TextQL
Enterprise AI data analyst agents that handle messy data workloads, integrating with existing platforms for natural language querying and automated dashboard creation.
Last verified:
What is TextQL?
TextQL is an AI data analytics platform that connects to your entire data stack—including data warehouses, databases, BI tools, and SaaS applications—and enables anyone in your organization to ask business questions in plain English and get actionable analysis without writing SQL. The platform's core AI agent, named Ana, acts as an AI data scientist that writes SQL queries, runs Python code for data transformations and statistical analysis, searches the web for real-time external data, and produces charts, reports, dashboards, and files through natural conversation.
Key features include Text-to-SQL for automatic query generation in your warehouse's specific dialect, Python sandbox for data transformations and chart generation, Ontology for governed metrics layers with consistent definitions, Playbooks for automated recurring reports delivered via email or Slack, persistent dashboards that auto-update, Slack integration for instant answers within team conversations, and support for 50+ data connectors including Snowflake, BigQuery, Redshift, Databricks, Postgres, MySQL, Tableau, and Power BI. TextQL works across your entire data stack without requiring ETL or data migration, joining marketing data from HubSpot with transactional data from Postgres and warehouse analytics from Snowflake in a single query.
TextQL is designed for everyone in an organization—not just data teams. Non-technical users in sales, finance, marketing, and operations can confidently explore data on their own using plain English questions, while data professionals save time previously spent on repetitive query writing and troubleshooting. The platform is built for enterprise use with SOC 2 Type II certification, HIPAA readiness, role-based access control, audit logging, and support for public cloud, VPC, or on-premises deployments where Ana runs entirely in your environment with your compute, storage, database, and LLMs.
TextQL pricing
Pricing model: Free
TextQL offers three subscription tiers billed monthly with usage-based pricing based on Agent Compute Units (ACUs). The Analyst tier is $0/month with 50,000 ACU monthly credit and overage rate of $2.00 per 1,000 ACUs, including up to 3 seats, unlimited connectors, secrets manager, ontology builder, and all integrations. The Team tier is $250/month with 216,666 ACU monthly credit and overage rate of $3.00 per 1,000 ACUs, including everything in Analyst plus unlimited seats, Role Based Access Control, Single Sign On, and priority support with 1-hour response. Enterprise tier has custom base price, custom monthly credit, and custom overage rates, including everything in Team plus dedicated infrastructure, embed or white-label TextQL, on-prem and VPC deployments, and dedicated account manager. Compute consumes 500 ACUs per instance-hour. AI inference is charged per 1M tokens with varying rates by model (Anthropic Opus/Sonnet/Haiku, OpenAI GPT-5, Kimi). Optional billing controls include Auto-Invoice (invoices in arrears) or Managed Invoice with account manager. Credit card payments accepted for ACU credit purchases ($10-$10,000 range).
TextQL pros
- No SQL required - ask business questions in plain English
- Connects to 50+ data sources simultaneously without ETL
- Works across entire data stack - join data from multiple sources in one query
- Ana is an agentic AI that runs end-to-end workflows autonomously
- No data migration or pipeline rebuilds required
- Get answers in minutes, not weeks - data team can query within 10 minutes
- Slack integration for instant answers without leaving conversations
- Persistent dashboards that auto-update from your data sources
- Playbooks schedule recurring reports delivered automatically via email or Slack
- Ontology provides governed metrics layer with consistent enforced definitions
- Web Search tool enriches analysis with real-time external market data
- Python sandbox for data transformations statistical analysis and chart generation
- Usage-based pricing not per seat - per-user cost approaches zero as organization grows
- SOC 2 Type II certified and HIPAA-ready for enterprise compliance
- Deploy anywhere - public cloud VPC or on-premises with complete data control
- Role-based access control and audit logging for security
- Unlimited connectors included in all subscription tiers
- Secrets manager for secure credential handling
- Embed or white-label Ana in your own application
- 100,000s of tables supported with no configuration needed
- Self-serve answers without analyst back-and-forth for business teams
- Autonomous agents monitor analyze and report on key metrics proactively
- Shared activity stream feed where agents publish insights for team
- Client SDKs available for Python and JavaScript/TypeScript
TextQL cons
- No free tier - Analyst plan starts at $0/month but requires 50,000 ACU monthly credit purchase
- Usage-based billing with ACUs can be complex to understand and predict
- Sandbox remains warm for 1 hour after activity consuming ACUs continuously
- 500 ACUs consumed per instance-hour for virtual compute resources
- AI inference charged separately based on input and output tokens processed
- Different AI models have varying capabilities and price points requiring selection
- Overage rates apply ($2-3 per 1,000 ACUs) beyond monthly allotment
- Minimum credit card purchase is $10 for ACU credits
- Fast Mode for Opus 4.6 costs 6× standard ACU rates
- Customer-managed endpoints require separate infrastructure provisioning and billing
- Web Search tool costs 50 ACUs per search
- Ontology requires manual setup or Ana assistance to build semantic layer
- No training required but writing better prompts needs practice for best results
- Customer-managed endpoint pricing is 0.25× standard rates but excludes token costs
- Enterprise deployment requires contacting sales for custom pricing
- Auto-Invoice billing receives two invoices monthly which may complicate accounting
- Managed Invoice requires dedicated account manager relationship
- Cache features provide cost savings but require proper configuration
- GPT-5.4 Mini and other mini models have limited token ranges under 272K
- On-premises setup requires specific network access and system administrator support
Frequently asked questions about TextQL
What is TextQL and how does it work?
TextQL is an AI data analyst that connects to your entire data stack and answers questions in plain language. Ana, TextQL's AI data scientist, connects to your data warehouses and systems of record so anyone in your organization can ask questions, run analyses, and get answers all in plain language. Ana writes SQL, runs Python, searches the web, and produces charts, reports, dashboards, and files through natural conversation without requiring SQL or Python knowledge.
How does Text-to-SQL work in TextQL?
When you ask a question, Ana intelligently processes your request through five steps: 1) Analyze Your Question - parses your natural language question to understand what data you're looking for, 2) Examine Database Schema - inspects your database structure to identify relevant tables and columns, 3) Generate SQL Query - constructs an optimized SQL query in your warehouse's specific dialect, 4) Execute Query - runs the query against your data warehouse securely, 5) Load Results - automatically loads results as a pandas DataFrame in the Python sandbox for further analysis. You can view both the SQL query and results in the chat interface.
What data sources does TextQL support?
TextQL connects to 50+ sources simultaneously including cloud data warehouses (Snowflake, BigQuery, Redshift, Databricks, Azure Synapse Analytics), traditional databases (Postgres, MySQL, Amazon Aurora MySQL, Supabase), and specialized databases (ClickHouse, MotherDuck, Athena). It also supports BI tools (Tableau, Power BI), SaaS applications (Salesforce, HubSpot, Google Drive), and other sources (SQL Server, Trino, YouTube Analytics). You can join HubSpot marketing data with Postgres transactional data and Snowflake warehouse analytics in a single query without moving or duplicating data.
How is TextQL different from other AI data tools?
TextQL works across your entire data stack without ETL required, connecting to 50+ sources simultaneously. It's an agent not a chatbot - runs end-to-end workflows autonomously like scheduling recurring reports via Playbooks, detecting anomalies proactively, and delivering insights via Slack or email without human intervention. It's built for everyone not just data teams - no SQL, no Python, no training required. TextQL charges for usage not per seat, so as your organization grows from 50 to 500 users the per-user cost approaches zero. It's enterprise-ready out of the box with SOC 2 Type II certification and HIPAA readiness.
What are Playbooks and how do they work?
Playbooks are automated analyses that run on a schedule. You can stop chasing reports and schedule the analyses that matter, getting them delivered automatically. Build playbooks directly in Threads with a playbook builder where you specify the playbook name, prompt, creator, tools, and datasets. Schedule playbooks to run at specific times (e.g., 9:00 AM daily) and deliver via email to multiple recipients. Playbook results can also be sent to Slack channels so teammates can read along and ask follow-up questions directly in Slack. You can deploy playbooks and view generated reports once run.
What is Ontology in TextQL?
Ontology is a structured semantic layer of your business data including metric definitions, entity relationships, and conventions that give Ana consistent precise knowledge of your data model. It provides a governed metrics layer for teams that need consistent enforced definitions. Ontology includes four building blocks: Objects (business entities), Attributes (properties of objects), Links (relationships between objects), and Metrics (attributes marked as measures or dimensions to optimize query performance). You can build your first ontology manually by creating objects attributes links and metrics, or have Ana create and modify it directly through chat. Ontology ensures consistency speed and security across your organization.
How does TextQL pricing work?
TextQL uses usage-based pricing charged in Agent Compute Units (ACUs) rather than per-seat pricing. There are three subscription tiers: Analyst at $0/month with 50,000 ACU monthly credit and $2.00 per 1,000 ACUs overage, Team at $250/month with 216,666 ACU monthly credit and $3.00 per 1,000 ACUs overage, and Enterprise with custom pricing. Compute consumes 500 ACUs per instance-hour. AI inference is charged per 1M tokens with varying rates by model (Anthropic, OpenAI, Kimi). When you start a workload a dedicated sandbox is provisioned that remains warm and available for 1 hour after your last activity consuming ACUs continuously. Optional billing includes Auto-Invoice or Managed Invoice, and credit card payments for ACU credit purchases ($10-$10,000).
Can I deploy TextQL on-premises or in my VPC?
Yes, TextQL supports flexible deployment options including public cloud, VPC, or on-premises. Ana runs entirely in your environment with the same simple setup, giving you complete control over your data and infrastructure. In on-premises or VPC deployments you use your compute, your storage, your database, and your LLMs. This deployment option is available for Enterprise clients with dedicated infrastructure. Customer-managed endpoints are available to non-SaaS deployments (VPC and on-prem configurations) where inference requests route through model serving infrastructure operated by your organization rather than TextQL. On-premises setup requires specific network access and you should contact your system administrator or email [email protected] for assistance.
How does the Slack integration work?
The Slack integration allows you to ask questions in Slack and get AI-powered insights from your data without leaving the conversation. You can tag @Ana in Slack messages to ask business questions like 'what was our customer churn rate last quarter?' and Ana will respond with answers based on your customer data including key insights broken down by categories. Multiple team members in a Slack channel can ask follow-up questions directly to Ana, and she responds with analysis. Playbook results can also be sent to Slack channels so teammates can read along and ask follow-up questions directly in Slack. The integration is included in all subscription tiers.
What security and compliance features does TextQL offer?
TextQL is SOC 2 Type II certified and HIPAA-ready for enterprise compliance. It includes role-based access control (RBAC) to manage who can access what using roles and permissions, audit logging to monitor security and administrative activity across your organization, and Single Sign-On (SSO) configuration with OIDC for enterprise authentication. TextQL also supports SCIM 2.0 provisioning to automate user and group lifecycle management. Network integration options let you choose how TextQL connects to your data sources based on your network and compliance requirements. A Security and Data Governance Whitepaper is available documenting all security features. Enterprise clients can deploy on-premises or in VPC for complete data control.