nao

nao is an AI code editor designed specifically for data professionals, including analysts, analytics engineers, data scientists, and data engineers. It aims to accelerate data work by providing an integrated development environment (IDE) that understands and interacts with data, enabling users to ship data at business pace.

Key Features:

• AI code editor for data, natively integrated with data warehouses.
• Ability to create and run SQL pipelines, Python pipelines, and work with dbt.
• Native data connections to various data warehouses (Snowflake, BigQuery, PostgreSQL, Databricks, Redshift, Iceberg).
• Instant diff preview to see the impact of new code on data.
• AI agents for data quality checks, data diffs (checking consistency between dev and production tables), and running/summarizing tests.
• SQL auto-complete and SQL worksheets.
• AI tab on SQL console.
• dbt integration: preview dbt models, auto-complete on model columns, lineage graph, column-level lineage in agent, create models, docs & tests with agent.
• BI tool integration (Looker, Power BI, Metabase, Tableau) for lineage up to BI and table usage scoring.
• Data stays local and nothing is shared with LLMs unless allowed; no storage of code or schema, only embeddings.

Use Cases:

• Writing SQL queries and executing them.
• Building and managing dbt projects, including model preview and testing.
• Creating and running Python pipelines for data work.
• Performing data quality checks and ensuring data consistency between environments.
• Analyzing data and running analytics.
• Integrating with existing data warehouses and BI tools.
• Generating smart AI suggestions based on data schema.

Benefits:

• Ships data faster by streamlining data workflows.
• Reduces data quality issues and prevents breaking numbers & dashboards through instant diff previews and agent-led checks.
• Provides smart AI suggestions tailored to the user's data schema.
• Ensures data security and privacy by keeping data local and not sharing sensitive information with LLMs without explicit permission.
• Consolidates various data tools into a single IDE, improving efficiency.
• Facilitates collaboration and consistency within data teams.

• Develops and executes SQL queries with auto-complete functionality
• Creates SQL and Python data pipelines
• Manages dbt projects, including model previewing, column auto-completion, and lineage graph generation
• Generates dbt models, documentation, and tests
• Performs data analytics
• Connects natively to data warehouses including Snowflake, BigQuery, PostgreSQL, Databricks, and Redshift
• Provides instant diff previews for data impact visualization
• Conducts data quality checks
• Executes data diffs for consistency between development and production environments
• Summarizes and executes defined tests
• Integrates with BI tools (Looker, Power BI, Metabase, Tableau) for lineage tracking and table usage scoring
• Generates AI suggestions based on data schema
• Ensures data security by local processing and restricted LLM access, without storing user code or schema