Overview

Product video
QNL AI Assistant is a conversational analytics assistant for Qlik Sense Enterprise (client-managed). Business users type a question such as "What was our revenue by region in 2025?" and get a verified answer from their Qlik apps, with a chart or table and a short written insight. No dashboards to build and no expressions to write.
How it works An AI agent searches the Qlik app's data model (fields, master measures and dimensions), builds and previews the query on the Qlik Engine, checks the result, and only then answers. Built-in validation checks catch common mistakes such as wrong time periods, unmatched filter values or invalid set analysis expressions before the user sees a number. When a question is ambiguous (for example, several stores with similar names), the assistant asks the user to choose instead of guessing.
Key capabilities
- Natural language questions over Qlik Sense apps
- Follow-up questions with conversation memory ("now show it by month", "what about these products in 2024?")
- Answers as charts, tables and short insights based only on the returned data
- Excel export of results and PDF export of conversations
- Answers that combine your PDF documents (policies, regulations) with Qlik data
- Optional web search for external values such as exchange rates
- App-specific business rules (default periods, measure definitions, glossary) managed from the admin portal
- "How did you calculate this?" explanations showing the measures, filters and dimensions used
Security and deployment QNL AI Assistant is delivered as a Linux AMI and runs inside your own VPC. Users sign in with their Active Directory accounts (LDAPS), and queries run on the Qlik Engine as the signed-in Qlik user, so your existing Qlik security rules and section access still apply. You choose the language model provider: Azure OpenAI, Anthropic Claude or a self-hosted OpenAI-compatible model (such as vLLM). Qlik data stays in your environment; only the question context and query results are sent to the language model provider you configure. Secrets are stored encrypted with a local keystore.
Prerequisites
- Qlik Sense Enterprise (client-managed) reachable from your VPC (VPN or AWS Direct Connect), with certificate-based access
- Active Directory reachable over LDAPS
- Network access to your chosen language model provider
Highlights
- Natural language analytics for Qlik Sense: ask questions in plain language and get charts, tables and short insights in seconds, with no dashboards to build. Verified answers: the AI agent previews and checks every Qlik Sense query on the Qlik Engine before answering, and asks when a question is ambiguous. Runs in your own AWS account with Active Directory sign-in, your existing Qlik security rules, and the language model provider you choose.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
QNL AI Assistant is Bring Your Own License; no software fees are charged via AWS Marketplace. License purchases and refunds are handled by BIApps. Refund requests must be sent in writing to info@biapps.com within 30 days of purchase and are considered if the key was not activated or the software cannot run in your environment despite support. AWS infrastructure charges are billed by AWS and not refundable by BIApps. Contact: info@biapps.com , +44 7375624106.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Initial release of QNL AI Assistant.
- Natural language questions over Qlik Sense Enterprise (client-managed) apps
- Answers as charts, tables and short insights, with Excel and PDF export
- Follow-up questions with conversation memory
- Clarification when a question is ambiguous
- Combined answers from PDF documents and Qlik data
- Optional web search for external values
- Active Directory sign-in (LDAPS) with Qlik security rules and section access applied per user
- Admin portal for settings, language model provider, app-specific rules and user roles
- Configurable language model provider: Azure OpenAI, Anthropic Claude or self-hosted OpenAI-compatible model
- Linux (x86_64) AMI with backend, PostgreSQL and web interface behind nginx with TLS, started automatically on first boot
Additional details
Usage instructions
QNL AI Assistant runs as a self-contained appliance on this instance: PostgreSQL, the backend service and the web UI start automatically on boot (systemd unit "qnl"). Persistent data lives under /data, configuration in /opt/qnl/.env.prod.
PREREQUISITES
- A license key from BIApps (Bring Your Own License). Contact info@biapps.com if you do not have one.
- Network access from the instance to your Qlik Sense Enterprise server (ports 4242 and 4747), to your Active Directory (LDAPS, port 636), to your chosen LLM provider (Azure OpenAI, Claude or a self-hosted OpenAI-compatible endpoint such as vLLM) and to the license server checkuplicense.azurewebsites.net (HTTPS, port 443).
- Qlik client certificates exported from the QMC (client.pem, client_key.pem, root.pem).
- Security group: 443 for users, 22 for administrators. Port 80 only redirects to 443.
INITIAL SETUP
- Connect: ssh ec2-user@<instance-public-dns>
- Edit the configuration: sudo nano /opt/qnl/.env.prod Fill in the LDAP section (LDAP_SERVER_URL, LDAP_USER_DIRECTORY, LDAP_SEARCH_BASE); it is required for sign-in. Qlik and LLM settings can be entered here as well, or later from the admin portal (Admin > Settings) after signing in. Database password and JWT secret were generated on first boot; leave them as they are.
- Copy the Qlik client certificates to /data/qlik-cer
- Optional: place your own TLS certificate at /data/certs/seerver.key. Ifabsent, a self-signed certificate is generated.
- Apply: sudo
- Open https://<instance-public-dns> in a browser and sign in with ynt asDOMAIN\username. Until the first administrator is assigned, the ery signed-inuser; assign administrators under Admin > Users (or ADMIN_USERS inccess).
- Open Admin > License and enter your license key. Until a valid and the adminportal work but the chat is disabled. The license is re-validated a.
- Enter or review the Qlik connection and LLM provider under Admin > mediatelywithout a restart.
DAY-TO-DAY OPERATION
- Status: sudo
- Containers: sudo docker compose --env-file /opt/qnl/.env.mpose.prod.ymlps - Application MM-DD.log;container logs: sudo docker compose --env-file /opt/qnl/.env.mpose.prod.ymllogs -f backend
- Configurationv.prod, thensudo systemctl restart qnl. Settings saved from the admin portal aand takeprecedence over .env.prod.
- License: sta changes underAdmin > License.
- Business ruld from theadmin portal (Admin > Rules).
- PDF documenthem into/data/app/pdf_files/ on the instance (the folder is configurable up it under/data/app so it persists). New files are indexed automatically.
- Backup: the /data directory (database, application data, license,d/opt/qnl/.env.prod.
- Managed datar PostgreSQLinstead of the bundled database, set DATABASE_URL in .env.prod to ted container is then unused.
UPGRADE New versions s new instancefrom it, copy /data and /opt/qnl/.env.prod from the olinstance (for en run sudosystemctl restart qnl. Database schema migrations are applied automacense moveswith /data and does not need to be re-entered.
The full administrator guide is installed on the instance at /opt/qnl/README.md.
Resources
Vendor resources
Support
Vendor support
Support is provided by BiApps LTD by email at info@biapps.com and through https://biapps.com . We respond within one business day (Monday to Friday, 09:00-18:00 Turkey time, UTC+3).
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.