Skip to main content

TextQL Product Overview

Overview

TextQL’s platform combines a semantic Ontology layer with a suite of AI-powered tools to give Ana deep understanding of your business data. The Ontology takes in the disparate tables, objects, metadata, etc. from your various sources and creates a unified representation of all the most important concepts in your business.

In-depth

Once our ontology model comprehensively represents the key concepts in your business, we use that to power AI data analyst, Ana. Ana can perform complex queries, build models and take actions on your behalf. Ana is designed to meet your team where they are. → For technical users, Ana chats become powerful data notebooks that users can further refine for clear results. → For business users, Ana understands natural high level questions, providing clear and concise responses with relevant insights. Ana is also designed to seamlessly integrate with your workflows, whether that’s using Ana in Slack, embedded in your internal tools, or accessed programmatically through the API.

How Chats Work

Overview

Any time you use TextQL, you’re talking to Ana. Ana is a powerful AI data analyst powered by large language models. TextQL is model-agnostic — users with the appropriate permissions can choose from a range of models across providers including Anthropic, OpenAI, and others. See Model Management for configuration details and the Pricing page for the full list of supported models. Ana can be accessed through a variety of interfaces, meeting you where you are.

In-depth

Ana receives chats from whichever interface you’re talking to her in. She then uses a combination of tools to address the request. A typical flow proceeds as follows:
  1. The selected LLM processes the request and determines which tools to invoke (e.g., Text-to-SQL, Python, Ontology, Web Search).
  2. If data fetching is needed, Ana constructs SQL queries against your connected data sources via Text-to-SQL, or routes through the Ontology semantic layer when it’s enabled. The user can review and edit queries in the interface.
  3. Retrieved data is loaded into a secure, isolated Python sandbox where Ana can generate and execute code for analysis, modeling, and visualization.
  4. Ana reads the code’s output, giving it the chance to refine the analysis, fix mistakes, or perform follow-up steps.
  5. This tool-use loop continues until Ana has a complete answer, which is presented to the user along with any generated charts, tables, or artifacts.
Ana’s tool set is configurable per chat — see Tools for the full list of available capabilities.

Technical Deep Dive

Overview

Our systems are architected to ensure your data is secure at every step. From managing RBAC data governance to maintaining encryption throughout.
*On-Prem deployments are available for enterprise customers, contact us for more info. ** Model providers can be tailored based on customer requirements, contact us for more info.

In-Depth

Users interact through our various frontend interfaces — the web app, Slack, Microsoft Teams, embedded iframes, or the API. From there, encrypted requests are made to the Ana backend service, hosted on AWS. This service authenticates the request, enforces role-based access controls, and runs the Ana flow described previously. We do not store customer data in our environment, only certain metadata needed to perform Ontology data retrieval. Data is encrypted at rest and in flight. Any service that interacts with customer data is run in private subnets with no inbound access from outside TextQL. Outbound requests can be configured to an IP whitelist only.

On-Prem & Self-Hosted

Overview

For enterprises with especially sensitive data we support both on-prem and self hosted deployments.

In-Depth

We support multiple modes of deploying TextQL:
  • Managed Deployment
    • Managed Multi-Tenant
    • Managed Single-Tenant
  • Self Hosted Deployment
    • Docker Compose
      • We’ll provide a compose file for our application. The database can be run within Docker or on a managed service like RDS
The TextQL service relies on language models for multiple functions. TextQL is model-agnostic and supports a wide range of providers and models. Administrators can configure which models are available to their organization and control access per-role. See Model Management for details and the Pricing page for the full list of supported models and their costs.