Sold by: NLSQL
Deployed on AWS
NLSQL AI Employee is an AI assistant for Microsoft Teams that runs in your AWS account, using Claude models on Amazon Bedrock. After a one-time Microsoft 365 sign-in, each user asks it in plain language to read, write and send email, manage the calendar and work with OneDrive files. It reads documents sent in chat, remembers what it is asked to, runs tasks on a schedule, sends a daily morning briefing and alerts users to important email and upcoming meetings. Other Azure Bot Service channels, such as Web Chat and Direct Line, work too, without the Microsoft 365 features. It deploys from one AWS CloudFormation template onto Amazon ECS with AWS Fargate, calls AWS only through the task's IAM role, and keeps your users' data in your own Amazon DynamoDB tables and S3 buckets.
Overview
Video
AI employee demonstration
Video
Functional AI employee demonstration
Video
Product video
AI Employee represents a groundbreaking advancement in business process automation, combining the power of Large Language Models (LLMs) with sophisticated AI agents to transform how organizations handle their daily cognitive tasks. This revolutionary platform serves as your intelligent digital workforce, capable of understanding, learning, and executing complex business operations with remarkable precision and efficiency. Key Features:
- Advanced Document Intelligence Seamlessly processes and modifies documents while preserving original formatting and design integrity Handles multiple file formats with intelligent content understanding Performs accurate translations while maintaining document structure Smart document analysis and information extraction capabilities
- Intelligent Email Management Automates email correspondence with human-like understanding Processes and categorizes incoming emails Composes and sends professional responses Manages attachments and follow-ups efficiently
- Enhanced Search & Analytics Implements reasoning-based search algorithms for more relevant results Performs deep data analysis across multiple sources Provides intelligent insights and recommendations Contextual understanding of search queries
- Cognitive Task Automation Streamlines decision-making processes through AI-powered analysis Automates routine cognitive tasks with high accuracy Adapts to specific business workflows and requirements Learns from interactions to improve performance over time Benefits: Significant time savings through automated task handling Reduced human error in routine operations Improves operational excellence Consistent quality in task execution Scalable solution that grows with your business Improved decision-making through data-driven insights Cost reduction in operational expenses Perfect for: Medium to large enterprises seeking operational efficiency Organizations with high-volume document processing needs Companies looking to modernize their workflow automation Businesses aiming to leverage AI for competitive advantage Teams requiring intelligent data analysis and processing AI Employee represents the next evolution in business process automation, offering a comprehensive solution that not only automates tasks but brings intelligence and reasoning to your daily operations. By combining advanced AI capabilities with practical business applications, it transforms how organizations handle information, make decisions, and manage workflows. Experience the future of work with AI Employee - where artificial intelligence meets practical business needs, delivering unprecedented efficiency, accuracy, and intelligence to your organization's operations.
Highlights
- AI employee for your company cognitive business processes automation
Details
Sold by
Delivery method
Supported services
Delivery option
NLSQL AI Employee on Amazon ECS (AWS Fargate)
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on a fixed subscription cost. You pay the same amount each billing period for unlimited usage of the product. Pricing is prorated, so you're only charged for the number of days you've been subscribed. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
- Monthly subscription
- $499.00/month
Vendor refund policy
100% refund within 30 days notice after deployment
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
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.
Delivery details
NLSQL AI Employee on Amazon ECS (AWS Fargate)
Supported services: Learn more
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Critical
- None.
Important
- The browser agent (with its live view) and image reading no longer need Google Gemini. With GeminiFeatures=Disabled, the default, they run on your Claude model in Amazon Bedrock, through the task role, and nothing is sent to Google. In 1.0.0 and 1.0.1 they were offered only with a Google Gemini API key.
- With GeminiFeatures=Enabled they run on Google Gemini with your own key, and switch to your Claude model whenever Gemini fails: no prepaid credits or billing, an invalid or expired key, a quota used up, or a model that is gone. The answer still comes, and the log group gets one line, for example Browser agent: Gemini failed (ModelProviderError, status 429); the main model () goes on with the task. Before, such a failure ended the browser task and the image question with an error.
- Without Gemini, each step of a browser task is one Bedrock call with a screenshot of the page, billed to your account like any other Bedrock use.
- New parameter BrowserAgent (default Enabled). Disabled offers no browser agent, routes no live view and leaves out the BrowserViewUrl output; image reading stays on. Choose it if you want no browser in the task.
- With BrowserAgent=Enabled, the live browser's paths (/vnc/, /websockify/, /api/browser-use/*) and the BrowserViewUrl output are part of the stack whatever GeminiFeatures says. Teams packages built with teams/build-package.sh then include the Browser-Use help tab; rebuild and upload the package once if your stack had GeminiFeatures=Disabled.
- To upgrade, update the stack with this version's template, whose ImageUri default is the 1.0.2 image. The tables, buckets and secrets are kept, so users stay signed in with their history and tasks.
Additional details
Usage instructions
NLSQL AI Employee 1.0.2 - Deployment Summary NLSQL AI Employee is an AI-powered employee assistant deployed on AWS using Amazon ECS and Fargate. It integrates with Microsoft Teams and Microsoft 365, using Claude through Amazon Bedrock to provide AI capabilities.
- Deployment Requirements
- Deploy using the AWS CloudFormation template.
- Supported AWS regions include US, Canada, South America, Europe and Asia-Pacific.
- Container image: 709825985650.dkr.ecr.us-east-1.amazonaws.com/nlsql/ai-employee:1.0.0
- Requires two public subnets across different Availability Zones.
- Prerequisites Before deployment, you must:
- Enable a Claude model in Amazon Bedrock and accept any required model access terms.
- Create a single-tenant Azure Bot and obtain its:
- Application ID
- Tenant ID
- Client secret
- Configure Microsoft Entra ID with Microsoft Graph permissions:
- openid, offline_access, User.Read
- Mail.ReadWrite, Mail.Send
- Files.ReadWrite
- Calendars.ReadWrite
- Grant administrator consent for the permissions.
- Optionally obtain a Google Gemini API key for browser automation and image-reading features.
- Deployment Steps
- Create an AWS Secrets Manager secret containing the Azure Bot client secret (AppPassword) and optionally the Gemini API key.
- Deploy the CloudFormation stack with:
- VPC ID
- Subnet IDs
- Secrets Manager ARN
- Microsoft App ID and Tenant ID
- Language model
- Optional Gemini feature configuration
- Acknowledge IAM capabilities and preserve successfully provisioned resources during the initial launch.
- Wait approximately 15 to 25 minutes for deployment to complete (CREATE_COMPLETE).
- Configure the Azure Bot messaging endpoint using the CloudFormation MessagingEndpoint output.
- Enable the Microsoft Teams channel.
- Add the OAuthRedirectUri output as a Web redirect URI in Microsoft Entra ID.
- Build and upload the Teams application package.
- Each Teams user must type login once to authenticate and connect Microsoft 365.
- Security and Data Management
- AWS KMS encrypts application secrets.
- A generated ENCRYPTION_KEY protects Microsoft 365 refresh tokens and must never be changed.
- Two encrypted DynamoDB tables provide point-in-time recovery.
- Two S3 buckets use server-side encryption and enforce TLS.
- Application data, including sign-ins, tasks, history and files, is retained when the stack is deleted.
- Load balancer access is restricted to CloudFront using a stack-specific security header.
- Bedrock global inference may process prompts in different commercial AWS Regions.
- Secret rotation requires updating the secret and forcing a new deployment.
- Health Monitoring
- HealthCheck: Returns HTTP 200 once the AWS Marketplace subscription is verified; otherwise returns 503.
- CloudWatch Logs: Records entitlement verification and reasons for task startup failures.
- ECS Console: Provides service events, task status and target health information.
- Costs and AWS Quotas In addition to the product subscription, AWS usage charges apply for:
- Fargate (default: 2 vCPU and 8 GB RAM).
- Load balancer and CloudFront.
- DynamoDB and S3.
- Secrets Manager (two secrets).
- CloudWatch Logs.
- Public IPv4 addresses.
- Amazon Bedrock token consumption.
- Scheduled tasks and alerts. Important: The AWS account requires an available Fargate vCPU quota of at least 4.
- External Dependencies The solution requires continuous internet connectivity and access to:
- AWS Marketplace Metering Service.
- Amazon Bedrock, DynamoDB, S3, Secrets Manager and CloudWatch.
- CloudFront and ECR.
- Microsoft Azure Bot Service and Bot Connector.
- Microsoft Entra ID and Microsoft Graph.
- Microsoft Teams and SharePoint. Google Gemini API and external websites are additional dependencies only when optional browser and image-reading features are enabled.
Resources
Vendor resources
Support
Vendor support
phone: +4407493859693, email: info@nlsql.com contact form:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
AI For HR helps deliver tailored engagement at scale across all employees. Enriching the experience along their journey from recruitment to retirement
AI Data Protection Gateway provides employees with a centralized interface for working with AI (Artificial Intelligence) while giving organizations control over access, security, and AI usage. The platform helps small and mid-sized businesses adopt AI services while reducing the risk of personal data and confidential business information being shared with external AI providers through employee prompts.
Workforce AI Security is Check Points platform for securing AI interaction across browsers, SaaS, desktop tools, code assistants, MCPs, and agents for all employees.
It delivers full visibility into AI usage of both sanctioned and shadow applications, so security teams can understand who is using which tools, what for, and what data is being shared.
Real time, contextual AI powered DLP safeguards sensitive data by blocking high risk actions and enforcing granular controls across apps, users, data types, and actions such as file uploads, prompts, and copy paste.
Together, Workforce AI Security gives organizations complete control over employees AI usage without slowing innovation.
In todays fast-paced world, efficiency is the key to success. Meet AI for Work, your ultimate AI-powered partner that helps employees at all levels to work smarter and faster. Whether accurately retrieving enterprise knowledge, streamlining routine tasks, optimizing workflows, or providing instant support, AI for Work is here to make work life easier and more productive
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.