Qlik Answers
Create AI-based assistants and AI-enabled applications with Qlik Answers. Ask questions and get answers from both structured and unstructured data sources.
Qlik Answers adds plug-and-play generative AI (GenAI) agents for Qlik Cloud.
Qlik Answers provides an agentic chat interface for asking questions and getting personalized, relevant answers. Answers are sourced using AI agents from curated structured and unstructured data sources, ensuring responses relevant to your needs. Users can view the sources that the agent used to create its answers, providing transparency over where the information comes from.
Qlik Answers supports both unstructured and structured data:
-
Unstructured data sources include file types such as HTML, DOCX, TXT, and PDF, which are added to knowledge bases and indexed. Qlik Answers assistants use knowledge bases to answer user questions.
-
Structured data sources are data from Qlik analytic applications. Applications can be made available to Qlik Answers for agentic conversations. Assistants can also include a single application as a content source. Combining your structured and unstructured data sources provides greater context to help Qlik Answers understand and interpret the structured data from your applications.
Qlik Answers can be useful for:
-
Providing conversational access to curated documentation, FAQs, and support content, allowing users to ask natural language questions and receive precise, contextual answers.
-
Enabling deep, agentic exploration of structured application data, allowing users to ask complex analytical questions that would traditionally require significant analyst effort.
-
Driving decision making by combining semantic understanding, business logic, and live application data in guided, multi step analytical workflows.
-
Generating sheets, charts, and analytical artifacts directly from conversational interactions within analytic applications.
-
Embedding agentic analytical experiences into external applications or websites, extending Qlik-powered insights beyond the Qlik environment.
Before beginning to use Qlik Answers, administrators should review Deploying and administering Qlik Answers.
To use the agentic Qlik Answers experience, you must opt in to cross-region data processing. This allows Qlik Cloud to temporarily process data outside your tenant region.
If you are using the legacy Qlik Answers experience (Q&A chatbot for unstructured data), you can choose to stay in-region by not opting in to cross-region processing. You can switch to newer models by opting in.
For details and the latest information about processing locations, see Enabling cross-region data processing.
Access to Qlik Answers depends on both user role and space permissions. For more information, see Qlik Answers access and permissions.
Qlik Answers workflows
The following outlines the best workflows for using Qlik Answers to provide an agentic generative AI chat experience, either using Qlik Answers directly with individual applications or Qlik Answers assistants.
Qlik Answers-available applications
- Prepare your application for Qlik Answers
Review your application and make sure it is optimized for use as a source for Qlik Answers.
- Make your application available to Qlik Answers
Make your application available to Qlik Answers.
Qlik Answers assistants
- Prepare your content sources
If you are using unstructured data, create your knowledge bases and add knowledge sources to them.
If you are using structured data, prepare your application for use with Qlik Answers.
- Create your assistant
Create your assistant and add content sources to the assistant.
- Customize the assistant chat experience
Add conversation starter questions and customize your chat.
- Make your assistant available
Make your assistant available to your users. Invite users to the space with your assistant or move the assistant to a space to which your users have access.
- Schedule the indexing of the content sources
Keep data sources up to date with scheduled indexing of data sources. Knowledge bases can have scheduled indexes.
Indexing knowledge base data sources
Applications are indexed after every reload, so schedule indexing by scheduling reloads.
- Manage the conversation history and improve your assistant
Review the history of conversations with your assistant, mark them as reviewed, and adjust the knowledge bases used by the assistant to provide better answers.
Qlik Answers guardrails
Qlik Answers implements the following guardrails when processing data into the large language model (LLM) and outputting it to Qlik Answers agents:
-
LLM monitoring for harmful content
Qlik Answers scans and rejects questions that contain invisible text or prompt injections.
-
Sanitization of Personal Identifying Information (PII) and secrets
Qlik Answers detects and removes PII data and secrets when sending data to the LLM. The detected information is added back when providing responses.
-
Hallucinations
Qlik Answers mitigates hallucinations by detecting contextual relevance in the provided content. Additionally, users can view the content used as a source to verify responses.
Qlik Answers and Insight Advisor
Qlik Answers replaces Insight Advisor and Insight Advisor Chat in tenants enabled for Qlik Answers. Insight Advisor and Insight Advisor Chat options and settings will also be hidden tenant-wide for applications. Qlik Answers provides a superior natural language interface for creating in-application content and exploring your data.
Qlik Answers and business logic
Business logic features in applications that do not apply to Qlik Answers are removed in tenants enabled for Qlik Answers. For the logical model, you retain access to Overview and Fields and Groups. The following tabs are removed:
-
Packages
-
Hierarchies
-
Behaviors
-
Calendar periods
For business logic vocabulary, you retain access to Synonyms. The following tabs are removed:
-
Custom analysis
-
Example questions
Once Qlik Answers is enabled, you cannot edit configurations in the hidden tabs.
If you have existing analyses that rely on settings configured in the hidden business logic tabs (such as custom behaviors or advanced configurations), you will not be able to modify these settings after enabling Qlik Answers.
Limitations
Qlik Answers has the following limitations:
-
The chat experience is supported for mobile browsers, but creating and managing knowledge bases and assistants are not optimized for standard mobile browser screen sizes.