{"resourceId":"aws-kiro-claude-haiku-5-5-govcloud-20261102","versions":[{"version":"external-6b83a7120db03624c5a28e38a69f95cab71819921e7f90f06600a2694b0254ed","resource":{"id":"aws-kiro-claude-haiku-5-5-govcloud-20261102","title":"Kiro adds Claude Haiku 5.5 in AWS GovCloud (US), completing the Claude 5.5 family for the agentic IDE and CLI there","organization":"Amazon Web Services (Kiro); Anthropic model","sector":"Government cloud; developer agents","geography":"United States (AWS GovCloud US Regions)","publishedAt":"2026-11-02","publicationDate":"2026-11-02","eventDate":null,"sourceName":"AWS What's New","sourceLabel":"Haiku 5.5 now available on Kiro in AWS GovCloud (US)","sourceUrl":"https://aws.amazon.com/about-aws/whats-new/2026/11/kiro-haiku-5-5-aws-govcloud-us/","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["developers-agents","infrastructure","governance-procurement"],"finding":"AWS announced on Nov 2 that Claude Haiku 5.5 is available in the Kiro IDE and CLI in the AWS GovCloud (US) Regions, so all three Claude 5.5 models are now in Kiro there. AWS positions Haiku 5.5 for high-volume, low-latency work such as summarising long context, classifying and routing requests, bulk text processing, small multi-file edits and parallel review subagents, with Opus 5.5 and Sonnet 5.5 doing harder planning. It has a 1M context window, a 0.06x credit multiplier and a 0.3x multiplier for requests over 100K tokens. The archive already holds Haiku 5.5 on Bedrock in GovCloud; this item is the Kiro developer-tool availability.","sledRelevance":"State and university development teams working inside GovCloud can now pick a cheaper, faster model tier for routine agentic coding tasks without leaving the boundary. Relevance is limited to organisations already using Kiro in GovCloud; no SLED customer or measured result is given.","evidence":"One-page vendor availability notice. No benchmark, accuracy, cost-per-task or customer data.","architectureImplications":"Model is selected in the Kiro IDE/CLI model picker after updating; work can be split so Haiku handles bulk or review subagent tasks while larger models plan.","governanceImplications":"Agencies should record which model tier each agent task uses, because cheaper models used as reviewers change the assurance of code review.","securityPrivacyImplications":"Remains inside GovCloud per the notice; the notice does not discuss data handling, logging or authorization status of Kiro itself.","caveats":"Vendor notice only. Authorization of Kiro in GovCloud for a given workload remains the agency's responsibility. Relevance limited to existing Kiro GovCloud users.","streamIds":["aws"],"roles":{"sales":"Position this as cost control for developer agents, not a new capability. Public-sector teams already using Kiro in GovCloud can route bulk and review work to a cheaper tier, which may stretch a fixed credit budget. Do not promise productivity gains: AWS gives no benchmarks. The useful conversation is how the customer budgets agent credits and which work they would trust to a smaller model, then a short trial that measures cost and rework against current practice.","engineering":"Engineering should treat Haiku 5.5 as one tier in a multi-model setup. Confirm the IDE/CLI version, the GovCloud Region, and how Kiro logs which model handled each request. Test it on the tasks AWS names, such as classification, summarising and parallel review, and compare defect rates with Sonnet 5.5. Check how the 0.3x multiplier above 100K tokens affects long-context jobs, and verify that model selection can be restricted by administrators if policy requires it.","delivery":"Delivery should add a model-tier policy to the existing Kiro rollout: which tasks may use Haiku, which need larger models, and who reviews agent changes. Run a short comparison on real backlog items, tracking credit use, rework and review findings. Update developer guidance and the change-management record. Treat any savings as proposals until measured, and revisit the policy when AWS changes multipliers or model availability."},"roleDetails":{"sales":{"customerProblem":"GovCloud development teams need to control agent credit spend while keeping routine coding work inside the boundary.","stakeholders":["Application development manager","State or university CIO","CISO","Budget office"],"discoveryQuestions":["Are you already using Kiro in GovCloud, and on which tasks?","How are agent credits budgeted today?","Which tasks would you accept a smaller model reviewing?"],"valueHypothesis":"Routing bulk and review tasks to a cheaper tier may lower credit use for teams already on Kiro in GovCloud; savings are unmeasured.","potentialEngagement":"A two-to-four-week model-tier comparison on one team's backlog, ending in a tier policy.","unsupportedClaims":["Productivity or quality gains","Workload authorization for Kiro","Any specific cost saving"]},"engineering":{"fit":"Teams already running Kiro in GovCloud; not relevant to non-Kiro or commercial-only users.","architectureIntegration":"Selected in Kiro IDE/CLI model picker; pairs with Opus/Sonnet 5.5 for planning in multi-agent workflows.","prerequisites":["Kiro in GovCloud enabled","Latest IDE/CLI version","Credit monitoring configured"],"constraints":["GovCloud US Regions only for this notice","Long requests over 100K tokens bill at 0.3x","No published benchmarks"],"security":"Confirm logging of model choice and that agency data handling rules for Kiro apply equally to the new tier.","proofOfValue":["Compare defect and rework rates against Sonnet 5.5 on the same tasks","Measure credit use per task","Verify admin control over model selection"]},"delivery":{"work":"Add a model-tier policy and run a measured comparison within the existing Kiro rollout.","dependencies":["Kiro authorization in the agency boundary","Credit budget","Code review process"],"ownership":"Application development manager owns tier policy; CISO approves data-handling scope.","skillsAdoption":"Developers need guidance on when to use each model tier and how to review subagent output.","governanceCheckpoints":["Policy approval before broad use","Review of comparison results","Re-check after AWS pricing or model changes"],"acceptanceCriteria":["Proposed: credit use per completed task tracked for all pilot tasks","Proposed: rework rate on Haiku tasks no higher than the baseline tier"],"risks":["Weaker review quality from smaller model","Cost surprises on long-context requests","Policy drift as models change"]}},"retrievedAt":"2026-11-03T04:02:03Z","enrichedAt":"2026-11-03T04:05:18Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Shifts developer effort toward orchestrating and reviewing agent output; no accessibility findings.","procurementImplications":"Credit multipliers (0.06x; 0.3x above 100K tokens) affect consumption budgeting; agencies should model spend by task type.","operatingModelImplications":"Supports a tiered model strategy for developer agents, which needs a documented policy on which tasks each tier may do.","sourceVerification":{"openedUrl":"https://aws.amazon.com/about-aws/whats-new/2026/11/kiro-haiku-5-5-aws-govcloud-us/","referenceExcerpt":"With Haiku 5.5, all three Claude 5.5 models are now available in Kiro in AWS GovCloud (US).","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}