Listing Thumbnail

    HCLTech re:play Fleet Supervisor AI Agent

     Info
    Sold by: HCLTech 
    HCLTech re:play turns any robotic fleet into a conversational system that responds to plain-language instructions over WhatsApp and web console. AI agents interpret requests, route them to specialists, and propose actions that supervisors approve before execution. Built for facilities teams managing cleaning robots, warehouse fleets, or any autonomous mobile robot deployment where human oversight and natural interaction matter.

    Overview

    Managing a robotic fleet should not require specialized dashboards that only a few trained operators can use. Facilities teams, warehouse supervisors and building staff need to interact with robots the same way they communicate with each other: through the messaging tools they already use every day.

    HCLTech re:play is an agentic conversational control layer that sits between your people and your robot fleet. Anyone can send instructions or report problems through WhatsApp or a web console using plain language. AI agents interpret those messages, determine the right action, and route tasks to the appropriate specialist agent. Every proposed action reaches supervisors as an approval prompt, and no robot moves without explicit human authorization.

    The system demonstrates its capabilities through a simulated fleet of nine cleaning robots operating across three floors of an office tower. Staff, or other building users can easily report spills or debris by sending a message or photo on WhatsApp. Supervisors can query fleet status, create tasks, pause robots, clear faults, and monitor everything through a live 3D console. The dispatch agent reads photos directly, classifies the issue as sweep, mop or hazard, determines location, checks robot availability and capability, then creates a task that waits for approval.

    The supervisor agent serves as the single entry point for all interactions. It interprets each message, answers simple queries directly, and routes complex requests to specialist agents. It maintains conversational memory so follow-up messages like "approve it" resolve correctly. It adapts responses based on the sender's role: supervisors receive fleet status and fault details, while general users get a limited view with no robot information. The agent takes facts only from live fleet data, asks one clarifying question when a request is ambiguous, and reports when guardrails refuse an action.

    Agents propose actions but never execute them autonomously. Deterministic code checks each proposed action against the sender's role and the fleet's operational rules, then logs the decision. Insights and communications agents handle diagnostics, fault alerts and shift reports. This architecture keeps AI in an advisory role while humans retain full control over fleet operations.

    The solution runs entirely on AWS services. Messaging flows through AWS End User Messaging Social for WhatsApp integration and Amazon SES for email. AI agents run on Amazon Bedrock with AgentCore orchestration. Fleet data and conversation history are stored in Amazon DynamoDB, with media files in Amazon S3. AWS Lambda functions handle message routing and approval workflows. Every interaction is logged with full audit trails, and data remains isolated within your AWS environment with encryption at rest and in transit.

    re:play moves robot fleet management out of vendor-specific dashboards and into the communication channels your teams already use. It reduces the training burden, expands who can interact with the fleet, and ensures that every robot action has clear human authorization and a complete audit trail.

    Highlights

    • Conversational Fleet Control - Operators and staff interact with robots through WhatsApp and web console using plain language, eliminating the need for specialized dashboards and expanding who can manage the fleet
    • Human-Approved Actions - AI agents propose every robot action as an approval prompt to supervisors, with deterministic code checking each action against sender roles and fleet rules before execution
    • Built on AWS Services - Runs on Amazon Bedrock AgentCore for AI orchestration, AWS End User Messaging Social for WhatsApp, Amazon SES for email, with DynamoDB, S3 and Lambda providing secure data storage and workflow automation

    Details

    Sold by

    Delivery method

    Deployed on AWS

    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

    Please contact us at awsecosystembu@hcltech.com  to know more on deployment and our support.