data-analytics Codex Plugin

Author: Data Analytics Maintainers
Category: Data & Analytics
Topics: Data Engineering & Analytics · Sales, Marketing & Business Ops · Monitoring & Observability
Version: 0.2.8
First cataloged: 2026-09-03 (UTC)
Explanation last updated: 2026-09-03 (UTC)
Source (GitHub) last updated: 2026-08-27 (UTC) (9 days ago)

The explanation below is AI-generated. Please verify it against the sources.

Data Analytics is an OpenAI-developed plugin that helps users turn product and business questions into evidence-backed answers. It provides guided workflows covering tasks such as diagnosing metric changes, designing KPI frameworks, building dashboards, sizing markets, and validating data quality. Work can begin from connected warehouses, BI or product analytics tools, documents, spreadsheets, uploaded files, or pasted results. Findings are turned into shareable reports, charts, dashboards, and notebooks. The plugin bundles a set of named skills and configuration for connecting to external apps and services.

About the service

This plugin is not itself a single SaaS but a connector layer that, when configured, can draw on a range of external services grouped by category: data warehouses and query engines such as Databricks, BigQuery, and Snowflake; product analytics and BI platforms such as Amplitude, Mixpanel, PostHog, Metabase, and ThoughtSpot; notebook environments such as Hex and Deepnote; and documentation, collaboration, email, and calendar tools such as Google Drive, Notion, Slack, Gmail, and Outlook.

What you can do with data-analytics

Get guided onboarding to pick a data source and workflow for a first task
Analyze a product or business question and receive a recommendation on where to focus
Diagnose why a specific metric moved and identify likely drivers
Design a KPI framework with outcome metrics, drivers, and guardrails
Turn recent metrics into a leadership-ready operating update
Build a dashboard with metrics, filters, and visual structure
Estimate market or opportunity sizing with stated assumptions
Produce an executive-style analytical report with charts and caveats
Improve or generate charts for presentations
Create a reproducible SQL or Python notebook
Run a QA review of an existing analysis before sharing it
Assess whether a given dataset or table is reliable enough to use

Sources

data-analytics plugin.json(opens in a new tab) (fetched: 2026-09-03 (UTC))
data-analytics README(opens in a new tab) (fetched: 2026-09-03 (UTC))

History of data-analytics

Codex Plugin 2026-09-03 (UTC) Added data-analytics

Back to list