Hex

Executes SQL, Python, and no-code cells in a cloud-hosted reactive compute environment where cell dependencies are automatically tracked and re-executed only when upstream cells change. Uses a dataflow execution model similar to spreadsheet recalculation, maintaining stateful session context across cell runs and supporting query pushdown to connected data warehouses to avoid materializing large datasets locally.

Natural language agent that generates, modifies, debugs, and documents SQL/Python code cells based on user prompts. The agent receives context from the current notebook state (cell values, data schemas), connected data sources, and optional semantic models (dbt-based metric definitions), then generates or edits code that executes in the reactive environment. Supports unlimited quick edits on Professional+ plans and trial access on free tier.

Manages connections to multiple data sources (Snowflake, Redshift, BigQuery, S3, generic SQL via SSH) with support for OAuth, SSH keys, and standard database credentials. Connections are workspace-level and can be shared across notebooks. Supports connection testing and credential rotation. Enterprise plan includes OIDC SSO for database connections.

Maintains version history of notebooks with snapshots at each execution or manual save. Users can view, compare, and rollback to previous versions. Version retention depends on plan: 7 days (free), 30 days (Professional), unlimited (Team+). Snapshots include cell code, execution results, and metadata (timestamp, author).

Provides read-only access to published apps and dashboards with ability to filter, drill-down, and interact with visualizations without viewing or editing underlying code. Explorer users cannot see SQL/Python cells, only the published results. Enables sharing insights with business stakeholders without exposing data warehouse queries or business logic.

Offers tiered compute profiles (Small through 4XL) with optional GPU acceleration (A10G, L4) for machine learning and heavy computation. Compute is billed per-minute for Large+ profiles; Medium compute is included on paid plans. Users can select compute profile per notebook run. GPU profiles enable faster model training and inference.

Provides observability APIs for monitoring notebook execution, tracking usage metrics, and auditing user actions in enterprise deployments. Enables integration with external monitoring tools (Datadog, New Relic, etc.). Includes audit logging for compliance and governance. Available on Enterprise plan only.

Enterprise plan option for deploying Hex in a single-tenant environment with HIPAA compliance, custom branding (white-label), and dedicated support. Enables embedding Hex analytics in customer-facing applications without Hex branding. Requires custom contract and pricing.

Multiple users can edit the same notebook simultaneously with real-time cursor tracking, comments, and conflict resolution. Permissions are split between code-level access (can edit/view cells) and published artifact access (can view/interact with dashboards). Supports version history (7-day to unlimited depending on plan) and scheduled runs with alerts. Multiplayer editing is available on all paid plans; free tier is single-user only.

No-code interface for building interactive dashboards and apps by dragging visualizations, tables, and input controls (filters, dropdowns, date pickers) onto a canvas. Apps are parameterized, allowing users to pass filter values that dynamically update underlying SQL/Python queries. Published apps support separate Explorer role (view-only drill-down access) and can be shared via URL or embedded. Supports custom branding (1-5 themes depending on plan) and scheduled exports via email/Slack.

Integrates with dbt projects to expose semantic models (standardized metric definitions, dimensions, relationships) to the Notebook Agent and Semantic Model Agent. Agents use semantic models to generate more accurate queries by referencing curated metrics instead of raw tables, reducing hallucination and enforcing business logic. Requires dbt project setup and Team+ plan ($75/editor/month) to access Semantic Model Agent.

Enables team members to discuss and iterate on code changes in a threaded conversation interface. The Threads Agent can explain code, suggest improvements, and generate alternative implementations based on team feedback. Threads are attached to specific cells or notebooks and maintain conversation history. Available on Team+ plan ($75/editor/month) only.

Automatically pushes SQL queries to connected data warehouses (Snowflake, Redshift, BigQuery) instead of materializing data locally. Hex's compute environment only downloads result sets, not full tables, allowing analysis of datasets larger than available memory. Query pushdown is transparent to users; no special syntax required. Reduces compute costs by leveraging warehouse compute instead of Hex's cloud infrastructure.

Allows teams to create and share reusable code blocks (SQL queries, Python functions, visualizations) as components that can be imported into other notebooks. Components are versioned and stored in collections, enabling code reuse across projects without duplication. Available on Team+ plan ($75/editor/month) only.

Exposes REST APIs to trigger notebook runs, retrieve results, and manage projects programmatically. Allows external tools (Airflow, Dagster, custom scripts) to execute Hex notebooks as part of data pipelines. API supports parameterized runs (passing filter values to notebooks) and result retrieval in JSON/CSV format. Available on Team+ plan ($75/editor/month) only.

Automatically executes notebooks on a schedule (daily, weekly, monthly, or custom cron) and sends results via email or Slack. Supports parameterized runs (e.g., run with different date ranges each day). Failures trigger alerts. Results can be exported as CSV, PDF, or embedded in Slack messages. Available on Team+ plan ($75/editor/month) only.