Generative AI on AWS
Generative AI is a type of AI that can create new content and ideas, including conversations, stories, images, videos, and music. With generative AI on AWS, you can reinvent your applications, create entirely new customer experiences, drive unprecedented levels of productivity, and transform your business.
Recent questions
see all1 / 18
- On an AWS account I control, one Amazon Bedrock AgentCore Policy `CreatePolicyEngine` call in `sa-east-1` using temporary credentials from the assumed IAM role `sentinela-agentcore-v1-provisioner` ret...
- Hi, I completed AWS account verification but all Amazon Bedrock models are still returning "ValidationException: Operation not allowed" in both the Bedrock Playground and via API. ISSUE: All tested ...
- I am unable to access any Amazon Bedrock foundation models on my new AWS account in the ap-southeast-2 (Sydney) region. Every model in the Bedrock Playground returns the following error: "Validatio...
- I'm wondering why Sonnet 5.5 isn't available in ap-southeast-2? I don't understand why some models are available, but some aren't. Opus 5.5 and Haiku 5.5 are all available in ap-southeast-2, but not...
- Hello - I have free AWS Tenant , how can i get access to AWS Bedrock,since its not included . I had as well opened support case , but looks like my account is nor eligible .
- Hi! I’m building an app using Bedrock GPT-OSS-20B in Sydney (`openai.gpt-oss-20b-1:0`) through Converse, with tier `default`, medium reasoning and `maxTokens=8192`. I’d like to clarify two things bef...
- I have built a deterministic code generator called AssuredCode. For government and regulatory environments it has desirable features over LLM code generation. In programmatic prompt/spec scenarios for...
asked 3 days ago
- I need a conservative token bound before invocation so my application can reserve the maximum possible model cost. I use nonstreaming Converse with `openai.gpt-oss-20b-1:0` in `ap-southeast-2`, Stand...
- InvokeAgentRuntime operation: maxVms limit exceeded for account : 614090060499
- My account is more than a few months old and still hasnt been verified and the support tickets that i have submitted for account verification request have ben unassigned for over 2 weeks now. I really...
-  Whenever I try to access the AI models in the aws bedrock playground I get this error. Even I am not able to access cloud...
asked 5 days ago
- The Functor Model learns by modifications to model functions rather than parameters. This is a mathematical proof of distribution equivalence - https://zenodo.org/records/23125183 This document (https...
asked 6 days ago
- Hello, In Amazon Bedrock Agent Core I have a Harness and an MCP Server, that I can see at the ManagementConsole->Build->Runtime section. When I edit the Harness, I do not see the MCP Server, and I ca...
- Every Amazon Bedrock model call on my account fails with: ValidationException: Operation not allowed Environment Region: us-east-1 API: Converse (boto3), using a Bedrock API key Models tried: Amazo...
- I see that Claude Sonnet 5.5 is only available using the global inference profile (global.anthropic.claude-sonnet-5-5) at launch and not available in the region or geography specific profiles. (us.ant...
- How is Kiro adoption trending over the look-back period, daily active users, new-user onboarding, and per-user engagement depth and where is adoption stalling by client type (IDE vs CLI vs plugin) or ...
asked 9 days ago
- Summary Please add a native Export and Import capability for IAM Policies in the AWS console, scoped to accounts within the same AWS Organization. This would allow practitioners to replicate a policy...
asked 10 days ago
- We are using Amazon Q Developer (Copilot) through Amazon Bedrock. We would like to know: Which team is consuming how many tokens? Which individual user is consuming how many tokens? What is the recom...
Recent Knowledge Center content
see all1 / 18
Recent articles
see all1 / 18
ArmenioEXPERT
published 3 days ago0 votes260 views
Amazon Bedrock cross-Region inference raises throughput, but on its own it doesn't make an application resilient. This article is for builders and architects running Bedrock inference in production. I...published 7 days ago0 votes52 views
AgentCore Runtime runs each session in its own isolated microVM, lets the session continue on a new microVM, and gives you configurable lifecycles, persistent session storage and fast V2 snapshot cold...published 7 days ago0 votes49 views
AgentCore Runtime runs each session in its own isolated microVM, lets the session continue on a new microVM, and gives you configurable lifecycles, persistent session storage and fast V2 snapshot cold...published 8 days ago0 votes69 views
This article shows how to implement Bedrock's OTPS method: keep streaming and non-streaming traffic on separate identifiers, build per-identifier dashboards so cross-Region profiles and latency-optimi...Tolu Okuboyejo - AWSEXPERT
published 10 days ago0 votes69 views
When an Amazon Redshift cluster slows down, CloudWatch shows the symptom—high CPU and commit-queue pressure—but not which queries caused it or how to fix them. Answering that traditionally required a ...MikeLimEXPERT
published 12 days ago2 votes406 views
Configure ChatGPT Work/Desktop, Codex CLI and Codex IDE extensions to use Amazon Bedrock runtime with AWS profileMikeLimEXPERT
published 12 days ago2 votes346 views
Configure Claude Code CLI and Claude Code extension for VS Code on Amazon Bedrock with AWS profile- AWS OFFICIALUpdated 14 days ago1 votes61 viewsLearn about a prototype to connect account records and access policies to improve the operation of the licensed education content that you sell.
- AWS OFFICIALUpdated 14 days ago0 votes90 viewsLearn how to keep voice AI reliable on the shop floor with a hardware-first approach and an AWS reference architecture that's built on Amazon Nova 2 Sonic.
published a month ago0 votes124 views
A financial-services SRE team connected its self-managed APM to AWS DevOps Agent, then hit the real problem: the managed, AWS-hosted model reads that telemetry — and it holds regulated data. The artic...MikeLimEXPERT
published a month ago2 votes955 views
Configure Claude Desktop (Cowork/Chat/Code) to use Amazon BedrockMikeLimEXPERT
published a month ago2 votes488 views
Step by step guide to deploy LiteLLM based LLM Gateway on AWSAbdullah KaramanEXPERT
published a month ago0 votes319 views
AWS DevOps Agent's native code integration covers GitHub, GitLab, and Azure DevOps, but not Bitbucket at this time. This article shows how to register the Atlassian Rovo MCP server as a capability pro...- AWS OFFICIALUpdated a month ago2 votes222 viewsLearn how to build an assistant that students can use to get answers to their questions. The assistant is based on your institution’s own documents, with citations and policy guardrails.
Dubey, ShubhenduEXPERT
published a month ago0 votes151 views
AWS Agent Registry is now generally available, but most teams meet it mid-sprawl: dozens of agents and MCP tools scattered across accounts, with no shared inventory, no cross-team discovery, and no au...published a month ago0 votes126 views
Privately reach Amazon Bedrock AgentCore (Runtime and Memory) from a self-hosted EKS agent authenticated with IRSA/SigV4, inside a no-egress VPC. Covers the AWS STS interface endpoint and regional STS...Mario SagethEXPERT
published a month ago0 votes183 views
This article shows how to use reinforcement fine-tuning (RFT) on Amazon Bedrock to improve an open-weight model's ability to generate correct, tool-specific Tcl automation scripts for semiconductor an...Harish MandhadiEXPERT
published a month ago0 votes174 views
Amazon Bedrock now natively attributes every inference cost to the IAM principal that made the call. This post shows engineers and FinOps teams how to set it up and query it.
Recent selections
see all1 / 7
AWS OfficialMODERATOR
published a year ago0 votes455 views
This spotlight on Amazon Bedrock equips you with the skills and troubleshooting tips to get the most out of a dynamic service.Cheryl du PreezEXPERT
published a year ago1 votes1.5K views
How AWS Agentic AI tools are accelerating mainframe modernization- AWS OFFICIALUpdated 2 years ago0 votes119 viewsThis learning path is for DevOps engineers, researchers, operations analysts, data analysts, and business domain experts
- AWS OFFICIALUpdated 2 years ago0 votes133 viewsUse this selection as a learning path if you are a business decision maker and need to know how to use artificial intelligence technologies to improve your business operations.
- AWS OFFICIALUpdated 2 years ago0 votes210 viewsUse this learning path if you are a software developer interested in embedding ML predictions and AI services in your applications to solve a business problem.
- AWS OFFICIALUpdated 2 years ago0 votes115 viewsUse this learning path if you're a technical person who collects, cleans, and transforms data on a daily basis. You create machine learning models to make predictions. You are familiar with statistica...
Jonathan_DEXPERT
published 3 years ago3 votes16.1K views
How can you get started with Generative AI on AWS?
1 / 18
Giovanni Lauria
EXPERTOsvaldo Marte
EXPERTAdeleke Adebowale .J.
EXPERTTushar Jagdale
EXPERTGunasekaran, Makendran
EXPERTkranthi putti
EXPERTAlex T
EXPERTVitor Castellani
EXPERTMina Gobrial
EXPERTHayato Kosugi
EXPERTOlawale Olaleye
EXPERT
Learn AWS faster by following popular topics
1 / 4
