|
| 1 | +--- |
| 2 | +sidebar_position: 1.6 |
| 3 | +sidebar_label: What can PromptQL do? |
| 4 | +description: |
| 5 | + "Learn what PromptQL can do to help you make decisions quicker or automate tasks with relability and accuracy." |
| 6 | +keywords: |
| 7 | + - promptql |
| 8 | + - accurate |
| 9 | + - reliable |
| 10 | + - capabilities |
| 11 | +toc_max_heading_level: 4 |
| 12 | +--- |
| 13 | + |
| 14 | +import Thumbnail from "@site/src/components/Thumbnail"; |
| 15 | + |
| 16 | +# What can PromptQL do? |
| 17 | + |
| 18 | +## Introduction |
| 19 | + |
| 20 | +PromptQL combines data analysis, AI capabilities, and automation tools into a conversational interface. It's designed to |
| 21 | +help you explore data, make decisions, and create reliable workflows—all through natural dialogue. |
| 22 | + |
| 23 | +## Core features |
| 24 | + |
| 25 | +### Agentic Semantic Metadata Layer |
| 26 | + |
| 27 | +PromptQL doesn't just execute queries—it builds and maintains a dynamic understanding of your data landscape. This |
| 28 | +"semantic metadata layer" grows more sophisticated with each interaction, learning your business terminology, data |
| 29 | +relationships, and analytical patterns. |
| 30 | + |
| 31 | +When you correct a definition or clarify a business rule, PromptQL remembers. It uses this knowledge to: |
| 32 | + |
| 33 | +- Translate natural language to precise queries |
| 34 | +- Apply consistent business rules across analyses |
| 35 | +- Suggest relevant connections between datasets |
| 36 | +- Self-correct based on feedback |
| 37 | + |
| 38 | +Think of it as an intelligent layer between you and your data that learns and adapts. It remembers that "active users" |
| 39 | +means something specific in your business, or that certain metrics should always be filtered in particular ways. |
| 40 | + |
| 41 | +:::info Learn more |
| 42 | + |
| 43 | +You can learn more about PromptQL's semantic understanding [here](/data-modeling/overview.mdx). |
| 44 | + |
| 45 | +::: |
| 46 | + |
| 47 | +### AI Primitives |
| 48 | + |
| 49 | +At its core, PromptQL works with data and AI functions, which we call **AI primitives**. It's helpful to think of these |
| 50 | +as tools in PromptQL's toolbox. |
| 51 | + |
| 52 | +For data, PromptQL can run complex SQL queries with built-in safety checks and optimization. It handles joins, and |
| 53 | +aggregations naturally, with automatic error handling and self-correction. |
| 54 | + |
| 55 | +The AI functions extend these capabilities beyond pure data analysis: |
| 56 | + |
| 57 | +| Primitive | Description | |
| 58 | +| --------- | -------------------------------------------- | |
| 59 | +| Classify | Sort text into dynamic categories. | |
| 60 | +| Summarize | Create concise summaries of longer text. | |
| 61 | +| Extract | Pull structured data from unstructured text. | |
| 62 | +| Visualize | Create interactive data visualizations. | |
| 63 | + |
| 64 | +By combining these primitives, PromptQL can tackle complex analytical tasks. For example, it might extract structured |
| 65 | +data from a batch of documents, classify the results, and visualize the patterns—all in a single workflow. Or it could |
| 66 | +summarize a large dataset, then extract key metrics from those summaries for deeper analysis. |
| 67 | + |
| 68 | +These combinations aren't just powerful—they're precise. Each primitive builds on the others, with error checking and |
| 69 | +validation at every step. The result is reliable, reproducible analysis that can be turned into automated workflows. |
| 70 | + |
| 71 | +:::info Learn more |
| 72 | + |
| 73 | +You can learn more about these primitives [here](/promptql-apis/execute-program-api.mdx#introduction). |
| 74 | + |
| 75 | +::: |
| 76 | + |
| 77 | +### Artifacts |
| 78 | + |
| 79 | +Think of artifacts as PromptQL's memory system. When you're exploring data or building workflows, artifacts help |
| 80 | +maintain context and enable reuse. |
| 81 | + |
| 82 | +| Type | Purpose | |
| 83 | +| ------------- | ---------------------------------------- | |
| 84 | +| Table | Store and reference structured data | |
| 85 | +| Text | Preserve documents and long-form content | |
| 86 | +| Visualization | Interactive charts and graphs | |
| 87 | +| Automation | Reusable, parameterized workflows | |
| 88 | + |
| 89 | +:::info Learn more |
| 90 | + |
| 91 | +You can learn more about artifacts [here](/promptql-playground/artifacts.mdx). |
| 92 | + |
| 93 | +::: |
| 94 | + |
| 95 | +## Use cases |
| 96 | + |
| 97 | +### Make decisions |
| 98 | + |
| 99 | +When it comes to decision-making, PromptQL acts as your analytical partner. It can explore data, detect patterns, |
| 100 | +visualize trends, and run comparisons. Each analysis can be saved for future reference, shared with your team, or used |
| 101 | +as part of your audit trail. |
| 102 | + |
| 103 | +The key is that PromptQL doesn't just show you numbers—it helps you understand them. Ask it to explain its methodology, |
| 104 | +break down complex metrics, or look at the same data from different angles. It's built to clarify, not just calculate. |
| 105 | + |
| 106 | +[Learn more](/decision-making.mdx) about making decisions with PromptQL. |
| 107 | + |
| 108 | +### Automate tasks |
| 109 | + |
| 110 | +Once you've found a valuable analysis pattern, PromptQL can turn it into a reliable automation. These aren't just saved |
| 111 | +queries—they're full workflows that can process new data, generate reports, monitor metrics, or alert on conditions. |
| 112 | + |
| 113 | +Each automation comes with built-in error handling and can be parameterized to handle different inputs. Chain them |
| 114 | +together for more complex operations, or schedule them to run regularly. The goal is to turn your one-off analyses into |
| 115 | +reliable, repeatable processes. |
| 116 | + |
| 117 | +[Learn more](/automation.mdx) about automating tasks with PromptQL. |
0 commit comments