Agentic Data Engineering

Your data engineering agent

Vibedata is your data engineering agent. It builds and maintains data pipelines on the platform you already run. The agent works inside your environment, and gates decide what ships. You keep your platform, code and keys.

Try the sandbox Deploy from Your Cloud Marketplace Read how it works

You stay the accountable driver; your data engineering agent works across build and operate, with context carried across Intents and skills and tools, your own added as plugins. Every change passes the gates before it reaches your data platform. — You stay accountable; your data engineering agent works inside a boundary and ships through a gate

Look inside one Intent

AI needs data faster than your team can supply it

53% of a data engineer’s time goes to maintaining existing pipelines (Fivetran, 2026). Agents can take that load, given somewhere to be wrong on real data that production never sees, and guardrails they cannot reason around.

Demand from AI agents grows around the data team, alongside AI / ML and business intelligence workloads.

Watch the demand grow

The world the agent works in

The four things a general coding agent lacks for data work.

The world the agent works in: isolation, guardrails, context, and cross-platform close one boundary

Isolation

Being wrong is survivable, because a wrong attempt is disposable.

Guardrails

Scoped to the data platform: schema changes, warehouse writes, and the deploy path.

Context

Data engineering context: grain, freshness, and which mart the business reads.

Cross-platform

The same loop, skills and gates on DuckDB, Microsoft Fabric and MotherDuck, built natively on each. Each Intent reads and writes on its platform.

Every change is verified by running it against real data on your compute. Vibedata reads back metadata, code and execution traces, never your rows. The gates decide when work is done.

One loop, from intent to operations

Ship the change

Vibedata ships and changes data products, ingestion and transformation together, from intent to a deployed pipeline. It also fixes what it finds in production: it explains, investigates and remediates inside a bounded blast radius. It asks before it changes anything, and a person merges the pull request.

Find what's broken

Vibedata watches the platform and files problems and improvements as GitHub Issues, then picks them up to fix.

Three use cases, one process

Agentic data engineering on the platform you already run. Data Product Delivery builds a change, and Data Quality Assurance tests it against real data. Once it ships, Data Lineage & Traceability shows where each production number came from.

See the use cases

Data Product Delivery leads to Data Quality Assurance. Assurance leads to an independent promotion gate, and the gate leads to production. Data Lineage & Traceability reads production and ends in one of two outcomes: an explanation, or a new Intent that goes back to Data Product Delivery. From intent to trusted data. — Delivery and assurance feed the gate; lineage explains or opens new work

What's yours, and what's ours

Four open parts connect to your data engineering agent. Open language: dbt and dlt, open-source tools. Open code: your own GitHub repo, which you can walk away with. Open knowledge: memory and skills, growing. Open connectivity: MCP in, MCP out, APIs and integrations. The agent sits inside a dashed ring, Vibedata, and the four parts sit on the outer ring, yours. — Open language, code, knowledge and connectivity connect to your data engineering agent

Yours, and standard

Runs in your own cloud subscription, under your keys.
Writes dlt and dbt code you own, as your platform's own objects.
Model-tiered per lifecycle stage, on your own model keys and endpoints. The gate decides what ships.

Vibedata, and native per platform

A per-Intent isolated workspace, built natively on each platform, and the agent working inside it.
Real-data gates on every change, and an agent-proof deploy lock.
Intent: what you intend to take to production, from build into operate.

In production today

DuckDB
Microsoft Fabric
MotherDuck

Design partner open

Databricks
Redshift

Coming next

BigQuery
Oracle
Postgres
Snowflake

See it run

Two doors, the hosted sandbox on DuckDB with GitHub sign-in, and your cloud marketplace, deployed into your own subscription, lead to the same loop. You author a pipeline and it goes to a gate. If it fails, it goes back to the pipeline. If it passes, it ships. — Either door, one loop: author a pipeline, gate it, ship it once it passes

Sign in with GitHub for the hosted sandbox, seeded on DuckDB. Or deploy from your cloud marketplace into your own subscription.

Try the sandbox Deploy from Your Cloud Marketplace Read how it works

Questions

What is Vibedata?

Vibedata is your data engineering agent. It builds and maintains data pipelines on the platform you already run, adding the four things a general coding agent lacks for data work: isolation, guardrails, context and cross-platform. A person approves the spec, design and plan and merges the pull request.

Where does it run?

In your own cloud subscription, deployed from your cloud marketplace. There is no multi-tenant SaaS.

Which platforms does it support?

In production today: DuckDB, Microsoft Fabric and MotherDuck. Design partner open: Databricks and Redshift. Coming next: BigQuery, Oracle, Postgres and Snowflake.

How do I try it?

There are two equal ways in: a hosted sandbox seeded on DuckDB that needs no install and no tenant setup, or a deployment from your cloud marketplace into your own subscription. Sandbox sign-in is through GitHub.

Does it read my data?

It reads metadata, code and execution traces, never your rows. Profiling and verification run as queries on your own compute. Agents act under scoped, short-lived credentials, with tamper-evident, immutable audit logging.