New49 AI skills + Starflow methodology
Prompt in plain English. Starflow ships.
Starflow ships.
The what, not the how. Pipelines as configuration, not code. Talk to Starflow's five AI personas or invoke 49 CLI skills directly, all from your IDE.
See it in action
Three ways to ship a pipeline
Talk to a Starflow persona, ask Starflow what to do next, or call a CLI skill directly. Every interaction below is the real prompt and the real shape of the response.
Talk to a Starflow persona
Five expert AI personas cover the data lifecycle. Winston the Data Architect lays out two or three options with trade-offs before naming a recommendation, and names the failure mode of every choice.
Meet the personas →Ask Starflow what to do next
Starflow reads a manifest of skill dependencies and scans the artifacts you've already produced. It recommends the next required step based on real state, not a fixed checklist, so it works whether you started at discovery or jumped in mid-stream.
See the manifest model →Or call a CLI skill directly
For quick, targeted tasks, skip the methodology. Each of the 49 CLI skills knows the exact flags, YAML schema, and write strategies for its Starlake command. Ask in plain English; receive correct configuration on the first try.
Browse the catalog →Developer Experience
Your AI-Powered Data Engineering Toolkit
Talk to Starflow's five expert AI personas, invoke 49 CLI skills directly, or work visually in VSCode. Pick the entry point that fits the task.
Starflow Method
Guided lifecycle from discovery to deployment, with five expert AI personas
Greenfield project or migration? Talk to a persona. Starflow walks you through Discovery, Architecture, Pipeline Design, and Implementation, then runs an adversarial code review and an end-of-epic retrospective so nothing slips.
1. Discovery
Map data domains, sources, and ownership.
2. Architecture
Design layers, engines, schemas, and governance.
3. Pipeline Design
Specify extract, load, transform, orchestrate.
4. Implementation
Build, review, deploy, retrospect.
49 CLI Skills for Claude Code
One skill per Starlake command, ready to invoke from your AI assistant
For quick, targeted tasks, skip the methodology and call a CLI skill directly. Each skill teaches Claude every command, YAML pattern, and best practice, so it generates correct configurations on the first try.
Ingestion & Loading
Transform & Extract
Lineage & Quality
Orchestration & Ops
Starlake for VSCode
Prefer to point and click? The full data platform, inside your editor
From schema inference to DAG deployment, manage your entire data pipeline without leaving VSCode. Supports BigQuery, Snowflake, Redshift, Databricks, and DuckDB.
Auto Schema Inference
Automatically infer schemas from data sources and generate YAML configurations. No manual schema writing required.
SQL Preview & Dry Run
Write, preview, and execute SQL transformations with Jinja2 support. Validate before running expensive queries.
Lineage & ER Diagrams
Generate interactive ER diagrams, explore data lineage across pipelines, and review access controls visually.
One-Click Orchestration
Generate, dry-run, and deploy workflow DAGs for Airflow and Dagster directly from your editor.
Starlake integrates effortlessly for maximum flexibility.
Features
Focus more on business value, less on pipelines
No-Code Ingestion
Through declarative configuration, data is validated, transformed and loaded into your data warehouse without writing a single line of code.
Low-Code Transformations
Declare the datasets you need and the transformations you want to apply, the write strategy and the rules you want to enforce, and let Starlake do the rest.
Automated Workflows
Let Starlake infer your model dependencies and apply predefined and custom Airflow® or Dagster® templates to automate your workflows.
AI-Powered Tooling
Build pipelines from your IDE with an intelligent VSCode extension and 48 AI skills that turn Claude Code into your Starlake expert.
Revolutionize Your Data Workflows
Comprehensive Solutions for Every Stage of Your Pipeline
From no-code ingestion to low-code transformations, Starlake automates workflows and enforces data governance, giving you the power to manage data at scale with ease and accuracy.
No-Code Data Ingestion
Extract and load data from diverse sources into your data warehouse without writing a single line of code. Validate, transform, and secure your data effortlessly
Low-Code Transformations
Use YAML and SQL to define transformations without complex scripting. Apply rules, enforce schema, and process data at scale with ease.
Data Governance and Quality
Ensure data consistency and compliance with schema enforcement, validation rules, and automated quality checks at every stage.
Automated Workflow Orchestration
Automate dependencies and workflows with Airflow or Dagster templates. Focus on delivering insights while Starlake manages the execution.
Revolutionize Your Data Workflows
Comprehensive Solutions for Every Stage of Your Pipeline
From no-code ingestion to low-code transformations, Starlake automates workflows and enforces data governance, giving you the power to manage data at scale with ease and accuracy.
Code less, deliver more
Declare the ingestion and transformation outcomes and let Starlake and your data warehouse take care of the underlying logic.
- Don't code, declare your intent using YAML or our browser based UI
- Infer dependencies and automate workflows
- Reuse orchestration templates among models and projects
Software Engineering for Data
Develop and test your workload locally and deploy globally. Use your native SQL dialect both on your test and production environments.
- Test your load and transformation logic locally
- Validate pipelines on small datasets first
- Support for major data warehouses
Complete Data Lifecycle Management
Starlake covers the entire data lifecycle, from data ingestion to data monitoring, including data validation, transformation and orchestration.
- Extract from source database or middleware in full or incremental mode
- Infer schema and data types from your inputs
- Apply transformations using SQL SELECT statements
Data Governance with Contracts
Keep your lakehouse from becoming a dataswamp using automated testing, schema enforcement, and validation rules.
- Schema enforcement ensuring data consistency
- Transformation logic governed by rules
- Data quality tracked and aligned with SLAs
SLA Commitments & Monitoring
Track Service Level Agreements (SLAs) to ensure data services meet the expected standards of quality, availability, and performance.
- Clear availability and freshness metrics
- Real time monitoring and auditing
- Historical analysis of issues
Flexible Deployment Options
Deploy Starlake on your own infrastructure or use our SaaS offering. Focus on your business while we handle the infrastructure.
- Serverless SaaS offering available
- Self-hosted Docker deployment option
- Ultra light infrastructure footprint