",{"id":520},"_31-standard-bedrock-metrics-7-days-per-active-region",[522],{"type":74,"value":523},"3.1 Standard Bedrock Metrics (7 days, per active region)",{"type":68,"tag":77,"props":525,"children":526},{},[527],{"type":74,"value":528},"Query without dimensions for aggregates:",{"type":68,"tag":357,"props":530,"children":531},{},[532,542,552,563,572,581,598,608,618],{"type":68,"tag":361,"props":533,"children":534},{},[535,540],{"type":68,"tag":137,"props":536,"children":538},{"className":537},[],[539],{"type":74,"value":168},{"type":74,"value":541}," (Sum)",{"type":68,"tag":361,"props":543,"children":544},{},[545,551],{"type":68,"tag":137,"props":546,"children":548},{"className":547},[],[549],{"type":74,"value":550},"InvocationThrottles",{"type":74,"value":541},{"type":68,"tag":361,"props":553,"children":554},{},[555,561],{"type":68,"tag":137,"props":556,"children":558},{"className":557},[],[559],{"type":74,"value":560},"InvocationLatency",{"type":74,"value":562}," (Average)",{"type":68,"tag":361,"props":564,"children":565},{},[566,571],{"type":68,"tag":137,"props":567,"children":569},{"className":568},[],[570],{"type":74,"value":176},{"type":74,"value":541},{"type":68,"tag":361,"props":573,"children":574},{},[575,580],{"type":68,"tag":137,"props":576,"children":578},{"className":577},[],[579],{"type":74,"value":183},{"type":74,"value":541},{"type":68,"tag":361,"props":582,"children":583},{},[584,590,592],{"type":68,"tag":137,"props":585,"children":587},{"className":586},[],[588],{"type":74,"value":589},"CacheReadInputTokenCount",{"type":74,"value":591}," (Sum) - NOTE: correct metric name, NOT ",{"type":68,"tag":137,"props":593,"children":595},{"className":594},[],[596],{"type":74,"value":597},"CacheReadInputTokens",{"type":68,"tag":361,"props":599,"children":600},{},[601,607],{"type":68,"tag":137,"props":602,"children":604},{"className":603},[],[605],{"type":74,"value":606},"CacheWriteInputTokenCount",{"type":74,"value":541},{"type":68,"tag":361,"props":609,"children":610},{},[611,617],{"type":68,"tag":137,"props":612,"children":614},{"className":613},[],[615],{"type":74,"value":616},"InvocationServerErrors",{"type":74,"value":541},{"type":68,"tag":361,"props":619,"children":620},{},[621,627],{"type":68,"tag":137,"props":622,"children":624},{"className":623},[],[625],{"type":74,"value":626},"InvocationClientErrors",{"type":74,"value":541},{"type":68,"tag":77,"props":629,"children":630},{},[631,633,638],{"type":74,"value":632},"Then query WITH ",{"type":68,"tag":137,"props":634,"children":636},{"className":635},[],[637],{"type":74,"value":223},{"type":74,"value":639}," dimension for per-model quota utilization:",{"type":68,"tag":357,"props":641,"children":642},{},[643],{"type":68,"tag":361,"props":644,"children":645},{},[646,652],{"type":68,"tag":137,"props":647,"children":649},{"className":648},[],[650],{"type":74,"value":651},"EstimatedTPMQuotaUsage",{"type":74,"value":653}," (Maximum) per ModelId discovered in Step 2",{"type":68,"tag":518,"props":655,"children":657},{"id":656},"_32-mantle-metrics-7-days-per-active-region",[658],{"type":74,"value":659},"3.2 Mantle Metrics (7 days, per active region)",{"type":68,"tag":77,"props":661,"children":662},{},[663],{"type":74,"value":664},"Query at zero-dimension for aggregates:",{"type":68,"tag":357,"props":666,"children":667},{},[668,677,686,695],{"type":68,"tag":361,"props":669,"children":670},{},[671,676],{"type":68,"tag":137,"props":672,"children":674},{"className":673},[],[675],{"type":74,"value":192},{"type":74,"value":541},{"type":68,"tag":361,"props":678,"children":679},{},[680,685],{"type":68,"tag":137,"props":681,"children":683},{"className":682},[],[684],{"type":74,"value":199},{"type":74,"value":541},{"type":68,"tag":361,"props":687,"children":688},{},[689,694],{"type":68,"tag":137,"props":690,"children":692},{"className":691},[],[693],{"type":74,"value":206},{"type":74,"value":541},{"type":68,"tag":361,"props":696,"children":697},{},[698,704],{"type":68,"tag":137,"props":699,"children":701},{"className":700},[],[702],{"type":74,"value":703},"InferenceClientErrors",{"type":74,"value":541},{"type":68,"tag":77,"props":706,"children":707},{},[708],{"type":74,"value":709},"Then per-Model for attribution (TotalInputTokens supports Model dimension):",{"type":68,"tag":357,"props":711,"children":712},{},[713,730],{"type":68,"tag":361,"props":714,"children":715},{},[716,721,723,728],{"type":68,"tag":137,"props":717,"children":719},{"className":718},[],[720],{"type":74,"value":199},{"type":74,"value":722}," with ",{"type":68,"tag":137,"props":724,"children":726},{"className":725},[],[727],{"type":74,"value":232},{"type":74,"value":729}," dimension per model discovered in Step 2",{"type":68,"tag":361,"props":731,"children":732},{},[733,738,739,744],{"type":68,"tag":137,"props":734,"children":736},{"className":735},[],[737],{"type":74,"value":206},{"type":74,"value":722},{"type":68,"tag":137,"props":740,"children":742},{"className":741},[],[743],{"type":74,"value":232},{"type":74,"value":745}," dimension",{"type":68,"tag":77,"props":747,"children":748},{},[749,751,757,759,765],{"type":74,"value":750},"For non-GPT-5.x models that emit ",{"type":68,"tag":137,"props":752,"children":754},{"className":753},[],[755],{"type":74,"value":756},"BurnDownConsumed",{"type":74,"value":758},", query with ",{"type":68,"tag":137,"props":760,"children":762},{"className":761},[],[763],{"type":74,"value":764},"(Model, Project)",{"type":74,"value":766}," pair.",{"type":68,"tag":518,"props":768,"children":770},{"id":769},"_33-service-quotas",[771],{"type":74,"value":772},"3.3 Service Quotas",{"type":68,"tag":77,"props":774,"children":775},{},[776,778,784],{"type":74,"value":777},"List all quotas under ",{"type":68,"tag":137,"props":779,"children":781},{"className":780},[],[782],{"type":74,"value":783},"serviceCode: bedrock",{"type":74,"value":785},". Paginate fully (can be 1,001+).",{"type":68,"tag":77,"props":787,"children":788},{},[789],{"type":74,"value":790},"Separate:",{"type":68,"tag":357,"props":792,"children":793},{},[794,805],{"type":68,"tag":361,"props":795,"children":796},{},[797,799],{"type":74,"value":798},"Standard Bedrock quotas: names NOT prefixed with ",{"type":68,"tag":137,"props":800,"children":802},{"className":801},[],[803],{"type":74,"value":804},"[bedrock-mantle endpoint]",{"type":68,"tag":361,"props":806,"children":807},{},[808,810],{"type":74,"value":809},"Mantle quotas: names prefixed with ",{"type":68,"tag":137,"props":811,"children":813},{"className":812},[],[814],{"type":74,"value":804},{"type":68,"tag":518,"props":816,"children":818},{"id":817},"_34-iam-full-depth",[819],{"type":74,"value":820},"3.4 IAM (full depth)",{"type":68,"tag":77,"props":822,"children":823},{},[824,829],{"type":68,"tag":409,"props":825,"children":826},{},[827],{"type":74,"value":828},"Step A",{"type":74,"value":830},": List all roles in the account.",{"type":68,"tag":77,"props":832,"children":833},{},[834,839],{"type":68,"tag":409,"props":835,"children":836},{},[837],{"type":74,"value":838},"Step B",{"type":74,"value":840},": For each role, get attached managed policies AND inline policies.",{"type":68,"tag":77,"props":842,"children":843},{},[844,849],{"type":68,"tag":409,"props":845,"children":846},{},[847],{"type":74,"value":848},"Step C",{"type":74,"value":850},": For inline policies, get the policy document directly.",{"type":68,"tag":77,"props":852,"children":853},{},[854,859],{"type":68,"tag":409,"props":855,"children":856},{},[857],{"type":74,"value":858},"Step D",{"type":74,"value":860},": For managed policies, get the policy version document using the DefaultVersionId.",{"type":68,"tag":77,"props":862,"children":863},{},[864,866,871,872,877,878,883,884,890,892,898],{"type":74,"value":865},"Search all policy documents for: ",{"type":68,"tag":137,"props":867,"children":869},{"className":868},[],[870],{"type":74,"value":256},{"type":74,"value":170},{"type":68,"tag":137,"props":873,"children":875},{"className":874},[],[876],{"type":74,"value":263},{"type":74,"value":170},{"type":68,"tag":137,"props":879,"children":881},{"className":880},[],[882],{"type":74,"value":272},{"type":74,"value":170},{"type":68,"tag":137,"props":885,"children":887},{"className":886},[],[888],{"type":74,"value":889},"bedrock-agentcore:",{"type":74,"value":891},", and bare ",{"type":68,"tag":137,"props":893,"children":895},{"className":894},[],[896],{"type":74,"value":897},"*",{"type":74,"value":899}," in Action fields.",{"type":68,"tag":77,"props":901,"children":902},{},[903,905,910],{"type":74,"value":904},"Note: CDK\u002FCloudFormation execution roles with ",{"type":68,"tag":137,"props":906,"children":908},{"className":907},[],[909],{"type":74,"value":897},{"type":74,"value":911}," are expected. Flag as INFO, not CRITICAL.",{"type":68,"tag":77,"props":913,"children":914},{},[915],{"type":74,"value":916},"If policy documents cannot be retrieved (only metadata returned), mark D1 as NOT_ASSESSED: \"IAM policy documents not retrieved.\"",{"type":68,"tag":518,"props":918,"children":920},{"id":919},"_35-alarms-and-observability",[921],{"type":74,"value":922},"3.5 Alarms and Observability",{"type":68,"tag":77,"props":924,"children":925},{},[926],{"type":74,"value":927},"List all CloudWatch alarms in each active region. Identify which reference Bedrock metrics.",{"type":68,"tag":77,"props":929,"children":930},{},[931],{"type":74,"value":932},"Check model invocation logging configuration. If the API returns empty response, logging is DISABLED.",{"type":68,"tag":77,"props":934,"children":935},{},[936,938,944],{"type":74,"value":937},"Check CloudTrail event selectors for ",{"type":68,"tag":137,"props":939,"children":941},{"className":940},[],[942],{"type":74,"value":943},"bedrock-runtime.amazonaws.com",{"type":74,"value":945}," data events (management events alone do not capture model invocations).",{"type":68,"tag":518,"props":947,"children":949},{"id":948},"_36-guardrails",[950],{"type":74,"value":951},"3.6 Guardrails",{"type":68,"tag":77,"props":953,"children":954},{},[955,957,963,965,971],{"type":74,"value":956},"List Bedrock guardrails. Zero guardrails on a production deployment using Standard Bedrock (",{"type":68,"tag":137,"props":958,"children":960},{"className":959},[],[961],{"type":74,"value":962},"bedrock-runtime",{"type":74,"value":964},") is a finding. Note: Guardrails are NOT available on the Mantle endpoint (",{"type":68,"tag":137,"props":966,"children":968},{"className":967},[],[969],{"type":74,"value":970},"bedrock-mantle",{"type":74,"value":972},"). Do not flag missing guardrails for Mantle-only workloads.",{"type":68,"tag":518,"props":974,"children":976},{"id":975},"_37-vpc-endpoints",[977],{"type":74,"value":978},"3.7 VPC Endpoints",{"type":68,"tag":77,"props":980,"children":981},{},[982],{"type":74,"value":983},"Check for VPC endpoints for all Bedrock services:",{"type":68,"tag":357,"props":985,"children":986},{},[987,998,1009,1020,1031],{"type":68,"tag":361,"props":988,"children":989},{},[990,996],{"type":68,"tag":137,"props":991,"children":993},{"className":992},[],[994],{"type":74,"value":995},"com.amazonaws.\u003Cregion>.bedrock",{"type":74,"value":997}," (Control Plane)",{"type":68,"tag":361,"props":999,"children":1000},{},[1001,1007],{"type":68,"tag":137,"props":1002,"children":1004},{"className":1003},[],[1005],{"type":74,"value":1006},"com.amazonaws.\u003Cregion>.bedrock-runtime",{"type":74,"value":1008}," (Runtime)",{"type":68,"tag":361,"props":1010,"children":1011},{},[1012,1018],{"type":68,"tag":137,"props":1013,"children":1015},{"className":1014},[],[1016],{"type":74,"value":1017},"com.amazonaws.\u003Cregion>.bedrock-mantle",{"type":74,"value":1019}," (Mantle\u002FOpenAI)",{"type":68,"tag":361,"props":1021,"children":1022},{},[1023,1029],{"type":68,"tag":137,"props":1024,"children":1026},{"className":1025},[],[1027],{"type":74,"value":1028},"com.amazonaws.\u003Cregion>.bedrock-agent",{"type":74,"value":1030}," (Agents Build-time)",{"type":68,"tag":361,"props":1032,"children":1033},{},[1034,1040],{"type":68,"tag":137,"props":1035,"children":1037},{"className":1036},[],[1038],{"type":74,"value":1039},"com.amazonaws.\u003Cregion>.bedrock-agent-runtime",{"type":74,"value":1041}," (Agents Runtime)",{"type":68,"tag":77,"props":1043,"children":1044},{},[1045,1047],{"type":74,"value":1046},"Ref: ",{"type":68,"tag":1048,"props":1049,"children":1053},"a",{"href":1050,"rel":1051},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fvpc-interface-endpoints.html",[1052],"nofollow",[1054],{"type":74,"value":1050},{"type":68,"tag":518,"props":1056,"children":1058},{"id":1057},"_38-scps-if-accessible",[1059],{"type":74,"value":1060},"3.8 SCPs (if accessible)",{"type":68,"tag":77,"props":1062,"children":1063},{},[1064],{"type":74,"value":1065},"List service control policies at the organization level. If access denied (member account), mark SCP check as NOT_ASSESSED: \"organization-level access required.\"",{"type":68,"tag":518,"props":1067,"children":1069},{"id":1068},"_39-data-retention-classic-plane",[1070],{"type":74,"value":1071},"3.9 Data Retention (classic plane)",{"type":68,"tag":77,"props":1073,"children":1074},{},[1075,1077,1083],{"type":74,"value":1076},"Attempt to read account-level data retention configuration via ",{"type":68,"tag":137,"props":1078,"children":1080},{"className":1079},[],[1081],{"type":74,"value":1082},"GetAccountDataRetention",{"type":74,"value":1084},".",{"type":68,"tag":77,"props":1086,"children":1087},{},[1088],{"type":74,"value":1089},"If the call succeeds, record the mode per region. If it fails (permission not in DA policy), use fallback: check if any Covered Model (Fable 5, Mythos 5) appears in the invoked ModelId list from Step 3.1. Covered Models cannot be invoked without provider data sharing being active - their presence in metrics IS retention evidence.",{"type":68,"tag":83,"props":1091,"children":1093},{"id":1092},"step-4-analyze-four-dimensions",[1094],{"type":74,"value":1095},"Step 4: Analyze - Four Dimensions",{"type":68,"tag":518,"props":1097,"children":1099},{"id":1098},"dimension-1-iam-access-governance",[1100],{"type":74,"value":1101},"Dimension 1: IAM & Access Governance",{"type":68,"tag":77,"props":1103,"children":1104},{},[1105],{"type":74,"value":1106},"Analyze policy documents from Step 3.4:",{"type":68,"tag":95,"props":1108,"children":1109},{},[1110,1126],{"type":68,"tag":99,"props":1111,"children":1112},{},[1113],{"type":68,"tag":103,"props":1114,"children":1115},{},[1116,1121],{"type":68,"tag":107,"props":1117,"children":1118},{},[1119],{"type":74,"value":1120},"Finding",{"type":68,"tag":107,"props":1122,"children":1123},{},[1124],{"type":74,"value":1125},"Severity",{"type":68,"tag":121,"props":1127,"children":1128},{},[1129,1149,1169,1182,1194,1207],{"type":68,"tag":103,"props":1130,"children":1131},{},[1132,1144],{"type":68,"tag":128,"props":1133,"children":1134},{},[1135,1137,1142],{"type":74,"value":1136},"Bare ",{"type":68,"tag":137,"props":1138,"children":1140},{"className":1139},[],[1141],{"type":74,"value":897},{"type":74,"value":1143}," Action on non-deployment role",{"type":68,"tag":128,"props":1145,"children":1146},{},[1147],{"type":74,"value":1148},"CRITICAL",{"type":68,"tag":103,"props":1150,"children":1151},{},[1152,1164],{"type":68,"tag":128,"props":1153,"children":1154},{},[1155,1157,1162],{"type":74,"value":1156},"Any bedrock prefix with ",{"type":68,"tag":137,"props":1158,"children":1160},{"className":1159},[],[1161],{"type":74,"value":897},{"type":74,"value":1163}," resource on non-deployment role",{"type":68,"tag":128,"props":1165,"children":1166},{},[1167],{"type":74,"value":1168},"HIGH",{"type":68,"tag":103,"props":1170,"children":1171},{},[1172,1177],{"type":68,"tag":128,"props":1173,"children":1174},{},[1175],{"type":74,"value":1176},"No SCP referencing Bedrock (regulated customer)",{"type":68,"tag":128,"props":1178,"children":1179},{},[1180],{"type":74,"value":1181},"HIGH (or NOT_ASSESSED if org access unavailable)",{"type":68,"tag":103,"props":1183,"children":1184},{},[1185,1190],{"type":68,"tag":128,"props":1186,"children":1187},{},[1188],{"type":74,"value":1189},"Zero guardrails configured (Standard Bedrock workloads)",{"type":68,"tag":128,"props":1191,"children":1192},{},[1193],{"type":74,"value":1168},{"type":68,"tag":103,"props":1195,"children":1196},{},[1197,1202],{"type":68,"tag":128,"props":1198,"children":1199},{},[1200],{"type":74,"value":1201},"No VPC endpoints for bedrock-runtime",{"type":68,"tag":128,"props":1203,"children":1204},{},[1205],{"type":74,"value":1206},"MEDIUM",{"type":68,"tag":103,"props":1208,"children":1209},{},[1210,1215],{"type":68,"tag":128,"props":1211,"children":1212},{},[1213],{"type":74,"value":1214},"Broad permissions on CDK\u002Fdeployment roles",{"type":68,"tag":128,"props":1216,"children":1217},{},[1218],{"type":74,"value":1219},"INFO",{"type":68,"tag":518,"props":1221,"children":1223},{"id":1222},"dimension-2-retention-zero-data-retention-zdr",[1224],{"type":74,"value":1225},"Dimension 2: Retention & Zero Data Retention (ZDR)",{"type":68,"tag":77,"props":1227,"children":1228},{},[1229],{"type":74,"value":1230},"Three retention regimes exist:",{"type":68,"tag":95,"props":1232,"children":1233},{},[1234,1258],{"type":68,"tag":99,"props":1235,"children":1236},{},[1237],{"type":68,"tag":103,"props":1238,"children":1239},{},[1240,1243,1248,1253],{"type":68,"tag":107,"props":1241,"children":1242},{},[],{"type":68,"tag":107,"props":1244,"children":1245},{},[1246],{"type":74,"value":1247},"Claude (standard)",{"type":68,"tag":107,"props":1249,"children":1250},{},[1251],{"type":74,"value":1252},"Claude Covered Models (Fable 5, Mythos 5)",{"type":68,"tag":107,"props":1254,"children":1255},{},[1256],{"type":74,"value":1257},"OpenAI GPT-5.x",{"type":68,"tag":121,"props":1259,"children":1260},{},[1261,1284],{"type":68,"tag":103,"props":1262,"children":1263},{},[1264,1269,1274,1279],{"type":68,"tag":128,"props":1265,"children":1266},{},[1267],{"type":74,"value":1268},"ZDR obtainable?",{"type":68,"tag":128,"props":1270,"children":1271},{},[1272],{"type":74,"value":1273},"Yes, self-service",{"type":68,"tag":128,"props":1275,"children":1276},{},[1277],{"type":74,"value":1278},"NO - mandatory 30-day retention",{"type":68,"tag":128,"props":1280,"children":1281},{},[1282],{"type":74,"value":1283},"Yes, must be granted",{"type":68,"tag":103,"props":1285,"children":1286},{},[1287,1292,1297,1302],{"type":68,"tag":128,"props":1288,"children":1289},{},[1290],{"type":74,"value":1291},"Scope",{"type":68,"tag":128,"props":1293,"children":1294},{},[1295],{"type":74,"value":1296},"Set the mode",{"type":68,"tag":128,"props":1298,"children":1299},{},[1300],{"type":74,"value":1301},"Cannot be changed",{"type":68,"tag":128,"props":1303,"children":1304},{},[1305],{"type":74,"value":1306},"Per account, per model, per region",{"type":68,"tag":77,"props":1308,"children":1309},{},[1310],{"type":74,"value":1311},"Assessment:",{"type":68,"tag":1313,"props":1314,"children":1315},"ol",{},[1316,1328,1333,1338],{"type":68,"tag":361,"props":1317,"children":1318},{},[1319,1321,1326],{"type":74,"value":1320},"If ",{"type":68,"tag":137,"props":1322,"children":1324},{"className":1323},[],[1325],{"type":74,"value":1082},{"type":74,"value":1327}," succeeded, report the mode per region",{"type":68,"tag":361,"props":1329,"children":1330},{},[1331],{"type":74,"value":1332},"If Covered Model detected in invocation metrics, flag: provider data sharing is active",{"type":68,"tag":361,"props":1334,"children":1335},{},[1336],{"type":74,"value":1337},"If GPT-5.x models present in Mantle metrics, note: ZDR must be explicitly granted per account\u002Fmodel\u002Fregion",{"type":68,"tag":361,"props":1339,"children":1340},{},[1341],{"type":74,"value":1342},"Check SCP results for retention enforcement policies",{"type":68,"tag":95,"props":1344,"children":1345},{},[1346,1360],{"type":68,"tag":99,"props":1347,"children":1348},{},[1349],{"type":68,"tag":103,"props":1350,"children":1351},{},[1352,1356],{"type":68,"tag":107,"props":1353,"children":1354},{},[1355],{"type":74,"value":1120},{"type":68,"tag":107,"props":1357,"children":1358},{},[1359],{"type":74,"value":1125},{"type":68,"tag":121,"props":1361,"children":1362},{},[1363,1376,1389,1401,1413],{"type":68,"tag":103,"props":1364,"children":1365},{},[1366,1371],{"type":68,"tag":128,"props":1367,"children":1368},{},[1369],{"type":74,"value":1370},"Covered Model invoked without documented awareness",{"type":68,"tag":128,"props":1372,"children":1373},{},[1374],{"type":74,"value":1375},"CRITICAL (regulated) \u002F HIGH (general)",{"type":68,"tag":103,"props":1377,"children":1378},{},[1379,1384],{"type":68,"tag":128,"props":1380,"children":1381},{},[1382],{"type":74,"value":1383},"GPT-5.x in use, ZDR status unknown",{"type":68,"tag":128,"props":1385,"children":1386},{},[1387],{"type":74,"value":1388},"HIGH (regulated) \u002F MEDIUM (general)",{"type":68,"tag":103,"props":1390,"children":1391},{},[1392,1397],{"type":68,"tag":128,"props":1393,"children":1394},{},[1395],{"type":74,"value":1396},"No SCP enforcing retention policy (regulated customer)",{"type":68,"tag":128,"props":1398,"children":1399},{},[1400],{"type":74,"value":1168},{"type":68,"tag":103,"props":1402,"children":1403},{},[1404,1409],{"type":68,"tag":128,"props":1405,"children":1406},{},[1407],{"type":74,"value":1408},"Model invocation logging disabled",{"type":68,"tag":128,"props":1410,"children":1411},{},[1412],{"type":74,"value":1168},{"type":68,"tag":103,"props":1414,"children":1415},{},[1416,1421],{"type":68,"tag":128,"props":1417,"children":1418},{},[1419],{"type":74,"value":1420},"Retention state unreadable",{"type":68,"tag":128,"props":1422,"children":1423},{},[1424],{"type":74,"value":1425},"UNRESOLVED - flag for customer confirmation",{"type":68,"tag":518,"props":1427,"children":1429},{"id":1428},"dimension-3-quota-capacity-headroom",[1430],{"type":74,"value":1431},"Dimension 3: Quota & Capacity Headroom",{"type":68,"tag":77,"props":1433,"children":1434},{},[1435],{"type":74,"value":1436},"Compare PER-MODEL utilization against PER-MODEL quotas. Never compare an account aggregate against a per-model limit.",{"type":68,"tag":77,"props":1438,"children":1439},{},[1440],{"type":74,"value":1441},"For Standard Bedrock:",{"type":68,"tag":357,"props":1443,"children":1444},{},[1445,1457,1462],{"type":68,"tag":361,"props":1446,"children":1447},{},[1448,1450,1455],{"type":74,"value":1449},"Use per-ModelId ",{"type":68,"tag":137,"props":1451,"children":1453},{"className":1452},[],[1454],{"type":74,"value":651},{"type":74,"value":1456}," from Step 3.1",{"type":68,"tag":361,"props":1458,"children":1459},{},[1460],{"type":74,"value":1461},"Compare each model's 7-day peak against its specific quota from Step 3.3",{"type":68,"tag":361,"props":1463,"children":1464},{},[1465],{"type":74,"value":1466},"Cache awareness: cache reads do NOT consume quota, cache writes DO",{"type":68,"tag":77,"props":1468,"children":1469},{},[1470,1472,1477],{"type":74,"value":1471},"For Mantle GPT-5.x (where ",{"type":68,"tag":137,"props":1473,"children":1475},{"className":1474},[],[1476],{"type":74,"value":756},{"type":74,"value":1478}," does not emit):",{"type":68,"tag":357,"props":1480,"children":1481},{},[1482,1493,1505],{"type":68,"tag":361,"props":1483,"children":1484},{},[1485,1487],{"type":74,"value":1486},"Compute utilization from per-Model ",{"type":68,"tag":137,"props":1488,"children":1490},{"className":1489},[],[1491],{"type":74,"value":1492},"TotalInputTokens + TotalOutputTokens",{"type":68,"tag":361,"props":1494,"children":1495},{},[1496,1498,1503],{"type":74,"value":1497},"Compare against ",{"type":68,"tag":137,"props":1499,"children":1501},{"className":1500},[],[1502],{"type":74,"value":804},{"type":74,"value":1504}," quota for that model",{"type":68,"tag":361,"props":1506,"children":1507},{},[1508],{"type":74,"value":1509},"Note: output tokens burn at 5:1 rate for Claude Opus\u002FSonnet 4.5+ (real consumption = InputTokenCount + CacheWriteInputTokenCount + OutputTokenCount x 5)",{"type":68,"tag":95,"props":1511,"children":1512},{},[1513,1527],{"type":68,"tag":99,"props":1514,"children":1515},{},[1516],{"type":68,"tag":103,"props":1517,"children":1518},{},[1519,1523],{"type":68,"tag":107,"props":1520,"children":1521},{},[1522],{"type":74,"value":1120},{"type":68,"tag":107,"props":1524,"children":1525},{},[1526],{"type":74,"value":1125},{"type":68,"tag":121,"props":1528,"children":1529},{},[1530,1542,1561,1573],{"type":68,"tag":103,"props":1531,"children":1532},{},[1533,1538],{"type":68,"tag":128,"props":1534,"children":1535},{},[1536],{"type":74,"value":1537},"Any model's peak utilization >90% of its quota",{"type":68,"tag":128,"props":1539,"children":1540},{},[1541],{"type":74,"value":1148},{"type":68,"tag":103,"props":1543,"children":1544},{},[1545,1557],{"type":68,"tag":128,"props":1546,"children":1547},{},[1548,1550,1555],{"type":74,"value":1549},"Any ",{"type":68,"tag":137,"props":1551,"children":1553},{"className":1552},[],[1554],{"type":74,"value":550},{"type":74,"value":1556}," > 0 in 7 days",{"type":68,"tag":128,"props":1558,"children":1559},{},[1560],{"type":74,"value":1168},{"type":68,"tag":103,"props":1562,"children":1563},{},[1564,1569],{"type":68,"tag":128,"props":1565,"children":1566},{},[1567],{"type":74,"value":1568},"Any model's peak >70% with growth trend",{"type":68,"tag":128,"props":1570,"children":1571},{},[1572],{"type":74,"value":1168},{"type":68,"tag":103,"props":1574,"children":1575},{},[1576,1581],{"type":68,"tag":128,"props":1577,"children":1578},{},[1579],{"type":74,"value":1580},"No CRIS enabled + >50% utilization (Standard only, N\u002FA Mantle)",{"type":68,"tag":128,"props":1582,"children":1583},{},[1584],{"type":74,"value":1206},{"type":68,"tag":77,"props":1586,"children":1587},{},[1588,1590,1595,1596,1601,1602,1607,1609,1614],{"type":74,"value":1589},"Note: CRIS is detectable via inference profile prefixes in ModelId - ",{"type":68,"tag":137,"props":1591,"children":1593},{"className":1592},[],[1594],{"type":74,"value":315},{"type":74,"value":170},{"type":68,"tag":137,"props":1597,"children":1599},{"className":1598},[],[1600],{"type":74,"value":322},{"type":74,"value":170},{"type":68,"tag":137,"props":1603,"children":1605},{"className":1604},[],[1606],{"type":74,"value":329},{"type":74,"value":1608}," (geographic) or ",{"type":68,"tag":137,"props":1610,"children":1612},{"className":1611},[],[1613],{"type":74,"value":337},{"type":74,"value":1615}," (global). Absence of any prefix means single-region only.",{"type":68,"tag":77,"props":1617,"children":1618},{},[1619],{"type":74,"value":1620},"If per-model quota data cannot be joined to metrics (naming mismatch), mark as INSUFFICIENT_DATA with available numbers shown.",{"type":68,"tag":518,"props":1622,"children":1624},{"id":1623},"dimension-6-operational-observability",[1625],{"type":74,"value":1626},"Dimension 6: Operational Observability",{"type":68,"tag":77,"props":1628,"children":1629},{},[1630,1632,1638],{"type":74,"value":1631},"Check which monitoring is in place. Reference: CWR checklist ",{"type":68,"tag":137,"props":1633,"children":1635},{"className":1634},[],[1636],{"type":74,"value":1637},"bedrock",{"type":74,"value":1639}," v2.0 defines alarm checks with thresholds. Key checks:",{"type":68,"tag":357,"props":1641,"children":1642},{},[1643,1648,1653,1658,1663,1668],{"type":68,"tag":361,"props":1644,"children":1645},{},[1646],{"type":74,"value":1647},"Throttle alarm (InvocationThrottles > 0)",{"type":68,"tag":361,"props":1649,"children":1650},{},[1651],{"type":74,"value":1652},"Server error alarm (InvocationServerErrors as % of Invocations)",{"type":68,"tag":361,"props":1654,"children":1655},{},[1656],{"type":74,"value":1657},"Client error alarm (InvocationClientErrors as % of Invocations)",{"type":68,"tag":361,"props":1659,"children":1660},{},[1661],{"type":74,"value":1662},"Quota utilization alarm (EstimatedTPMQuotaUsage approaching limit)",{"type":68,"tag":361,"props":1664,"children":1665},{},[1666],{"type":74,"value":1667},"Latency alarm (InvocationLatency p90 by model family)",{"type":68,"tag":361,"props":1669,"children":1670},{},[1671],{"type":74,"value":1672},"Cost alarm",{"type":68,"tag":77,"props":1674,"children":1675},{},[1676],{"type":74,"value":1677},"Also check measured values against thresholds:",{"type":68,"tag":357,"props":1679,"children":1680},{},[1681,1693],{"type":68,"tag":361,"props":1682,"children":1683},{},[1684,1685,1691],{"type":74,"value":1320},{"type":68,"tag":137,"props":1686,"children":1688},{"className":1687},[],[1689],{"type":74,"value":1690},"InvocationServerErrors \u002F Invocations > 1%",{"type":74,"value":1692}," = active breach, HIGH",{"type":68,"tag":361,"props":1694,"children":1695},{},[1696,1697,1703],{"type":74,"value":1320},{"type":68,"tag":137,"props":1698,"children":1700},{"className":1699},[],[1701],{"type":74,"value":1702},"InvocationClientErrors \u002F Invocations > 5%",{"type":74,"value":1692},{"type":68,"tag":95,"props":1705,"children":1706},{},[1707,1721],{"type":68,"tag":99,"props":1708,"children":1709},{},[1710],{"type":68,"tag":103,"props":1711,"children":1712},{},[1713,1717],{"type":68,"tag":107,"props":1714,"children":1715},{},[1716],{"type":74,"value":1120},{"type":68,"tag":107,"props":1718,"children":1719},{},[1720],{"type":74,"value":1125},{"type":68,"tag":121,"props":1722,"children":1723},{},[1724,1736,1748,1760,1771,1783],{"type":68,"tag":103,"props":1725,"children":1726},{},[1727,1732],{"type":68,"tag":128,"props":1728,"children":1729},{},[1730],{"type":74,"value":1731},"Measured metric actively breaching a threshold",{"type":68,"tag":128,"props":1733,"children":1734},{},[1735],{"type":74,"value":1168},{"type":68,"tag":103,"props":1737,"children":1738},{},[1739,1744],{"type":68,"tag":128,"props":1740,"children":1741},{},[1742],{"type":74,"value":1743},"Zero Bedrock-related alarms configured",{"type":68,"tag":128,"props":1745,"children":1746},{},[1747],{"type":74,"value":1168},{"type":68,"tag":103,"props":1749,"children":1750},{},[1751,1756],{"type":68,"tag":128,"props":1752,"children":1753},{},[1754],{"type":74,"value":1755},"No throttle monitoring",{"type":68,"tag":128,"props":1757,"children":1758},{},[1759],{"type":74,"value":1168},{"type":68,"tag":103,"props":1761,"children":1762},{},[1763,1767],{"type":68,"tag":128,"props":1764,"children":1765},{},[1766],{"type":74,"value":1408},{"type":68,"tag":128,"props":1768,"children":1769},{},[1770],{"type":74,"value":1168},{"type":68,"tag":103,"props":1772,"children":1773},{},[1774,1779],{"type":68,"tag":128,"props":1775,"children":1776},{},[1777],{"type":74,"value":1778},"CloudTrail data events not enabled for bedrock-runtime",{"type":68,"tag":128,"props":1780,"children":1781},{},[1782],{"type":74,"value":1206},{"type":68,"tag":103,"props":1784,"children":1785},{},[1786,1791],{"type":68,"tag":128,"props":1787,"children":1788},{},[1789],{"type":74,"value":1790},"Missing cost alarm",{"type":68,"tag":128,"props":1792,"children":1793},{},[1794],{"type":74,"value":1206},{"type":68,"tag":77,"props":1796,"children":1797},{},[1798,1800,1805,1807,1813,1815,1820,1821,1827],{"type":74,"value":1799},"Note on metric names: The correct CloudWatch names are ",{"type":68,"tag":137,"props":1801,"children":1803},{"className":1802},[],[1804],{"type":74,"value":550},{"type":74,"value":1806}," (not ",{"type":68,"tag":137,"props":1808,"children":1810},{"className":1809},[],[1811],{"type":74,"value":1812},"ThrottledEvents",{"type":74,"value":1814},") and ",{"type":68,"tag":137,"props":1816,"children":1818},{"className":1817},[],[1819],{"type":74,"value":651},{"type":74,"value":1806},{"type":68,"tag":137,"props":1822,"children":1824},{"className":1823},[],[1825],{"type":74,"value":1826},"QuotaUtilization",{"type":74,"value":1828},"). Some documentation uses alternate names that return zero datapoints.",{"type":68,"tag":83,"props":1830,"children":1832},{"id":1831},"step-5-generate-report",[1833],{"type":74,"value":1834},"Step 5: Generate Report",{"type":68,"tag":77,"props":1836,"children":1837},{},[1838],{"type":74,"value":1839},"Output format:",{"type":68,"tag":1841,"props":1842,"children":1846},"pre",{"className":1843,"code":1845,"language":74},[1844],"language-text","# Bedrock Adoption Readiness Assessment\nAccount: \u003Caccount-id> | Regions: \u003Clist> | Date: \u003Ctoday>\nSurfaces: Standard Bedrock [Y\u002FN] | Mantle [Y\u002FN]\n7-Day Volume: \u003CN> invocations | 30-Day Spend: $\u003Camount>\nAssessment: READY \u002F READY WITH ACTIONS \u002F NOT READY\n\n## Dimension Status\n- D1 IAM: [ASSESSED \u002F NOT_ASSESSED: reason]\n- D2 Retention: [ASSESSED \u002F UNRESOLVED: needs confirmation]\n- D3 Quota: [ASSESSED \u002F INSUFFICIENT_DATA]\n- D6 Observability: [ASSESSED]\n\n## Findings\n[Sorted by severity, then dimension]\n\n| # | Finding | Severity | Dimension | Recommendation |\n|---|---------|----------|-----------|----------------|\n\n## Model Inventory\n| Model | Surface | Region | 7-Day Invocations | TPM Peak | Quota | % Used |\n|-------|---------|--------|-------------------|----------|-------|--------|\n\n## Priority Actions\n1. [Highest severity + remediation]\n2. [Next]\n3. [Next]\n\n## Next Steps\n- Immediate (CRITICAL)\n- This week (HIGH)\n- This month (MEDIUM)\n",[1847],{"type":68,"tag":137,"props":1848,"children":1850},{"__ignoreMap":1849},"",[1851],{"type":74,"value":1845},{"type":68,"tag":77,"props":1853,"children":1854},{},[1855],{"type":74,"value":1856},"Verdict thresholds:",{"type":68,"tag":357,"props":1858,"children":1859},{},[1860,1870,1880],{"type":68,"tag":361,"props":1861,"children":1862},{},[1863,1868],{"type":68,"tag":409,"props":1864,"children":1865},{},[1866],{"type":74,"value":1867},"READY",{"type":74,"value":1869},": 0 critical, \u003C=2 high, 0 unresolved, 0 NOT_ASSESSED",{"type":68,"tag":361,"props":1871,"children":1872},{},[1873,1878],{"type":68,"tag":409,"props":1874,"children":1875},{},[1876],{"type":74,"value":1877},"READY WITH ACTIONS",{"type":74,"value":1879},": 0 critical, (>2 high OR any unresolved OR any NOT_ASSESSED)",{"type":68,"tag":361,"props":1881,"children":1882},{},[1883,1888],{"type":68,"tag":409,"props":1884,"children":1885},{},[1886],{"type":74,"value":1887},"NOT READY",{"type":74,"value":1889},": Any critical finding",{"type":68,"tag":83,"props":1891,"children":1893},{"id":1892},"severity-definitions",[1894],{"type":74,"value":1895},"Severity Definitions",{"type":68,"tag":95,"props":1897,"children":1898},{},[1899,1919],{"type":68,"tag":99,"props":1900,"children":1901},{},[1902],{"type":68,"tag":103,"props":1903,"children":1904},{},[1905,1909,1914],{"type":68,"tag":107,"props":1906,"children":1907},{},[1908],{"type":74,"value":1125},{"type":68,"tag":107,"props":1910,"children":1911},{},[1912],{"type":74,"value":1913},"Definition",{"type":68,"tag":107,"props":1915,"children":1916},{},[1917],{"type":74,"value":1918},"SLA",{"type":68,"tag":121,"props":1920,"children":1921},{},[1922,1939,1956,1973,1991],{"type":68,"tag":103,"props":1923,"children":1924},{},[1925,1929,1934],{"type":68,"tag":128,"props":1926,"children":1927},{},[1928],{"type":74,"value":1148},{"type":68,"tag":128,"props":1930,"children":1931},{},[1932],{"type":74,"value":1933},"Immediate risk to security, data exposure, or unbounded cost",{"type":68,"tag":128,"props":1935,"children":1936},{},[1937],{"type":74,"value":1938},"Fix before production use",{"type":68,"tag":103,"props":1940,"children":1941},{},[1942,1946,1951],{"type":68,"tag":128,"props":1943,"children":1944},{},[1945],{"type":74,"value":1168},{"type":68,"tag":128,"props":1947,"children":1948},{},[1949],{"type":74,"value":1950},"Significant gap that will cause issues at scale",{"type":68,"tag":128,"props":1952,"children":1953},{},[1954],{"type":74,"value":1955},"Fix within 1 week",{"type":68,"tag":103,"props":1957,"children":1958},{},[1959,1963,1968],{"type":68,"tag":128,"props":1960,"children":1961},{},[1962],{"type":74,"value":1206},{"type":68,"tag":128,"props":1964,"children":1965},{},[1966],{"type":74,"value":1967},"Notable improvement opportunity",{"type":68,"tag":128,"props":1969,"children":1970},{},[1971],{"type":74,"value":1972},"Plan within 30 days",{"type":68,"tag":103,"props":1974,"children":1975},{},[1976,1981,1986],{"type":68,"tag":128,"props":1977,"children":1978},{},[1979],{"type":74,"value":1980},"LOW",{"type":68,"tag":128,"props":1982,"children":1983},{},[1984],{"type":74,"value":1985},"Minor optimization",{"type":68,"tag":128,"props":1987,"children":1988},{},[1989],{"type":74,"value":1990},"Address when convenient",{"type":68,"tag":103,"props":1992,"children":1993},{},[1994,1998,2003],{"type":68,"tag":128,"props":1995,"children":1996},{},[1997],{"type":74,"value":1219},{"type":68,"tag":128,"props":1999,"children":2000},{},[2001],{"type":74,"value":2002},"Observation, no action required",{"type":68,"tag":128,"props":2004,"children":2005},{},[2006],{"type":74,"value":2007},"N\u002FA",{"type":68,"tag":83,"props":2009,"children":2011},{"id":2010},"references",[2012],{"type":74,"value":2013},"References",{"type":68,"tag":357,"props":2015,"children":2016},{},[2017,2028,2039,2050,2061,2072,2083,2094],{"type":68,"tag":361,"props":2018,"children":2019},{},[2020,2022],{"type":74,"value":2021},"Bedrock Security: ",{"type":68,"tag":1048,"props":2023,"children":2026},{"href":2024,"rel":2025},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fsecurity.html",[1052],[2027],{"type":74,"value":2024},{"type":68,"tag":361,"props":2029,"children":2030},{},[2031,2033],{"type":74,"value":2032},"Bedrock Quotas: ",{"type":68,"tag":1048,"props":2034,"children":2037},{"href":2035,"rel":2036},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fquotas.html",[1052],[2038],{"type":74,"value":2035},{"type":68,"tag":361,"props":2040,"children":2041},{},[2042,2044],{"type":74,"value":2043},"Cross-Region Inference: ",{"type":68,"tag":1048,"props":2045,"children":2048},{"href":2046,"rel":2047},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fcross-region-inference.html",[1052],[2049],{"type":74,"value":2046},{"type":68,"tag":361,"props":2051,"children":2052},{},[2053,2055],{"type":74,"value":2054},"Model Invocation Logging: ",{"type":68,"tag":1048,"props":2056,"children":2059},{"href":2057,"rel":2058},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fmodel-invocation-logging.html",[1052],[2060],{"type":74,"value":2057},{"type":68,"tag":361,"props":2062,"children":2063},{},[2064,2066],{"type":74,"value":2065},"Inference Profiles: ",{"type":68,"tag":1048,"props":2067,"children":2070},{"href":2068,"rel":2069},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Finference-profiles.html",[1052],[2071],{"type":74,"value":2068},{"type":68,"tag":361,"props":2073,"children":2074},{},[2075,2077],{"type":74,"value":2076},"Data Retention: ",{"type":68,"tag":1048,"props":2078,"children":2081},{"href":2079,"rel":2080},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fdata-retention.html",[1052],[2082],{"type":74,"value":2079},{"type":68,"tag":361,"props":2084,"children":2085},{},[2086,2088],{"type":74,"value":2087},"Enforce ZDR with SCPs: ",{"type":68,"tag":1048,"props":2089,"children":2092},{"href":2090,"rel":2091},"https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fsecurity\u002Fenforce-zero-data-retention-on-amazon-bedrock-with-bedrock-projects-and-service-control-policies\u002F",[1052],[2093],{"type":74,"value":2090},{"type":68,"tag":361,"props":2095,"children":2096},{},[2097,2099],{"type":74,"value":2098},"CloudWatch Metrics TTFT & EstimatedTPMQuotaUsage: ",{"type":68,"tag":1048,"props":2100,"children":2103},{"href":2101,"rel":2102},"https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fimprove-operational-visibility-for-inference-workloads-on-amazon-bedrock-with-new-cloudwatch-metrics-for-ttft-and-estimated-quota-consumption\u002F",[1052],[2104],{"type":74,"value":2101},{"items":2106,"total":2209},[2107,2123,2138,2146,2162,2178,2194],{"slug":2108,"name":2108,"fn":2109,"description":2110,"org":2111,"tags":2112,"stars":27,"repoUrl":28,"updatedAt":2122},"aws-health-events","analyze AWS Health events for incidents","ALWAYS use this skill in the beginning of any incident investigation, root cause analysis, or operational troubleshooting. This skill retrieves and analyzes AWS Health events (service issues, scheduled changes, and account notifications) to identify AWS-side events that may explain or correlate with observed operational issues. Activate this skill when investigating an issue and you observe service degradation, elevated error rates, latency spikes, connection failures, throttling, capacity issues, deployment-related failures, alarms, or any operational event or issue. This skill searches AWS Health events by service, time window, region, and status to surface active or recent service disruptions, scheduled maintenance, and account-specific notifications that inform the current investigation. Also activate when a user requests a health event summary or report for their account over a specified time period.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2113,2114,2117,2119],{"name":26,"slug":8,"type":15},{"name":2115,"slug":2116,"type":15},"Debugging","debugging",{"name":2118,"slug":44,"type":15},"Incident Response",{"name":2120,"slug":2121,"type":15},"Monitoring","monitoring","2026-08-20T03:53:41.178955",{"slug":2124,"name":2124,"fn":2125,"description":2126,"org":2127,"tags":2128,"stars":27,"repoUrl":28,"updatedAt":2137},"aws-vpc-dns-investigation","investigate VPC DNS resolution issues","Use this skill when a name is not resolving as expected inside a VPC, or before applying a DNS control-plane change. Activate on symptoms such as NXDOMAIN or SERVFAIL from an EC2 instance, a hostname resolving to a public address when a private endpoint was expected, an AWS service endpoint that stopped resolving after a VPC endpoint or Route 53 change, an application reaching the wrong IP, resolution that works from one instance but not another, IPv6 or dualstack resolution differences, a suspected on-premises forwarding or hybrid DNS problem, or a request to check whether enabling private DNS, adding a Resolver rule, associating a private hosted zone, attaching DNS Firewall, or associating a Route 53 Profile would break anything. It drives the aws-vpc-dns-diagnostics MCP server to observe live resolution from inside the subnet and to simulate a proposed change before it is applied.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2129,2130,2131,2134],{"name":26,"slug":8,"type":15},{"name":2115,"slug":2116,"type":15},{"name":2132,"slug":2133,"type":15},"DNS","dns",{"name":2135,"slug":2136,"type":15},"Networking","networking","2026-08-20T03:53:46.027593",{"slug":4,"name":4,"fn":5,"description":6,"org":2139,"tags":2140,"stars":27,"repoUrl":28,"updatedAt":29},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2141,2142,2143,2144,2145],{"name":26,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"slug":2147,"name":2147,"fn":2148,"description":2149,"org":2150,"tags":2151,"stars":27,"repoUrl":28,"updatedAt":2161},"crm-production-investigation-guidelines","investigate CRM production incidents","Guidelines for investigating production incidents in the CRM application. Use when triaging any alert or incident involving the CRM REST API, SQS queues, Lambda functions, or Aurora DSQL database in this AWS account. Ensures thorough root cause analysis using AWS-native observability tools.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2152,2153,2156,2157,2158],{"name":26,"slug":8,"type":15},{"name":2154,"slug":2155,"type":15},"CRM","crm",{"name":2115,"slug":2116,"type":15},{"name":2118,"slug":44,"type":15},{"name":2159,"slug":2160,"type":15},"Operations","operations","2026-08-20T03:53:23.532781",{"slug":2163,"name":2163,"fn":2164,"description":2165,"org":2166,"tags":2167,"stars":27,"repoUrl":28,"updatedAt":2177},"database-migration-service-expertise","troubleshoot AWS Database Migration Service","AWS Database Migration Service (DMS) operational review and troubleshooting skill. Conducts best practices validation, health assessments, performance diagnostics, cost optimization reviews, and migration cutover guidance. Triggers on requests like \"DMS review\", \"DMS health check\", \"DMS troubleshooting\", \"migration assessment\", \"DMS best practices audit\", \"DMS cost optimization\", \"replication instance review\", \"CDC latency issue\", or \"DMS task failure\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2168,2169,2172,2173,2176],{"name":26,"slug":8,"type":15},{"name":2170,"slug":2171,"type":15},"Database","database",{"name":2115,"slug":2116,"type":15},{"name":2174,"slug":2175,"type":15},"Migration","migration",{"name":2159,"slug":2160,"type":15},"2026-08-20T03:53:23.927999",{"slug":2179,"name":2179,"fn":2180,"description":2181,"org":2182,"tags":2183,"stars":27,"repoUrl":28,"updatedAt":2193},"database-rds-devops","diagnose Aurora MySQL and PostgreSQL databases","Database-level data-plane diagnostics for Aurora MySQL and Aurora PostgreSQL. Executes predefined read-only health check queries via RDS Data API to analyze buffer pool, connections, locks, replication, storage, performance, and index efficiency. Requires the rds-aidba MCP server for database-internal access beyond what CloudWatch and RDS APIs provide.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2184,2185,2186,2187,2190],{"name":26,"slug":8,"type":15},{"name":2170,"slug":2171,"type":15},{"name":2115,"slug":2116,"type":15},{"name":2188,"slug":2189,"type":15},"MySQL","mysql",{"name":2191,"slug":2192,"type":15},"PostgreSQL","postgresql","2026-08-20T03:53:41.560344",{"slug":2195,"name":2195,"fn":2196,"description":2197,"org":2198,"tags":2199,"stars":27,"repoUrl":28,"updatedAt":2208},"eks-operation-review","audit Amazon EKS cluster operations","Comprehensive Amazon EKS operational review aligned with the AWS EKS Best Practices Guide. Use this skill when a user asks to review, audit, or assess EKS clusters for best practices compliance, operational readiness, security posture, cost optimization, reliability, networking, scalability, or upgrade readiness. Triggers on requests like \"EKS review\", \"EKS best practices audit\", \"EKS operational assessment\", \"review my EKS cluster\", or \"EKS health check\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2200,2203,2204,2207],{"name":2201,"slug":2202,"type":15},"Audit","audit",{"name":26,"slug":8,"type":15},{"name":2205,"slug":2206,"type":15},"Kubernetes","kubernetes",{"name":2159,"slug":2160,"type":15},"2026-08-20T03:53:20.524374",17,{"items":2211,"total":2374},[2212,2230,2245,2256,2271,2281,2296,2312,2326,2339,2350,2360],{"slug":2213,"name":2213,"fn":2214,"description":2215,"org":2216,"tags":2217,"stars":2227,"repoUrl":2228,"updatedAt":2229},"agents-build","add capabilities to existing agent projects","Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"agent auth\", \"streaming\", \"VPC\", \"VPC connectivity\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"migration issue\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"add payments capability to my agent\", \"wire payments plugin\", \"integrate x402 payments with the agent I'm building\", \"add MPP payments\", \"Machine Payments Protocol\". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI\u002Fdev-server errors: use agents-debug. Runtime x402\u002FMPP payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2218,2220,2223,2224],{"name":2219,"slug":35,"type":15},"Agents",{"name":2221,"slug":2222,"type":15},"Automation","automation",{"name":26,"slug":8,"type":15},{"name":2225,"slug":2226,"type":15},"Engineering","engineering",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-08-20T03:27:06.137661",{"slug":2231,"name":2231,"fn":2232,"description":2233,"org":2234,"tags":2235,"stars":2227,"repoUrl":2228,"updatedAt":2244},"agents-connect","connect agents to external services","Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: \"connect to API\", \"add gateway\", \"connect to MCP server\", \"Lambda tools\", \"OpenAPI\", \"gateway target\", \"Cedar policy\", \"restrict tools\", \"policy engine\", \"gateway auth error\", \"store API key\", \"outbound credential\", \"env var API key\", \"API key None after deploy\", \"credential not available after deploy\", \"should this be a gateway target\", \"give my agent tools\", \"add tools to agent\". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2236,2237,2240,2243],{"name":2219,"slug":35,"type":15},{"name":2238,"slug":2239,"type":15},"API Development","api-development",{"name":2241,"slug":2242,"type":15},"Authentication","authentication",{"name":26,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":2246,"name":2246,"fn":2247,"description":2248,"org":2249,"tags":2250,"stars":2227,"repoUrl":2228,"updatedAt":2255},"agents-debug","debug agent and environment issues","Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: \"agent not working\", \"wrong answer\", \"agent error\", \"tool call failing\", \"debug agent\", \"check logs\", \"read traces\", \"broken\", \"500 error\", \"424 error\", \"model access denied\", \"command not found\", \"stuck in DELETING\", \"maxVms exceeded\", \"cold start diagnosis\", \"cold start slow\", \"agentcore create error\", \"create failed\", \"exit code 7\", \"connection refused local dev\". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2251,2252,2253,2254],{"name":2219,"slug":35,"type":15},{"name":26,"slug":8,"type":15},{"name":2115,"slug":2116,"type":15},{"name":13,"slug":14,"type":15},"2026-07-16T06:00:44.679093",{"slug":2257,"name":2257,"fn":2258,"description":2259,"org":2260,"tags":2261,"stars":2227,"repoUrl":2228,"updatedAt":2270},"agents-deploy","deploy AI agents to AWS","Use when deploying your agent to AWS, or when a deploy has failed. Handles pre-flight validation, CDK\u002FIAM\u002Fquota error diagnosis, version management, rollback, and canary deployments. Triggers on: \"deploy my agent\", \"agentcore deploy\", \"deploy failed\", \"CDK error\", \"rollback\", \"canary deploy\", \"pin version\", \"redeploy\", \"deploy stuck\". Not for production hardening — use agents-harden. Not for adding capabilities before deploy — use agents-build or agents-connect. Not for VPC configuration errors — use agents-build.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2262,2263,2264,2267],{"name":2219,"slug":35,"type":15},{"name":26,"slug":8,"type":15},{"name":2265,"slug":2266,"type":15},"CI\u002FCD","ci-cd",{"name":2268,"slug":2269,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":2272,"name":2272,"fn":2273,"description":2274,"org":2275,"tags":2276,"stars":2227,"repoUrl":2228,"updatedAt":2280},"agents-get-started","scaffold and deploy new agent projects","Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: \"build an agent\", \"create an agent\", \"get started\", \"new project\", \"agentcore create\", \"which framework\", \"Strands vs LangGraph\", \"hello world agent\", \"first agent\", \"create MCP server\", \"host MCP server\", \"agentcore dev\", \"dev server\", \"what port\", \"local development\". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2277,2278,2279],{"name":2219,"slug":35,"type":15},{"name":26,"slug":8,"type":15},{"name":2268,"slug":2269,"type":15},"2026-07-12T08:42:51.963247",{"slug":2282,"name":2282,"fn":2283,"description":2284,"org":2285,"tags":2286,"stars":2227,"repoUrl":2228,"updatedAt":2295},"agents-harden","harden agents for production","Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: \"production checklist\", \"harden agent\", \"production ready\", \"secure agent\", \"inbound auth\", \"going live\", \"cold start optimization\", \"session lifecycle\", \"StopRuntimeSession\", \"quota\", \"throttling\", \"maxVms\", \"rate limit\", \"security audit of outbound API calls\", \"gateway target audit for production\", \"restrict who can call\", \"lock down endpoint\", \"only our app can call\". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2287,2288,2289,2292],{"name":2219,"slug":35,"type":15},{"name":26,"slug":8,"type":15},{"name":2290,"slug":2291,"type":15},"Best Practices","best-practices",{"name":2293,"slug":2294,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":2297,"name":2297,"fn":2298,"description":2299,"org":2300,"tags":2301,"stars":2227,"repoUrl":2228,"updatedAt":2311},"agents-optimize","optimize agent quality and performance","Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI\u002FCD quality gates, observability, or cost optimization. Triggers on: \"evaluate my agent\", \"add evaluator\", \"measure quality\", \"quality gate\", \"run evals\", \"agent too slow\", \"why is it slow\", \"reduce latency\", \"set up observability\", \"CloudWatch dashboard\", \"how much does my agent cost\", \"cost optimization\", \"logs not showing up\", \"logs missing\", \"spans not found\", \"eval failing\", \"eval error\", \"dev traces\", \"local traces\", \"agentcore dev traces\", \"traces to CloudWatch\". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2302,2303,2304,2307,2308],{"name":2219,"slug":35,"type":15},{"name":26,"slug":8,"type":15},{"name":2305,"slug":2306,"type":15},"Evals","evals",{"name":13,"slug":14,"type":15},{"name":2309,"slug":2310,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",{"slug":2313,"name":2313,"fn":2314,"description":2315,"org":2316,"tags":2317,"stars":2227,"repoUrl":2228,"updatedAt":2325},"agents-pay","handle x402 payments for agent tasks","Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: \"my agent hit a 402 while calling an API\", \"a tool call returned 402 Payment Required\", \"my agent needs to pay for x402-protected content\", \"let the agent pay for content, capped at $5 per session\", \"set a spend limit for the agent\", \"ProcessPayment failed\", or \"why did my agent refuse to pay\". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references\u002Fpayments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2318,2319,2320,2323],{"name":2219,"slug":35,"type":15},{"name":2221,"slug":2222,"type":15},{"name":2321,"slug":2322,"type":15},"Payments","payments",{"name":2324,"slug":2324,"type":15},"x402","2026-08-10T04:16:31.844309",{"slug":2327,"name":2327,"fn":2328,"description":2329,"org":2330,"tags":2331,"stars":2227,"repoUrl":2228,"updatedAt":2338},"amazon-aurora-mysql","manage Amazon Aurora MySQL clusters","Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically (MySQL-compatible engine, Aurora serverless, parallel query). Trigger for Aurora MySQL cluster operations, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or MySQL upgrade planning. Aurora MySQL uses full (VPC-based) configuration — express configuration is PostgreSQL-only. For Aurora PostgreSQL, use amazon-aurora-postgresql instead. Contains safety guardrails and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2332,2333,2334,2335],{"name":26,"slug":8,"type":15},{"name":2170,"slug":2171,"type":15},{"name":2188,"slug":2189,"type":15},{"name":2336,"slug":2337,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":2340,"name":2340,"fn":2341,"description":2342,"org":2343,"tags":2344,"stars":2227,"repoUrl":2228,"updatedAt":2349},"amazon-aurora-postgresql","configure Amazon Aurora PostgreSQL clusters","Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora serverless, express configuration, pgvector, Babelfish). Trigger for Aurora PostgreSQL cluster operations, express-configuration quick-start, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or PostgreSQL upgrade planning. For Aurora MySQL, use amazon-aurora-mysql instead. Contains safety guardrails, express-first routing, and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2345,2346,2347,2348],{"name":26,"slug":8,"type":15},{"name":2170,"slug":2171,"type":15},{"name":2191,"slug":2192,"type":15},{"name":2336,"slug":2337,"type":15},"2026-07-16T06:00:34.789624",{"slug":2351,"name":2351,"fn":2352,"description":2353,"org":2354,"tags":2355,"stars":2227,"repoUrl":2228,"updatedAt":2359},"amazon-bedrock","build generative AI apps with Amazon Bedrock","Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2356,2357,2358],{"name":2219,"slug":35,"type":15},{"name":26,"slug":8,"type":15},{"name":20,"slug":21,"type":15},"2026-08-07T04:38:13.03499",{"slug":2361,"name":2361,"fn":2362,"description":2363,"org":2364,"tags":2365,"stars":2227,"repoUrl":2228,"updatedAt":2373},"amazon-braket","run quantum computing workflows on AWS","Runs quantum computing workflows on AWS through Amazon Braket — discovering devices (QPUs and simulators) and their availability, building gate-model circuits and analog Hamiltonian programs, submitting quantum tasks, program sets and hybrid jobs, looking up prices, and capping spend with spending limits. Applies to any request about quantum computing, quantum hardware, quantum simulation, AHS, OpenQASM, or running a quantum algorithm on AWS.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2366,2367,2370],{"name":26,"slug":8,"type":15},{"name":2368,"slug":2369,"type":15},"Quantum Computing","quantum-computing",{"name":2371,"slug":2372,"type":15},"Simulation","simulation","2026-08-27T13:04:17.249442",142]