Data Analysis

Data analysis use cases have AI harmonize data from multiple sources, identify trends and patterns, and produce visualizations and insights. The AI handles the tedious work — cleaning, formatting, merging, and pattern recognition — while you direct the analysis and interpret the results.

Data analysis is often the highest-value primitive for teams that have data but lack the time or technical skills to extract meaning from it. AI dramatically lowers the barrier to working with data, letting anyone ask questions of their datasets in plain language.

Data Analysis is one of six use case primitives identified in OpenAI’s Identifying and Scaling AI Use Cases, adapted here to be platform-agnostic.

When to apply this primitive

Use Data Analysis when:

• You have data and need to extract meaning, patterns, or trends from it
• You need to harmonize data from multiple sources into a single view
• The deliverable is a chart, dashboard, trend report, or data-driven recommendation
• You want to explore a dataset to find what’s interesting before deciding what to investigate further

Not the right primitive when:

• The main output is code or a reusable tool for analyzing data — that’s Coding
• You’re gathering qualitative information from documents and sources — that’s Research
• You’re running a data pipeline on a schedule without human involvement — that’s Automation

Worked use cases

No worked examples published yet for this primitive.

Browse the full library for adjacent ideas, or design your own using the Deconstruct step of the AI Workflow Framework.

Related

• AI Use Cases Overview — the full library, searchable and filterable by primitive
• Context — providing datasets and domain knowledge
• Skills — packaging analysis workflows for repeatable use
• Coding — when the goal is the analysis tool itself, not the insight
• Automation — running analysis workflows on a schedule