Understand TextQL’s Pricing
Task Category | Operation | ACU Cost |
---|---|---|
Ontology | Creating a Metric | 2 |
Creating a Dimension | 2 | |
Documenting a Column | 2 | |
Retrieval | Planning | 5 |
Search | 15 | |
Select | 50 | |
Object Explorer Query | 50 | |
Metric Explorer Query | 50 | |
Load CSV | 25 | |
Analysis | Read Tableau Dashboard | 50 |
Cleaning (Python) | 20 | |
Visualize (Python) | 35 | |
ML Modeling (Python) | 125 | |
Presentation | App Creation (Streamlit) | 250 |
Generate Summary | 50 | |
Generate Recommendations | 100 | |
Create PDF Report | 250 | |
Schedule Run | 175 |
Optimization Lever | Why It Helps | How to Apply It |
---|---|---|
Reuse agent context instead of starting fresh Threads | A running Thread preserves chat history, intermediate calculations, and cached result sets. Building on that context prevents the agent from re‑discovering tables or regenerating plots it already created. |
|
Leverage a well‑curated Ontology | Columns, metrics, and dimensions registered in your Ontology steer Ana straight to the right data and filters, cutting exploration time. |
|
Embed known SQL snippets or table names in Playbooks | If Ana already knows where the data lives, she can skip search → sample → profile cycles. |
|
Why do some tasks require more ACUs than others?
Are there limits on seats or data sources?
What happens if I run out of ACUs before my period ends?
Do unused ACUs roll over?
Will TextQL increase my data warehouse computing costs?