Listing Thumbnail

    Managed Support AI Assistants on Amazon Bedrock by Dedicatted

     Info
    Sold by: Dedicatted 
    For customer support teams whose AI assistant went live, but whose answers drift as products, policies and prices change, whose hand-offs to people are mis-routed, and whose failed conversations nobody reviews. Dedicatted operates your support assistant on Amazon Bedrock month to month: knowledge updates, answer quality reviews, escalation tuning, personalization rules and a monthly containment and quality report.

    Overview

    Who this is for

    SaaS, retail, telecom, travel and property technology companies in Canada, the United States and Europe with a customer-facing assistant or support agent on Amazon Bedrock or Amazon Connect, on web, mobile, chat or voice. The buyer is the VP Customer Support, Head of Customer Experience or product owner.

    The problem

    An assistant is accurate on launch day and drifts afterwards. Products and policies change but the knowledge does not, escalations go to the wrong queue, customers repeat themselves after hand-off, and nobody reads the conversations that failed. The team that built it has moved on to the next project.

    What we deliver

    Operations onboarding. We baseline containment, escalation, answer quality and customer satisfaction signals, build an evaluation set from real conversations, and map knowledge sources and their owners.

    Monthly operation. Our engineers update knowledge as products and policies change, review samples of failed and escalated conversations, tune prompts, Amazon Bedrock Guardrails and escalation rules, and run every change through the evaluation set before release.

    Personalization. Answers use what each customer is allowed to see, such as their plan, orders or account status, through governed tools, with the rules reviewed monthly.

    Reporting. A monthly report covers containment, escalations, answer quality findings and cost per conversation, with a quarterly conversation review.

    To build a new assistant, see Digital Concierge: GenAI Assistant for Web, Mobile, and Contact Center; for the AI platform layer only, see Managed AI Platform Operations on AWS by Dedicatted.

    AWS services integrated

    Amazon Bedrock, Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails, Amazon Bedrock AgentCore, Amazon Connect and Amazon Lex where voice or contact center is used, AWS Lambda, Amazon S3, Amazon DynamoDB and Amazon CloudWatch.

    Outcomes

    • Answers stay in step with your products, policies and prices.
    • Failed and escalated conversations are reviewed and fixed every month.
    • Every change passes the evaluation set before customers see it.
    • Containment, escalation and cost per conversation are reported monthly.

    Evidence

    Dedicatted holds the AWS AI Services Competency and is in the AWS Managed Service Provider Program. We built an AI-powered support transformation for a software company, published as a case study on our AWS Partner Solutions Finder profile, and a resident-facing concierge assistant for a Toronto smart-building software company whose AWS accounts we run under a managed service.

    Where we deliver

    Dedicatted is an AWS Premier Tier Services Partner and AWS Managed Service Provider headquartered in Toronto and Montreal, Canada. It is the first Canadian partner to hold both AWS AI Competencies (Generative AI and Agentic AI) and the first and only Canadian AWS Partner to hold the AWS Digital Sovereignty Services Competency. We deliver across Canada, the United States and Europe, in English and French, and support Canadian data residency in the AWS Canada (Central) and Canada West (Calgary) Regions.

    AWS infrastructure charges

    AWS bills you for Amazon Bedrock usage, Knowledge Bases, Guardrails, AgentCore, Amazon Connect and Lex where used, Lambda, S3, DynamoDB and CloudWatch. We work through IAM roles you create.

    Highlights

    • Your support AI assistant kept accurate after launch: knowledge updated as products, policies and prices change, failed and escalated conversations reviewed, and prompts, Amazon Bedrock Guardrails and escalation rules tuned through an evaluation set.
    • Personalized, governed answers: customers get answers based on what they are allowed to see through governed tools, with a monthly report on containment, escalations, quality findings and cost per conversation.
    • From an AWS Premier Tier Services Partner with the AWS AI Services Competency, whose AI-powered support transformation for a software company is published on our AWS Partner Solutions Finder profile.

    Details

    Delivery method

    Deployed on AWS
    New

    Introducing multi-product solutions

    You can now purchase comprehensive solutions tailored to use cases and industries.

    Multi-product solutions

    Features and programs

    Trust Center

    Trust Center
    Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.

    Pricing

    Custom pricing options

    Pricing is based on your specific requirements and eligibility. To get a custom quote for your needs, request a private offer.

    How can we make this page better?

    Tell us how we can improve this page, or report an issue with this product.
    Tell us how we can improve this page, or report an issue with this product.

    Legal

    Content disclaimer

    Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.

    Support

    Vendor support

    Contact

    Before you buy

    • A scoping call confirms the assistant, channels, knowledge sources and AWS accounts in scope and the quality measures that matter to your support team, followed by a written scope and a private offer through AWS Marketplace.

    During the service

    • Production incidents reach our engineers through the paging route agreed at onboarding, with response targets written into the private offer.
    • Other requests go by email or a shared channel, in English or French, with a named service lead and a monthly review.

    Response time

    • Requests that are not production incidents receive a response within two business days.

    Ending the service

    • The evaluation set, prompts, guardrail configuration, runbooks and the conversation review history stay with your team, and our access is removed.